Index

_

__init__() (cvnets.anchor_generator.base_anchor_generator.BaseAnchorGenerator method) (cvnets.anchor_generator.ssd_anchor_generator.SSDAnchorGenerator method) (cvnets.image_projection_layers.attention_pool_2d.AttentionPool2dHead method) (cvnets.image_projection_layers.base_image_projection.BaseImageProjectionHead method) (cvnets.image_projection_layers.global_pool_2d.GlobalPool2D method) (cvnets.image_projection_layers.simple_projection_head.SimpleImageProjectionHead method) (cvnets.layers.activation.gelu.GELU method) (cvnets.layers.activation.hard_sigmoid.Hardsigmoid method) (cvnets.layers.activation.hard_swish.Hardswish method) (cvnets.layers.activation.leaky_relu.LeakyReLU method) (cvnets.layers.activation.prelu.PReLU method) (cvnets.layers.activation.relu.ReLU method) (cvnets.layers.activation.relu6.ReLU6 method) (cvnets.layers.activation.sigmoid.Sigmoid method) (cvnets.layers.activation.swish.Swish method) (cvnets.layers.activation.tanh.Tanh method) (cvnets.layers.adaptive_pool.AdaptiveAvgPool2d method) (cvnets.layers.AdjustBatchNormMomentum method) (cvnets.layers.AvgPool2d method) (cvnets.layers.base_layer.BaseLayer method) (cvnets.layers.conv_layer.Conv2d method) (cvnets.layers.conv_layer.NormActLayer method) (cvnets.layers.conv_layer.TransposeConvLayer2d method) (cvnets.layers.Dropout method) (cvnets.layers.dropout.Dropout method) (cvnets.layers.dropout.Dropout2d method) (cvnets.layers.Dropout2d method) (cvnets.layers.Embedding method) (cvnets.layers.embedding.Embedding method) (cvnets.layers.Flatten method) (cvnets.layers.flatten.Flatten method) (cvnets.layers.global_pool.GlobalPool method) (cvnets.layers.GlobalPool method) (cvnets.layers.GroupLinear method) (cvnets.layers.Identity method) (cvnets.layers.identity.Identity method) (cvnets.layers.linear_attention.LinearSelfAttention method) (cvnets.layers.linear_layer.GroupLinear method) (cvnets.layers.linear_layer.LinearLayer method) (cvnets.layers.LinearLayer method) (cvnets.layers.LinearSelfAttention method) (cvnets.layers.MaxPool2d method) (cvnets.layers.multi_head_attention.MultiHeadAttention method) (cvnets.layers.MultiHeadAttention method) (cvnets.layers.NormActLayer method) (cvnets.layers.normalization.batch_norm.BatchNorm1d method) (cvnets.layers.normalization.batch_norm.BatchNorm2d method) (cvnets.layers.normalization.batch_norm.BatchNorm2dFP32 method) (cvnets.layers.normalization.batch_norm.BatchNorm3d method) (cvnets.layers.normalization.group_norm.GroupNorm method) (cvnets.layers.normalization.instance_norm.InstanceNorm1d method) (cvnets.layers.normalization.instance_norm.InstanceNorm2d method) (cvnets.layers.normalization.layer_norm.LayerNorm method) (cvnets.layers.normalization.layer_norm.LayerNorm2D_NCHW method) (cvnets.layers.normalization.layer_norm.LayerNormFP32 method) (cvnets.layers.normalization.sync_batch_norm.SyncBatchNorm method) (cvnets.layers.normalization.sync_batch_norm.SyncBatchNormFP32 method) (cvnets.layers.normalization_layers.AdjustBatchNormMomentum method) (cvnets.layers.pixel_shuffle.PixelShuffle method) (cvnets.layers.PixelShuffle method) (cvnets.layers.pooling.AvgPool2d method) (cvnets.layers.pooling.MaxPool2d method) (cvnets.layers.positional_embedding.LearnablePositionalEmbedding method) (cvnets.layers.positional_embedding.PositionalEmbedding method) (cvnets.layers.positional_embedding.SinusoidalPositionalEmbedding method) (cvnets.layers.positional_encoding.LearnablePositionEncoding method) (cvnets.layers.positional_encoding.SinusoidalPositionalEncoding method) (cvnets.layers.PositionalEmbedding method) (cvnets.layers.random_layers.RandomApply method) (cvnets.layers.single_head_attention.SingleHeadAttention method) (cvnets.layers.SingleHeadAttention method) (cvnets.layers.Softmax method) (cvnets.layers.softmax.Softmax method) (cvnets.layers.stochastic_depth.StochasticDepth method) (cvnets.layers.StochasticDepth method) (cvnets.layers.token_merging.TokenMerging method) (cvnets.layers.TransposeConvLayer2d method) (cvnets.layers.UpSample method) (cvnets.layers.upsample.UpSample method) (cvnets.matcher_det.base_matcher.BaseMatcher method) (cvnets.matcher_det.ssd_matcher.SSDMatcher method) (cvnets.misc.averaging_utils.EMA method) (cvnets.models.audio_classification.base_audio_classification.BaseAudioClassification method) (cvnets.models.base_model.BaseAnyNNModel method) (cvnets.models.classification.base_image_encoder.BaseImageEncoder method) (cvnets.models.classification.byteformer.ByteFormer method) (cvnets.models.classification.config.efficientnet.CompoundScalingConfig method) (cvnets.models.classification.config.efficientnet.EfficientNetBlockConfig method) (cvnets.models.classification.config.regnet.BlockParamsConfig method) (cvnets.models.classification.efficientnet.EfficientNet method) (cvnets.models.classification.fastvit.FastViT method) (cvnets.models.classification.mobilenetv1.MobileNetv1 method) (cvnets.models.classification.mobilenetv2.MobileNetV2 method) (cvnets.models.classification.mobilenetv3.MobileNetV3 method) (cvnets.models.classification.mobileone.MobileOne method) (cvnets.models.classification.mobilevit.MobileViT method) (cvnets.models.classification.mobilevit_v2.MobileViTv2 method) (cvnets.models.classification.regnet.RegNet method) (cvnets.models.classification.resnet.ResNet method) (cvnets.models.classification.swin_transformer.SwinTransformer method) (cvnets.models.classification.vit.VisionTransformer method) (cvnets.models.detection.base_detection.BaseDetection method) (cvnets.models.detection.mask_rcnn.MaskRCNNDetector method) (cvnets.models.detection.mask_rcnn.MaskRCNNEncoder method) (cvnets.models.detection.ssd.SingleShotMaskDetector method) (cvnets.models.detection.utils.rcnn_utils.FastRCNNConvFCHead method) (cvnets.models.detection.utils.rcnn_utils.FastRCNNPredictor method) (cvnets.models.detection.utils.rcnn_utils.MaskRCNNHeads method) (cvnets.models.detection.utils.rcnn_utils.MaskRCNNPredictor method) (cvnets.models.detection.utils.rcnn_utils.RPNHead method) (cvnets.models.multi_modal_img_text.base_multi_modal_img_text.BaseMultiModalImageText method) (cvnets.models.multi_modal_img_text.clip.CLIP method) (cvnets.models.segmentation.base_seg.BaseSegmentation method) (cvnets.models.segmentation.enc_dec.SegEncoderDecoder method) (cvnets.models.segmentation.heads.base_seg_head.BaseSegHead method) (cvnets.models.segmentation.heads.deeplabv3.DeeplabV3 method) (cvnets.models.segmentation.heads.pspnet.PSPNet method) (cvnets.models.segmentation.heads.simple_seg_head.SimpleSegHead method) (cvnets.modules.AnyRegNetStage method) (cvnets.modules.ASPP method) (cvnets.modules.aspp_block.ASPP method) (cvnets.modules.aspp_block.ASPPConv2d method) (cvnets.modules.aspp_block.ASPPPooling method) (cvnets.modules.aspp_block.ASPPSeparableConv2d method) (cvnets.modules.base_module.BaseModule method) (cvnets.modules.BasicResNetBlock method) (cvnets.modules.BottleneckResNetBlock method) (cvnets.modules.efficientnet.EfficientNetBlock method) (cvnets.modules.EfficientNetBlock method) (cvnets.modules.fastvit.AttentionBlock method) (cvnets.modules.fastvit.ConvFFN method) (cvnets.modules.fastvit.PatchEmbed method) (cvnets.modules.fastvit.RepCPE method) (cvnets.modules.fastvit.RepMixer method) (cvnets.modules.fastvit.RepMixerBlock method) (cvnets.modules.feature_pyramid.FeaturePyramidNetwork method) (cvnets.modules.FeaturePyramidNetwork method) (cvnets.modules.InvertedResidual method) (cvnets.modules.InvertedResidualSE method) (cvnets.modules.mobilenetv2.InvertedResidual method) (cvnets.modules.mobilenetv2.InvertedResidualSE method) (cvnets.modules.mobileone_block.MobileOneBlock method) (cvnets.modules.mobileone_block.RepLKBlock method) (cvnets.modules.MobileOneBlock method) (cvnets.modules.mobilevit_block.MobileViTBlock method) (cvnets.modules.mobilevit_block.MobileViTBlockv2 method) (cvnets.modules.MobileViTBlock method) (cvnets.modules.MobileViTBlockv2 method) (cvnets.modules.PatchMerging method) (cvnets.modules.Permute method) (cvnets.modules.PSP method) (cvnets.modules.pspnet_module.PSP method) (cvnets.modules.regnet_modules.AnyRegNetStage method) (cvnets.modules.regnet_modules.XRegNetBlock method) (cvnets.modules.RepLKBlock method) (cvnets.modules.resnet_modules.BasicResNetBlock method) (cvnets.modules.resnet_modules.BottleneckResNetBlock method) (cvnets.modules.squeeze_excitation.SqueezeExcitation method) (cvnets.modules.SqueezeExcitation method) (cvnets.modules.ssd_heads.SSDHead method) (cvnets.modules.ssd_heads.SSDInstanceHead method) (cvnets.modules.SSDHead method) (cvnets.modules.SSDInstanceHead method) (cvnets.modules.swin_transformer_block.PatchMerging method) (cvnets.modules.swin_transformer_block.Permute method) (cvnets.modules.swin_transformer_block.ShiftedWindowAttention method) (cvnets.modules.swin_transformer_block.SwinTransformerBlock method) (cvnets.modules.SwinTransformerBlock method) (cvnets.modules.transformer.LinearAttnFFN method) (cvnets.modules.transformer.TransformerEncoder method) (cvnets.modules.TransformerEncoder method) (cvnets.modules.windowed_transformer.WindowedTransformerEncoder method) (cvnets.modules.WindowedTransformerEncoder method) (cvnets.modules.XRegNetBlock method) (cvnets.neural_augmentor.neural_aug.BaseNeuralAugmentor method) (cvnets.neural_augmentor.neural_aug.BasicNeuralAugmentor method) (cvnets.neural_augmentor.neural_aug.DistributionNeuralAugmentor method) (cvnets.neural_augmentor.utils.neural_aug_utils.Clip method) (cvnets.neural_augmentor.utils.neural_aug_utils.FixedSampler method) (cvnets.neural_augmentor.utils.neural_aug_utils.Identity method) (cvnets.neural_augmentor.utils.neural_aug_utils.UniformSampler method) (cvnets.text_encoders.base_text_encoder.BaseTextEncoder method) (cvnets.text_encoders.transformer.TextTransformer method) (data.datasets.audio_classification.speech_commands_v2.SpeechCommandsv2Dataset method) (data.datasets.classification.base_image_classification_dataset.BaseImageClassificationDataset method) (data.datasets.classification.base_imagenet_shift_dataset.BaseImageNetShiftDataset method) (data.datasets.classification.imagenet.ImageNetDataset method) (data.datasets.classification.imagenet_a.ImageNetADataset method) (data.datasets.classification.imagenet_r.ImageNetRDataset method) (data.datasets.classification.imagenet_sketch.ImageNetSketchDataset method) (data.datasets.classification.imagenet_v2.Imagenetv2Dataset method) (data.datasets.classification.places365.Places365Dataset method) (data.datasets.dataset_base.BaseDataset method) (data.datasets.dataset_base.BaseVideoDataset method) (data.datasets.detection.base_detection.BaseDetectionDataset method) (data.datasets.detection.coco_base.COCODetection method) (data.datasets.detection.coco_mask_rcnn.COCODetectionMaskRCNN method) (data.datasets.detection.coco_ssd.COCODetectionSSD method) (data.datasets.multi_modal_img_text.base_multi_modal_img_text.BaseMultiModalImgText method) (data.datasets.multi_modal_img_text.img_text_tar_dataset.ImgTextTarDataset method) (data.datasets.multi_modal_img_text.zero_shot.base_zero_shot.BaseZeroShotDataset method) (data.datasets.multi_modal_img_text.zero_shot.imagenet.ImageNetDatasetZeroShot method) (data.datasets.segmentation.ade20k.ADE20KDataset method) (data.datasets.segmentation.base_segmentation.BaseImageSegmentationDataset method) (data.datasets.segmentation.coco_segmentation.COCOSegmentationDataset method) (data.datasets.segmentation.pascal_voc.PascalVOCDataset method) (data.loader.dataloader.CVNetsDataLoader method) (data.sampler.base_sampler.BaseSampler method) (data.sampler.base_sampler.BaseSamplerDDP method) (data.sampler.batch_sampler.BatchSampler method), [1] (data.sampler.batch_sampler.BatchSamplerDDP method), [1] (data.sampler.chain_sampler.ChainSampler method) (data.sampler.multi_scale_sampler.MultiScaleSampler method), [1] (data.sampler.multi_scale_sampler.MultiScaleSamplerDDP method), [1] (data.sampler.variable_batch_sampler.VariableBatchSampler method), [1] (data.sampler.variable_batch_sampler.VariableBatchSamplerDDP method), [1] (data.text_tokenizer.base_tokenizer.BaseTokenizer method) (data.text_tokenizer.clip_tokenizer.ClipTokenizer method) (data.transforms.audio.AudioResample method) (data.transforms.audio.Gain method) (data.transforms.audio.LambdaAudio method) (data.transforms.audio.MFCCs method) (data.transforms.audio.Noise method) (data.transforms.audio.Roll method) (data.transforms.audio.SetFixedLength method) (data.transforms.audio.StandardizeChannels method) (data.transforms.audio_bytes.TorchaudioSave method) (data.transforms.base_transforms.BaseTransformation method) (data.transforms.common.Compose method) (data.transforms.image_bytes.BytePermutation method) (data.transforms.image_bytes.MaskPositions method) (data.transforms.image_bytes.PILSave method) (data.transforms.image_bytes.RandomUniformNoise method) (data.transforms.image_bytes.ShuffleBytes method) (data.transforms.image_pil.AutoAugment method) (data.transforms.image_pil.BoxPercentCoords method) (data.transforms.image_pil.CenterCrop method) (data.transforms.image_pil.FixedSizeCrop method) (data.transforms.image_pil.InstanceProcessor method) (data.transforms.image_pil.PhotometricDistort method) (data.transforms.image_pil.RandAugment method) (data.transforms.image_pil.RandAugmentTimm method) (data.transforms.image_pil.RandomCrop method) (data.transforms.image_pil.RandomErasing method) (data.transforms.image_pil.RandomGaussianBlur method) (data.transforms.image_pil.RandomHorizontalFlip method) (data.transforms.image_pil.RandomOrder method) (data.transforms.image_pil.RandomResize method) (data.transforms.image_pil.RandomResizedCrop method) (data.transforms.image_pil.RandomRotate method) (data.transforms.image_pil.RandomShortSizeResize method) (data.transforms.image_pil.Resize method) (data.transforms.image_pil.ScaleJitter method) (data.transforms.image_pil.SSDCroping method) (data.transforms.image_pil.ToTensor method) (data.transforms.image_pil.TrivialAugmentWide method) (data.transforms.image_torch.RandomCutmix method) (data.transforms.image_torch.RandomMixup method) (data.transforms.video.CenterCrop method) (data.transforms.video.CropByBoundingBox method) (data.transforms.video.RandomCrop method) (data.transforms.video.RandomHorizontalFlip method) (data.transforms.video.RandomResizedCrop method) (data.transforms.video.RandomShortSizeResizeCrop method) (data.transforms.video.Resize method) (data.transforms.video.SaveInputs method) (data.transforms.video.ShuffleAudios method) (data.transforms.video.ToTensor method) (data.video_reader.base_av_reader.BaseAVReader method) (data.video_reader.decord_reader.DecordAVReader method) (engine.evaluation_engine.Evaluator method) (engine.training_engine.Trainer method) (loss_fn.base_criteria.BaseCriteria method) (loss_fn.classification.base_classification_criteria.BaseClassificationCriteria method) (loss_fn.classification.binary_cross_entropy.BinaryCrossEntropy method) (loss_fn.classification.cross_entropy.CrossEntropy method) (loss_fn.composite_loss.CompositeLoss method) (loss_fn.detection.base_detection_criteria.BaseDetectionCriteria method) (loss_fn.detection.mask_rcnn_loss.MaskRCNNLoss method) (loss_fn.detection.ssd_multibox_loss.SSDLoss method) (loss_fn.distillation.base_distillation.BaseDistillationCriteria method) (loss_fn.distillation.hard_distillation.HardDistillationLoss method) (loss_fn.distillation.soft_kl_distillation.SoftKLLoss method) (loss_fn.multi_modal_img_text.base_multi_modal_img_text_criteria.BaseMultiModalImageTextCriteria method) (loss_fn.multi_modal_img_text.contrastive_loss_clip.ContrastiveLossClip method) (loss_fn.neural_augmentation.NeuralAugmentation method) (loss_fn.segmentation.base_segmentation_criteria.BaseSegmentationCriteria method) (loss_fn.segmentation.cross_entropy.SegCrossEntropy method) (metrics.coco_map.COCOEvaluator method) (metrics.image_text_retrieval.ImageTextRetrievalMetric method) (metrics.metric_base.BaseMetric method) (metrics.metric_base.EpochMetric method) (metrics.probability_histograms.ProbabilityHistogramMetric method) (metrics.retrieval_cmc.RetrievalCMC method) (metrics.stats.Statistics method) (optim.adam.AdamOptimizer method) (optim.adamw.AdamWOptimizer method) (optim.base_optim.BaseOptim method) (optim.scheduler.base_scheduler.BaseLRScheduler method) (optim.scheduler.cosine.CosineScheduler method) (optim.scheduler.cyclic.CyclicLRScheduler method) (optim.scheduler.fixed.FixedLRScheduler method) (optim.scheduler.multi_step.MultiStepLRScheduler method) (optim.scheduler.polynomial.PolynomialScheduler method) (optim.sgd.SGDOptimizer method) (options.errors.UnrecognizedYamlConfigEntry method) (options.parse_args.JsonValidator method) (utils.color_map.Colormap method) (utils.registry.Registry method)

A

AdamOptimizer (class in optim.adam) AdamWOptimizer (class in optim.adamw) AdaptiveAvgPool2d (class in cvnets.layers.adaptive_pool) add_arguments() (cvnets.anchor_generator.base_anchor_generator.BaseAnchorGenerator class method) (cvnets.anchor_generator.ssd_anchor_generator.SSDAnchorGenerator class method) (cvnets.image_projection_layers.attention_pool_2d.AttentionPool2dHead class method) (cvnets.image_projection_layers.base_image_projection.BaseImageProjectionHead class method) (cvnets.image_projection_layers.global_pool_2d.GlobalPool2D class method) (cvnets.image_projection_layers.simple_projection_head.SimpleImageProjectionHead class method) (cvnets.layers.base_layer.BaseLayer class method) (cvnets.layers.global_pool.GlobalPool class method) (cvnets.layers.GlobalPool class method) (cvnets.layers.GroupLinear class method) (cvnets.layers.linear_layer.GroupLinear class method) (cvnets.layers.linear_layer.LinearLayer class method) (cvnets.layers.LinearLayer class method) (cvnets.matcher_det.base_matcher.BaseMatcher class method) (cvnets.matcher_det.ssd_matcher.SSDMatcher class method) (cvnets.models.audio_classification.base_audio_classification.BaseAudioClassification class method) (cvnets.models.base_model.BaseAnyNNModel class method) (cvnets.models.classification.base_image_encoder.BaseImageEncoder class method) (cvnets.models.classification.byteformer.ByteFormer class method) (cvnets.models.classification.efficientnet.EfficientNet class method) (cvnets.models.classification.fastvit.FastViT class method) (cvnets.models.classification.mobilenetv1.MobileNetv1 class method) (cvnets.models.classification.mobilenetv2.MobileNetV2 class method) (cvnets.models.classification.mobilenetv3.MobileNetV3 class method) (cvnets.models.classification.mobileone.MobileOne class method) (cvnets.models.classification.mobilevit.MobileViT class method) (cvnets.models.classification.mobilevit_v2.MobileViTv2 class method) (cvnets.models.classification.regnet.RegNet class method) (cvnets.models.classification.resnet.ResNet class method) (cvnets.models.classification.swin_transformer.SwinTransformer class method) (cvnets.models.classification.vit.VisionTransformer class method) (cvnets.models.detection.base_detection.BaseDetection class method) (cvnets.models.detection.mask_rcnn.MaskRCNNDetector class method) (cvnets.models.detection.ssd.SingleShotMaskDetector class method) (cvnets.models.multi_modal_img_text.base_multi_modal_img_text.BaseMultiModalImageText class method) (cvnets.models.multi_modal_img_text.clip.CLIP class method) (cvnets.models.segmentation.base_seg.BaseSegmentation class method) (cvnets.models.segmentation.heads.base_seg_head.BaseSegHead class method) (cvnets.models.segmentation.heads.deeplabv3.DeeplabV3 class method) (cvnets.models.segmentation.heads.pspnet.PSPNet class method) (cvnets.models.segmentation.heads.simple_seg_head.SimpleSegHead class method) (cvnets.neural_augmentor.neural_aug.BaseNeuralAugmentor class method) (cvnets.text_encoders.base_text_encoder.BaseTextEncoder class method) (cvnets.text_encoders.transformer.TextTransformer class method) (data.datasets.audio_classification.speech_commands_v2.SpeechCommandsv2Dataset class method) (data.datasets.classification.base_image_classification_dataset.BaseImageClassificationDataset class method) (data.datasets.classification.imagenet_v2.Imagenetv2Dataset class method) (data.datasets.dataset_base.BaseDataset class method) (data.datasets.dataset_base.BaseVideoDataset class method) (data.datasets.detection.base_detection.BaseDetectionDataset class method) (data.datasets.detection.coco_base.COCODetection class method) (data.datasets.detection.coco_mask_rcnn.COCODetectionMaskRCNN class method) (data.datasets.multi_modal_img_text.base_multi_modal_img_text.BaseMultiModalImgText class method) (data.datasets.multi_modal_img_text.img_text_tar_dataset.ImgTextTarDataset class method) (data.datasets.multi_modal_img_text.zero_shot.base_zero_shot.BaseZeroShotDataset class method) (data.datasets.segmentation.base_segmentation.BaseImageSegmentationDataset class method) (data.datasets.segmentation.pascal_voc.PascalVOCDataset class method) (data.sampler.base_sampler.BaseSampler class method) (data.sampler.base_sampler.BaseSamplerDDP class method) (data.sampler.batch_sampler.BatchSampler class method), [1] (data.sampler.chain_sampler.ChainSampler class method) (data.sampler.multi_scale_sampler.MultiScaleSampler class method), [1] (data.sampler.variable_batch_sampler.VariableBatchSampler class method), [1] (data.text_tokenizer.base_tokenizer.BaseTokenizer class method) (data.text_tokenizer.clip_tokenizer.ClipTokenizer class method) (data.transforms.audio.AudioResample class method) (data.transforms.audio.Gain class method) (data.transforms.audio.MFCCs class method) (data.transforms.audio.Noise class method) (data.transforms.audio.Roll class method) (data.transforms.audio.SetFixedLength class method) (data.transforms.audio.StandardizeChannels class method) (data.transforms.audio_bytes.TorchaudioSave class method) (data.transforms.base_transforms.BaseTransformation class method) (data.transforms.image_bytes.BytePermutation class method) (data.transforms.image_bytes.MaskPositions class method) (data.transforms.image_bytes.PILSave class method) (data.transforms.image_bytes.RandomUniformNoise class method) (data.transforms.image_bytes.ShuffleBytes class method) (data.transforms.image_pil.AutoAugment class method) (data.transforms.image_pil.CenterCrop class method) (data.transforms.image_pil.FixedSizeCrop class method) (data.transforms.image_pil.PhotometricDistort class method) (data.transforms.image_pil.RandAugment class method) (data.transforms.image_pil.RandAugmentTimm class method) (data.transforms.image_pil.RandomCrop class method) (data.transforms.image_pil.RandomErasing class method) (data.transforms.image_pil.RandomGaussianBlur class method) (data.transforms.image_pil.RandomHorizontalFlip class method) (data.transforms.image_pil.RandomOrder class method) (data.transforms.image_pil.RandomResize class method) (data.transforms.image_pil.RandomResizedCrop class method) (data.transforms.image_pil.RandomRotate class method) (data.transforms.image_pil.RandomShortSizeResize class method) (data.transforms.image_pil.Resize class method) (data.transforms.image_pil.ScaleJitter class method) (data.transforms.image_pil.SSDCroping class method) (data.transforms.image_pil.ToTensor class method) (data.transforms.image_pil.TrivialAugmentWide class method) (data.transforms.image_torch.RandomCutmix class method) (data.transforms.image_torch.RandomMixup class method) (data.transforms.video.CenterCrop class method) (data.transforms.video.CropByBoundingBox class method) (data.transforms.video.RandomCrop class method) (data.transforms.video.RandomHorizontalFlip class method) (data.transforms.video.RandomResizedCrop class method) (data.transforms.video.RandomShortSizeResizeCrop class method) (data.transforms.video.Resize class method) (data.transforms.video.SaveInputs class method) (data.transforms.video.ShuffleAudios class method) (data.video_reader.base_av_reader.BaseAVReader class method) (loss_fn.base_criteria.BaseCriteria class method) (loss_fn.classification.base_classification_criteria.BaseClassificationCriteria class method) (loss_fn.classification.binary_cross_entropy.BinaryCrossEntropy class method) (loss_fn.classification.cross_entropy.CrossEntropy class method) (loss_fn.composite_loss.CompositeLoss class method) (loss_fn.detection.base_detection_criteria.BaseDetectionCriteria class method) (loss_fn.detection.mask_rcnn_loss.MaskRCNNLoss class method) (loss_fn.detection.ssd_multibox_loss.SSDLoss class method) (loss_fn.distillation.base_distillation.BaseDistillationCriteria class method) (loss_fn.distillation.hard_distillation.HardDistillationLoss class method) (loss_fn.distillation.soft_kl_distillation.SoftKLLoss class method) (loss_fn.multi_modal_img_text.base_multi_modal_img_text_criteria.BaseMultiModalImageTextCriteria class method) (loss_fn.neural_augmentation.NeuralAugmentation class method) (loss_fn.segmentation.base_segmentation_criteria.BaseSegmentationCriteria class method) (loss_fn.segmentation.cross_entropy.SegCrossEntropy class method) (metrics.image_text_retrieval.ImageTextRetrievalMetric class method) (metrics.metric_base.BaseMetric class method) (metrics.probability_histograms.ProbabilityHistogramMetric class method) (metrics.retrieval_cmc.RetrievalCMC class method) (optim.adam.AdamOptimizer class method) (optim.adamw.AdamWOptimizer class method) (optim.base_optim.BaseOptim class method) (optim.scheduler.base_scheduler.BaseLRScheduler class method) (optim.scheduler.cosine.CosineScheduler class method) (optim.scheduler.cyclic.CyclicLRScheduler class method) (optim.scheduler.fixed.FixedLRScheduler class method) (optim.scheduler.multi_step.MultiStepLRScheduler class method) (optim.scheduler.polynomial.PolynomialScheduler class method) (optim.sgd.SGDOptimizer class method)

add_loss_fn_arguments() (in module loss_fn) add_sampler_arguments() (in module data.sampler) add_squeeze_channels() (in module cvnets.models.classification.config.resnet) ADE20KDataset (class in data.datasets.segmentation.ade20k) adjust_atrous_rate() (cvnets.modules.aspp_block.ASPPConv2d method) (cvnets.modules.aspp_block.ASPPSeparableConv2d method) adjust_mask_value() (data.datasets.segmentation.ade20k.ADE20KDataset static method) (data.datasets.segmentation.base_segmentation.BaseImageSegmentationDataset static method) adjust_momentum() (cvnets.layers.AdjustBatchNormMomentum method) (cvnets.layers.normalization_layers.AdjustBatchNormMomentum method) AdjustBatchNormMomentum (class in cvnets.layers) (class in cvnets.layers.normalization_layers) all_arguments() (utils.registry.Registry method) all_gather() (in module utils.third_party.ddp_functional_utils) all_gather_list() (in module utils.tensor_utils) all_reduce() (in module utils.third_party.ddp_functional_utils) all_to_all() (in module utils.third_party.ddp_functional_utils) all_to_all_single() (in module utils.third_party.ddp_functional_utils) AnyRegNetStage (class in cvnets.modules) (class in cvnets.modules.regnet_modules) apply_byte_permutation() (in module data.collate_fns.byteformer_collate_functions) apply_mask_positions() (in module data.collate_fns.byteformer_collate_functions) apply_mixing_transforms() (in module data.transforms.image_torch) apply_padding() (in module data.collate_fns.byteformer_collate_functions) apply_pil_save() (in module data.collate_fns.byteformer_collate_functions) apply_random_uniform_noise() (in module data.collate_fns.byteformer_collate_functions) apply_recursively() (in module utils.object_utils) apply_shuffle_bytes() (in module data.collate_fns.byteformer_collate_functions) apply_token_reduction_net() (cvnets.models.classification.byteformer.ByteFormer method) apply_torchaudio_save() (in module data.collate_fns.byteformer_collate_functions) arguments_activation_fn() (in module cvnets.layers.activation) arguments_anchor_gen() (in module cvnets.anchor_generator) arguments_augmentation() (in module data.transforms) arguments_box_matcher() (in module cvnets.matcher_det) arguments_collate_fn() (in module data.collate_fns) arguments_common() (in module options.opts) arguments_dataset() (in module data.datasets) arguments_ddp() (in module options.opts) arguments_ema() (in module cvnets.misc.averaging_utils) arguments_image_projection_head() (in module cvnets.image_projection_layers) arguments_model() (in module cvnets.models) arguments_multi_modal_img_text() (in module data.datasets.multi_modal_img_text) arguments_neural_augmentor() (in module cvnets.neural_augmentor) arguments_norm_layers() (in module cvnets.layers.normalization) arguments_optimizer() (in module optim) arguments_scheduler() (in module optim.scheduler) arguments_stats() (in module metrics) arguments_text_encoder() (in module cvnets.text_encoders) arguments_tokenizer() (in module data.text_tokenizer) arguments_video_reader() (in module data.video_reader) arguments_zero_shot_dataset() (in module data.datasets.multi_modal_img_text.zero_shot) ASPP (class in cvnets.modules) (class in cvnets.modules.aspp_block) ASPPConv2d (class in cvnets.modules.aspp_block) ASPPPooling (class in cvnets.modules.aspp_block) ASPPSeparableConv2d (class in cvnets.modules.aspp_block) assertion_check() (in module utils.pytorch_to_coreml) assign_priors() (in module cvnets.misc.third_party.ssd_utils) async_download_file_from_s3() (in module data.datasets.multi_modal_img_text.img_text_tar_dataset) AttentionBlock (class in cvnets.modules.fastvit) AttentionPool2dHead (class in cvnets.image_projection_layers.attention_pool_2d) audio_fps (data.datasets.dataset_base.VideoMetadataDict attribute) AudioByteFormer (class in cvnets.models.audio_classification.audio_byteformer) AudioResample (class in data.transforms.audio) AutoAugment (class in data.transforms.image_pil) autocast_fn() (in module engine.utils) average_ckpts() (in module utils.checkpoint_utils) AverageMetric (class in metrics.metric_base) AveragePrecisionMetric (class in metrics.average_precision) avg_and_save_k_checkpoints() (in module utils.checkpoint_utils) avg_statistics() (metrics.stats.Statistics method) AvgPool2d (class in cvnets.layers) (class in cvnets.layers.pooling)

B

backbone_forward() (cvnets.models.classification.byteformer.ByteFormer method) BaseAnchorGenerator (class in cvnets.anchor_generator.base_anchor_generator) BaseAnyNNModel (class in cvnets.models.base_model) BaseAudioClassification (class in cvnets.models.audio_classification.base_audio_classification) BaseAVReader (class in data.video_reader.base_av_reader) BaseClassificationCriteria (class in loss_fn.classification.base_classification_criteria) BaseCriteria (class in loss_fn.base_criteria) BaseDataset (class in data.datasets.dataset_base) BaseDetection (class in cvnets.models.detection.base_detection) BaseDetectionCriteria (class in loss_fn.detection.base_detection_criteria) BaseDetectionDataset (class in data.datasets.detection.base_detection) BaseDistillationCriteria (class in loss_fn.distillation.base_distillation) BaseImageClassificationDataset (class in data.datasets.classification.base_image_classification_dataset) BaseImageDataset (class in data.datasets.dataset_base) BaseImageEncoder (class in cvnets.models.classification.base_image_encoder) BaseImageNetShiftDataset (class in data.datasets.classification.base_imagenet_shift_dataset) BaseImageProjectionHead (class in cvnets.image_projection_layers.base_image_projection) BaseImageSegmentationDataset (class in data.datasets.segmentation.base_segmentation) BaseLayer (class in cvnets.layers.base_layer) BaseLRScheduler (class in optim.scheduler.base_scheduler) BaseMatcher (class in cvnets.matcher_det.base_matcher) BaseMetric (class in metrics.metric_base) BaseModule (class in cvnets.modules.base_module) BaseMultiModalImageText (class in cvnets.models.multi_modal_img_text.base_multi_modal_img_text) BaseMultiModalImageTextCriteria (class in loss_fn.multi_modal_img_text.base_multi_modal_img_text_criteria) BaseMultiModalImgText (class in data.datasets.multi_modal_img_text.base_multi_modal_img_text) BaseNeuralAugmentor (class in cvnets.neural_augmentor.neural_aug) BaseOptim (class in optim.base_optim) BaseSampler (class in data.sampler.base_sampler) BaseSamplerDDP (class in data.sampler.base_sampler) BaseSegHead (class in cvnets.models.segmentation.heads.base_seg_head) BaseSegmentation (class in cvnets.models.segmentation.base_seg) BaseSegmentationCriteria (class in loss_fn.segmentation.base_segmentation_criteria) BaseTextEncoder (class in cvnets.text_encoders.base_text_encoder) BaseTokenizer (class in data.text_tokenizer.base_tokenizer) BaseTransformation (class in data.transforms.base_transforms) BaseVideoDataset (class in data.datasets.dataset_base) BaseZeroShotDataset (class in data.datasets.multi_modal_img_text.zero_shot.base_zero_shot) basic_blocks() (in module cvnets.models.classification.fastvit) BasicNeuralAugmentor (class in cvnets.neural_augmentor.neural_aug) BasicResNetBlock (class in cvnets.modules) (class in cvnets.modules.resnet_modules) BatchNorm1d (class in cvnets.layers.normalization.batch_norm) BatchNorm2d (class in cvnets.layers.normalization.batch_norm)

BatchNorm2dFP32 (class in cvnets.layers.normalization.batch_norm) BatchNorm3d (class in cvnets.layers.normalization.batch_norm) BatchSampler (class in data.sampler.batch_sampler), [1] BatchSamplerDDP (class in data.sampler.batch_sampler), [1] BinaryCrossEntropy (class in loss_fn.classification.binary_cross_entropy) BlockParamsConfig (class in cvnets.models.classification.config.regnet) BottleneckResNetBlock (class in cvnets.modules) (class in cvnets.modules.resnet_modules) bound_fn() (in module utils.math_utils) box_iou() (in module cvnets.misc.third_party.ssd_utils) boxes (cvnets.models.detection.DetectionPredTuple attribute) BoxPercentCoords (class in data.transforms.image_pil) broadcast() (in module utils.third_party.ddp_functional_utils) build_activation_layer() (in module cvnets.layers.activation) build_anchor_generator() (in module cvnets.anchor_generator) build_attention_mask() (cvnets.text_encoders.transformer.TextTransformer method) build_chain_sampler() (data.sampler.chain_sampler.ChainSampler class method) build_cls_teacher_from_opts() (in module loss_fn.utils.build_helper) build_collate_fn() (in module data.collate_fns) build_composite_loss_fn() (loss_fn.composite_loss.CompositeLoss class method) build_dataset_from_registry() (in module data.datasets) build_image_projection_head() (in module cvnets.image_projection_layers) build_loss_fn() (in module loss_fn) build_matcher() (in module cvnets.matcher_det) build_model() (cvnets.models.base_model.BaseAnyNNModel class method) (cvnets.models.classification.base_image_encoder.BaseImageEncoder class method) (cvnets.models.classification.byteformer.ByteFormer class method) (cvnets.models.detection.base_detection.BaseDetection class method) (cvnets.models.multi_modal_img_text.clip.CLIP class method) (cvnets.models.segmentation.enc_dec.SegEncoderDecoder class method) (cvnets.models.segmentation.heads.base_seg_head.BaseSegHead class method) build_neural_augmentor() (in module cvnets.neural_augmentor.neural_aug) build_normalization_layer() (in module cvnets.layers.normalization) build_optimizer() (in module optim) build_sampler() (in module data.sampler) build_scheduler() (in module optim.scheduler) build_test_collate_fn() (in module data.collate_fns) build_text_encoder() (in module cvnets.text_encoders) build_tokenizer() (in module data.text_tokenizer) build_zero_shot_dataset() (in module data.datasets.multi_modal_img_text.zero_shot) ByteFormer (class in cvnets.models.classification.byteformer) byteformer_audio_collate_fn() (in module data.collate_fns.byteformer_collate_functions) byteformer_image_collate_fn() (in module data.collate_fns.byteformer_collate_functions) BytePermutation (class in data.transforms.image_bytes)

C

calculate_mfccs() (in module data.transforms.audio_aux.mfccs) caption_preprocessing() (in module data.datasets.utils.text) center_form_to_corner_form() (in module cvnets.misc.box_utils) CenterCrop (class in data.transforms.image_pil) (class in data.transforms.video) ChainSampler (class in data.sampler.chain_sampler) check_compatibility() (in module utils.common_utils) check_dataset() (data.datasets.segmentation.base_segmentation.BaseImageSegmentationDataset method) check_feature_map_output_channels() (in module cvnets.models.detection.base_detection) check_frozen_norm_layer() (in module utils.common_utils) check_model() (cvnets.models.classification.base_image_encoder.BaseImageEncoder method) check_trainable_parameters() (in module optim) check_variable() (in module cvnets.matcher_det.ssd_matcher) check_video() (data.video_reader.base_av_reader.BaseAVReader method) class_id_to_imagenet_class_id() (data.datasets.classification.base_imagenet_shift_dataset.BaseImageNetShiftDataset static method) (data.datasets.classification.imagenet_a.ImageNetADataset static method) (data.datasets.classification.imagenet_r.ImageNetRDataset static method) (data.datasets.classification.imagenet_sketch.ImageNetSketchDataset static method) class_names() (data.datasets.detection.coco_base.COCODetection static method) (data.datasets.multi_modal_img_text.zero_shot.base_zero_shot.BaseZeroShotDataset class method) (data.datasets.multi_modal_img_text.zero_shot.imagenet.ImageNetDatasetZeroShot class method) (data.datasets.segmentation.ade20k.ADE20KDataset static method) (data.datasets.segmentation.base_segmentation.BaseImageSegmentationDataset static method) (data.datasets.segmentation.coco_segmentation.COCOSegmentationDataset static method) (data.datasets.segmentation.pascal_voc.PascalVOCDataset static method) clean_strip() (in module cvnets.misc.common) CLIP (class in cvnets.models.multi_modal_img_text.clip) Clip (class in cvnets.neural_augmentor.utils.neural_aug_utils) clips_per_video (data.datasets.dataset_base.BaseVideoDataset property) ClipTokenizer (class in data.text_tokenizer.clip_tokenizer) cmc_calculation() (in module metrics.retrieval_cmc) coco_evaluation() (in module engine.detection_utils.coco_map) coco_mask_rcnn_collate_fn() (in module data.datasets.detection.coco_mask_rcnn) coco_ssd_collate_fn() (in module data.datasets.detection.coco_ssd) coco_to_pascal_mapping() (data.datasets.segmentation.coco_segmentation.COCOSegmentationDataset static method) COCODetection (class in data.datasets.detection.coco_base) COCODetectionMaskRCNN (class in data.datasets.detection.coco_mask_rcnn) COCODetectionSSD (class in data.datasets.detection.coco_ssd) COCOEvaluator (class in metrics.coco_map) COCOSegmentationDataset (class in data.datasets.segmentation.coco_segmentation) color_palette() (data.datasets.segmentation.ade20k.ADE20KDataset static method) (data.datasets.segmentation.base_segmentation.BaseImageSegmentationDataset static method) (data.datasets.segmentation.pascal_voc.PascalVOCDataset static method) color_text() (in module utils.logger) Colormap (class in utils.color_map) Compose (class in data.transforms.common) CompositeLoss (class in loss_fn.composite_loss) CompoundScalingConfig (class in cvnets.models.classification.config.efficientnet) compute() (metrics.coco_map.COCOEvaluator method) (metrics.confusion_mat.ConfusionMatrix method) (metrics.image_text_retrieval.ImageTextRetrievalMetric method) (metrics.intersection_over_union.IOUMetric method) (metrics.metric_base.AverageMetric method) (metrics.metric_base.BaseMetric method) (metrics.metric_base.EpochMetric method) compute_class_weights() (in module loss_fn.utils.class_weighting) compute_grad_norm() (engine.training_engine.Trainer method) compute_miou_batch() (in module metrics.intersection_over_union) compute_psnr() (in module metrics.psnr) compute_quant_scores() (in module engine.detection_utils.coco_map) compute_with_aggregates() (metrics.average_precision.AveragePrecisionMetric method) (metrics.metric_base.EpochMetric method) (metrics.probability_histograms.ProbabilityHistogramMetric method) (metrics.retrieval_cmc.RetrievalCMC method) ConfusionMatrix (class in metrics.confusion_mat) ContrastiveLossClip (class in loss_fn.multi_modal_img_text.contrastive_loss_clip) Conv2d (class in cvnets.layers.conv_layer) conv_layer_cls (cvnets.layers.conv_layer.SeparableConv1d attribute) (cvnets.layers.conv_layer.SeparableConv2d attribute) (cvnets.layers.conv_layer.SeparableConv3d attribute) (cvnets.layers.SeparableConv1d attribute) (cvnets.layers.SeparableConv2d attribute) (cvnets.layers.SeparableConv3d attribute) convert_boxes_to_locations() (in module cvnets.misc.box_utils) convert_locations_to_boxes() (in module cvnets.misc.box_utils) convert_mask_to_tensor() (data.datasets.segmentation.base_segmentation.BaseImageSegmentationDataset static method) convert_pytorch_to_coreml() (in module utils.pytorch_to_coreml) convert_to_boxes() (cvnets.matcher_det.ssd_matcher.SSDMatcher method) convert_to_cityscape_format() (in module utils.visualization_utils) ConvFFN (class in cvnets.modules.fastvit) ConvLayer1d (class in cvnets.layers) (class in cvnets.layers.conv_layer) ConvLayer2d (class in cvnets.layers) (class in cvnets.layers.conv_layer) ConvLayer3d (class in cvnets.layers) (class in cvnets.layers.conv_layer) convolutional_stem() (in module cvnets.modules.fastvit) coordinates (cvnets.models.detection.ssd.SingleShotMaskDetector attribute) copy_weights() (in module utils.checkpoint_utils) corner_form_to_center_form() (in module cvnets.misc.box_utils) cosine_curriculum() (in module loss_fn.neural_augmentation) cosine_distance_matrix() (in module metrics.retrieval_cmc) CosineScheduler (class in optim.scheduler.cosine) cpu_count() (in module utils.resources) create_bases() (in module loss_landscape.landscape_utils) create_colored_mask() (in module utils.visualization_utils) create_directories() (in module utils.common_utils) create_intervallic_integer_list() (in module data.sampler.utils) create_rand_tensor() (in module utils.tensor_utils) create_test_loader() (in module data.data_loaders) create_train_val_loader() (in module data.data_loaders) CropByBoundingBox (class in data.transforms.video) CrossEntropy (class in loss_fn.classification.cross_entropy) cvnets module cvnets.anchor_generator module cvnets.anchor_generator.base_anchor_generator module cvnets.anchor_generator.ssd_anchor_generator module cvnets.image_projection_layers module cvnets.image_projection_layers.attention_pool_2d module cvnets.image_projection_layers.base_image_projection module cvnets.image_projection_layers.global_pool_2d module cvnets.image_projection_layers.simple_projection_head module cvnets.layers module cvnets.layers.activation module cvnets.layers.activation.gelu module cvnets.layers.activation.hard_sigmoid module cvnets.layers.activation.hard_swish module cvnets.layers.activation.leaky_relu module cvnets.layers.activation.prelu module cvnets.layers.activation.relu module cvnets.layers.activation.relu6 module cvnets.layers.activation.sigmoid module cvnets.layers.activation.swish module cvnets.layers.activation.tanh module cvnets.layers.adaptive_pool module cvnets.layers.base_layer module cvnets.layers.conv_layer module cvnets.layers.dropout module cvnets.layers.embedding module cvnets.layers.flatten module cvnets.layers.global_pool module cvnets.layers.identity module cvnets.layers.linear_attention module cvnets.layers.linear_layer module cvnets.layers.multi_head_attention module cvnets.layers.normalization module cvnets.layers.normalization.batch_norm module cvnets.layers.normalization.group_norm module cvnets.layers.normalization.instance_norm module cvnets.layers.normalization.layer_norm module cvnets.layers.normalization.sync_batch_norm module cvnets.layers.normalization_layers module cvnets.layers.pixel_shuffle module cvnets.layers.pooling module cvnets.layers.positional_embedding module

cvnets.layers.positional_encoding module cvnets.layers.random_layers module cvnets.layers.single_head_attention module cvnets.layers.softmax module cvnets.layers.stochastic_depth module cvnets.layers.token_merging module cvnets.layers.upsample module cvnets.matcher_det module cvnets.matcher_det.base_matcher module cvnets.matcher_det.ssd_matcher module cvnets.misc module cvnets.misc.averaging_utils module cvnets.misc.box_utils module cvnets.misc.common module cvnets.misc.init_utils module cvnets.misc.third_party module cvnets.misc.third_party.ssd_utils module cvnets.models module cvnets.models.audio_classification module cvnets.models.audio_classification.audio_byteformer module cvnets.models.audio_classification.base_audio_classification module cvnets.models.base_model module cvnets.models.classification module cvnets.models.classification.base_image_encoder module cvnets.models.classification.byteformer module cvnets.models.classification.config module cvnets.models.classification.config.byteformer module cvnets.models.classification.config.efficientnet module cvnets.models.classification.config.fastvit module cvnets.models.classification.config.mobilenetv1 module cvnets.models.classification.config.mobilenetv2 module cvnets.models.classification.config.mobilenetv3 module cvnets.models.classification.config.mobileone module cvnets.models.classification.config.mobilevit module cvnets.models.classification.config.mobilevit_v2 module cvnets.models.classification.config.regnet module cvnets.models.classification.config.resnet module cvnets.models.classification.config.swin_transformer module cvnets.models.classification.config.vit module cvnets.models.classification.efficientnet module cvnets.models.classification.fastvit module cvnets.models.classification.mobilenetv1 module cvnets.models.classification.mobilenetv2 module cvnets.models.classification.mobilenetv3 module cvnets.models.classification.mobileone module cvnets.models.classification.mobilevit module cvnets.models.classification.mobilevit_v2 module cvnets.models.classification.regnet module cvnets.models.classification.resnet module cvnets.models.classification.swin_transformer module cvnets.models.classification.vit module cvnets.models.detection module cvnets.models.detection.base_detection module cvnets.models.detection.mask_rcnn module cvnets.models.detection.ssd module cvnets.models.detection.utils module cvnets.models.detection.utils.rcnn_utils module cvnets.models.multi_modal_img_text module cvnets.models.multi_modal_img_text.base_multi_modal_img_text module cvnets.models.multi_modal_img_text.clip module cvnets.models.segmentation module cvnets.models.segmentation.base_seg module cvnets.models.segmentation.enc_dec module cvnets.models.segmentation.heads module cvnets.models.segmentation.heads.base_seg_head module cvnets.models.segmentation.heads.deeplabv3 module cvnets.models.segmentation.heads.pspnet module cvnets.models.segmentation.heads.simple_seg_head module cvnets.modules module cvnets.modules.aspp_block module cvnets.modules.base_module module cvnets.modules.efficientnet module cvnets.modules.fastvit module cvnets.modules.feature_pyramid module cvnets.modules.mobilenetv2 module cvnets.modules.mobileone_block module cvnets.modules.mobilevit_block module cvnets.modules.pspnet_module module cvnets.modules.regnet_modules module cvnets.modules.resnet_modules module cvnets.modules.squeeze_excitation module cvnets.modules.ssd_heads module cvnets.modules.swin_transformer_block module cvnets.modules.transformer module cvnets.modules.windowed_transformer module cvnets.neural_augmentor module cvnets.neural_augmentor.neural_aug module cvnets.neural_augmentor.utils module cvnets.neural_augmentor.utils.neural_aug_utils module cvnets.text_encoders module cvnets.text_encoders.base_text_encoder module cvnets.text_encoders.transformer module CVNetsDataLoader (class in data.loader.dataloader) CyclicLRScheduler (class in optim.scheduler.cyclic)

D

data module data.collate_fns module data.collate_fns.byteformer_collate_functions module data.collate_fns.collate_functions module data.data_loaders module data.datasets module data.datasets.audio_classification module data.datasets.audio_classification.speech_commands_v2 module data.datasets.classification module data.datasets.classification.base_image_classification_dataset module data.datasets.classification.base_imagenet_shift_dataset module data.datasets.classification.imagenet module data.datasets.classification.imagenet_a module data.datasets.classification.imagenet_r module data.datasets.classification.imagenet_sketch module data.datasets.classification.imagenet_synsets module data.datasets.classification.imagenet_v2 module data.datasets.classification.places365 module data.datasets.dataset_base module data.datasets.detection module data.datasets.detection.base_detection module data.datasets.detection.coco_base module data.datasets.detection.coco_mask_rcnn module data.datasets.detection.coco_ssd module data.datasets.multi_modal_img_text module data.datasets.multi_modal_img_text.base_multi_modal_img_text module data.datasets.multi_modal_img_text.flickr module data.datasets.multi_modal_img_text.img_text_tar_dataset module data.datasets.multi_modal_img_text.zero_shot module data.datasets.multi_modal_img_text.zero_shot.base_zero_shot module data.datasets.multi_modal_img_text.zero_shot.imagenet module data.datasets.multi_modal_img_text.zero_shot.imagenet_class_names module data.datasets.multi_modal_img_text.zero_shot.templates module data.datasets.segmentation module data.datasets.segmentation.ade20k module data.datasets.segmentation.base_segmentation module data.datasets.segmentation.coco_segmentation module data.datasets.segmentation.pascal_voc module data.datasets.utils module data.datasets.utils.common module data.datasets.utils.text module data.datasets.utils.video module data.loader module

data.loader.dataloader module data.sampler module data.sampler.base_sampler module data.sampler.batch_sampler module, [1] data.sampler.chain_sampler module data.sampler.multi_scale_sampler module, [1] data.sampler.utils module data.sampler.variable_batch_sampler module, [1] data.text_tokenizer module data.text_tokenizer.base_tokenizer module data.text_tokenizer.clip_tokenizer module data.transforms module data.transforms.audio module data.transforms.audio_aux module data.transforms.audio_aux.mfccs module data.transforms.audio_bytes module data.transforms.base_transforms module data.transforms.common module data.transforms.image_bytes module data.transforms.image_pil module data.transforms.image_torch module data.transforms.utils module data.transforms.video module data.video_reader module data.video_reader.base_av_reader module data.video_reader.decord_reader module data.video_reader.pyav_reader module debug() (in module utils.logger) decode_image() (in module data.datasets.multi_modal_img_text.img_text_tar_dataset) decode_text() (in module data.datasets.multi_modal_img_text.img_text_tar_dataset) DecordAVReader (class in data.video_reader.decord_reader) DeeplabV3 (class in cvnets.models.segmentation.heads.deeplabv3) default_collate_fn() (in module data.collate_fns.collate_functions) depth_mult (cvnets.models.classification.config.efficientnet.CompoundScalingConfig attribute) DetectionPredTuple (class in cvnets.models.detection) device_setup() (in module utils.common_utils) disable_printing() (in module utils.logger) dist_barrier() (in module utils.ddp_utils) dist_monitored_barrier() (in module utils.ddp_utils) distributed_init() (in module utils.ddp_utils) DistributionNeuralAugmentor (class in cvnets.neural_augmentor.neural_aug) double_dash_line() (in module utils.logger) draw_binary_masks() (in module engine.eval_segmentation) draw_bounding_boxes() (in module utils.visualization_utils) draw_colored_masks() (in module engine.eval_segmentation) Dropout (class in cvnets.layers) (class in cvnets.layers.dropout) Dropout2d (class in cvnets.layers) (class in cvnets.layers.dropout) dummy_audio_video_clips() (data.video_reader.base_av_reader.BaseAVReader method) dummy_input_and_label() (cvnets.models.audio_classification.audio_byteformer.AudioByteFormer method) (cvnets.models.base_model.BaseAnyNNModel method) (cvnets.models.classification.base_image_encoder.BaseImageEncoder method) (cvnets.models.classification.byteformer.ByteFormer method) (cvnets.models.detection.mask_rcnn.MaskRCNNDetector method) (cvnets.models.detection.ssd.SingleShotMaskDetector method) (cvnets.models.multi_modal_img_text.clip.CLIP method) (cvnets.models.segmentation.base_seg.BaseSegmentation method) (cvnets.text_encoders.base_text_encoder.BaseTextEncoder method) DummyMetric (class in metrics.metric_base_test)

E

EfficientNet (class in cvnets.models.classification.efficientnet) EfficientNetBlock (class in cvnets.modules) (class in cvnets.modules.efficientnet) EfficientNetBlockConfig (class in cvnets.models.classification.config.efficientnet) EMA (class in cvnets.misc.averaging_utils) Embedding (class in cvnets.layers) (class in cvnets.layers.embedding) enable_printing() (in module utils.logger) encode_text() (cvnets.text_encoders.transformer.TextTransformer method) engine module engine.detection_utils module engine.detection_utils.coco_map module engine.eval_detection module engine.eval_segmentation module engine.evaluation_engine module engine.segmentation_utils module engine.segmentation_utils.cityscapes_iou module engine.training_engine module engine.utils module epoch_summary() (metrics.stats.Statistics method) EpochMetric (class in metrics.metric_base) error() (in module utils.logger) eval() (loss_fn.composite_loss.CompositeLoss method) eval_cityscapes() (in module engine.segmentation_utils.cityscapes_iou) eval_fn_image() (engine.evaluation_engine.Evaluator method) eval_fn_video() (engine.evaluation_engine.Evaluator method) Evaluator (class in engine.evaluation_engine) expand_boxes() (data.transforms.video.CropByBoundingBox method) expansion (cvnets.modules.BasicResNetBlock attribute) (cvnets.modules.BottleneckResNetBlock attribute) (cvnets.modules.resnet_modules.BasicResNetBlock attribute) (cvnets.modules.resnet_modules.BottleneckResNetBlock attribute)

extend_selected_args_with_prefix() (in module options.utils) extra_repr() (cvnets.layers.token_merging.TokenMerging method) (cvnets.models.classification.config.regnet.BlockParamsConfig method) (data.datasets.classification.base_image_classification_dataset.BaseImageClassificationDataset method) (data.datasets.dataset_base.BaseDataset method) (data.datasets.dataset_base.BaseImageDataset method) (data.datasets.detection.coco_base.COCODetection method) (data.datasets.detection.coco_ssd.COCODetectionSSD method) (data.datasets.multi_modal_img_text.base_multi_modal_img_text.BaseMultiModalImgText method) (data.sampler.base_sampler.BaseSampler method) (data.sampler.base_sampler.BaseSamplerDDP method) (data.sampler.batch_sampler.BatchSampler method), [1] (data.sampler.batch_sampler.BatchSamplerDDP method), [1] (data.sampler.multi_scale_sampler.MultiScaleSampler method), [1] (data.sampler.multi_scale_sampler.MultiScaleSamplerDDP method), [1] (data.sampler.variable_batch_sampler.VariableBatchSampler method), [1] (data.sampler.variable_batch_sampler.VariableBatchSamplerDDP method), [1] (loss_fn.base_criteria.BaseCriteria method) (loss_fn.classification.binary_cross_entropy.BinaryCrossEntropy method) (loss_fn.classification.cross_entropy.CrossEntropy method) (loss_fn.detection.mask_rcnn_loss.MaskRCNNLoss method) (loss_fn.detection.ssd_multibox_loss.SSDLoss method) (loss_fn.distillation.hard_distillation.HardDistillationLoss method) (loss_fn.distillation.soft_kl_distillation.SoftKLLoss method) (loss_fn.neural_augmentation.NeuralAugmentation method) (loss_fn.segmentation.cross_entropy.SegCrossEntropy method) (optim.scheduler.base_scheduler.BaseLRScheduler method) extract_content() (in module data.datasets.multi_modal_img_text.img_text_tar_dataset) extract_end_points_all() (cvnets.models.classification.base_image_encoder.BaseImageEncoder method) (cvnets.models.classification.swin_transformer.SwinTransformer method) (cvnets.models.classification.vit.VisionTransformer method) extract_end_points_l4() (cvnets.models.classification.base_image_encoder.BaseImageEncoder method) extract_features() (cvnets.models.classification.base_image_encoder.BaseImageEncoder method) (cvnets.models.classification.vit.VisionTransformer method) extract_opts_with_prefix_replacement() (in module options.utils) extract_patch_embeddings() (cvnets.models.classification.vit.VisionTransformer method)

F

FastRCNNConvFCHead (class in cvnets.models.detection.utils.rcnn_utils) FastRCNNPredictor (class in cvnets.models.detection.utils.rcnn_utils) FastViT (class in cvnets.models.classification.fastvit) FeaturePyramidNetwork (class in cvnets.modules) (class in cvnets.modules.feature_pyramid) fetch_labels_from_timestamps() (in module data.datasets.utils.video) file_has_allowed_extension() (in module data.datasets.utils.common) file_has_valid_image_extension() (in module data.datasets.utils.common) filter_keys() (in module utils.dict_utils) find_easy_samples() (engine.training_engine.Trainer method) FixedLRScheduler (class in optim.scheduler.fixed) FixedSampler (class in cvnets.neural_augmentor.utils.neural_aug_utils) FixedSizeCrop (class in data.transforms.image_pil) Flatten (class in cvnets.layers) (class in cvnets.layers.flatten) flatten_to_dict() (in module utils.object_utils) flatten_yaml_as_dict() (in module options.utils) FlickrDataset (class in data.datasets.multi_modal_img_text.flickr) folding() (cvnets.modules.mobilevit_block.MobileViTBlock method) (cvnets.modules.MobileViTBlock method) folding_coreml() (cvnets.modules.mobilevit_block.MobileViTBlockv2 method) (cvnets.modules.MobileViTBlockv2 method) folding_pytorch() (cvnets.modules.mobilevit_block.MobileViTBlockv2 method) (cvnets.modules.MobileViTBlockv2 method) forward() (cvnets.anchor_generator.base_anchor_generator.BaseAnchorGenerator method) (cvnets.image_projection_layers.attention_pool_2d.AttentionPool2dHead method) (cvnets.image_projection_layers.base_image_projection.BaseImageProjectionHead method) (cvnets.image_projection_layers.global_pool_2d.GlobalPool2D method) (cvnets.image_projection_layers.simple_projection_head.SimpleImageProjectionHead method) (cvnets.layers.activation.hard_sigmoid.Hardsigmoid method) (cvnets.layers.activation.hard_swish.Hardswish method) (cvnets.layers.base_layer.BaseLayer method) (cvnets.layers.conv_layer.NormActLayer method) (cvnets.layers.conv_layer.TransposeConvLayer2d method) (cvnets.layers.global_pool.GlobalPool method) (cvnets.layers.GlobalPool method) (cvnets.layers.GroupLinear method) (cvnets.layers.Identity method) (cvnets.layers.identity.Identity method) (cvnets.layers.linear_attention.LinearSelfAttention method) (cvnets.layers.linear_layer.GroupLinear method) (cvnets.layers.linear_layer.LinearLayer method) (cvnets.layers.LinearLayer method) (cvnets.layers.LinearSelfAttention method) (cvnets.layers.multi_head_attention.MultiHeadAttention method) (cvnets.layers.MultiHeadAttention method) (cvnets.layers.NormActLayer method) (cvnets.layers.normalization.batch_norm.BatchNorm2dFP32 method) (cvnets.layers.normalization.layer_norm.LayerNorm method) (cvnets.layers.normalization.layer_norm.LayerNormFP32 method) (cvnets.layers.normalization.sync_batch_norm.SyncBatchNormFP32 method) (cvnets.layers.positional_embedding.LearnablePositionalEmbedding method) (cvnets.layers.positional_embedding.PositionalEmbedding method) (cvnets.layers.positional_embedding.SinusoidalPositionalEmbedding method) (cvnets.layers.positional_encoding.LearnablePositionEncoding method) (cvnets.layers.positional_encoding.SinusoidalPositionalEncoding method) (cvnets.layers.PositionalEmbedding method) (cvnets.layers.random_layers.RandomApply method) (cvnets.layers.single_head_attention.SingleHeadAttention method) (cvnets.layers.SingleHeadAttention method) (cvnets.layers.token_merging.TokenMerging method) (cvnets.layers.TransposeConvLayer2d method) (cvnets.models.audio_classification.audio_byteformer.AudioByteFormer method) (cvnets.models.base_model.BaseAnyNNModel method) (cvnets.models.classification.base_image_encoder.BaseImageEncoder method) (cvnets.models.classification.byteformer.ByteFormer method) (cvnets.models.classification.vit.VisionTransformer method) (cvnets.models.detection.mask_rcnn.MaskRCNNDetector method) (cvnets.models.detection.mask_rcnn.MaskRCNNEncoder method) (cvnets.models.detection.ssd.SingleShotMaskDetector method) (cvnets.models.detection.utils.rcnn_utils.FastRCNNPredictor method) (cvnets.models.detection.utils.rcnn_utils.RPNHead method) (cvnets.models.multi_modal_img_text.clip.CLIP method) (cvnets.models.segmentation.enc_dec.SegEncoderDecoder method) (cvnets.models.segmentation.heads.base_seg_head.BaseSegHead method) (cvnets.modules.AnyRegNetStage method) (cvnets.modules.ASPP method) (cvnets.modules.aspp_block.ASPP method) (cvnets.modules.aspp_block.ASPPPooling method) (cvnets.modules.base_module.BaseModule method) (cvnets.modules.BasicResNetBlock method) (cvnets.modules.BottleneckResNetBlock method) (cvnets.modules.efficientnet.EfficientNetBlock method) (cvnets.modules.EfficientNetBlock method) (cvnets.modules.fastvit.AttentionBlock method) (cvnets.modules.fastvit.ConvFFN method) (cvnets.modules.fastvit.PatchEmbed method) (cvnets.modules.fastvit.RepCPE method) (cvnets.modules.fastvit.RepMixer method) (cvnets.modules.fastvit.RepMixerBlock method) (cvnets.modules.feature_pyramid.FeaturePyramidNetwork method) (cvnets.modules.FeaturePyramidNetwork method) (cvnets.modules.InvertedResidual method) (cvnets.modules.InvertedResidualSE method) (cvnets.modules.mobilenetv2.InvertedResidual method) (cvnets.modules.mobilenetv2.InvertedResidualSE method) (cvnets.modules.mobileone_block.MobileOneBlock method) (cvnets.modules.mobileone_block.RepLKBlock method) (cvnets.modules.MobileOneBlock method) (cvnets.modules.mobilevit_block.MobileViTBlock method) (cvnets.modules.mobilevit_block.MobileViTBlockv2 method) (cvnets.modules.MobileViTBlock method) (cvnets.modules.MobileViTBlockv2 method) (cvnets.modules.PatchMerging method) (cvnets.modules.Permute method) (cvnets.modules.PSP method) (cvnets.modules.pspnet_module.PSP method) (cvnets.modules.regnet_modules.AnyRegNetStage method) (cvnets.modules.regnet_modules.XRegNetBlock method) (cvnets.modules.RepLKBlock method) (cvnets.modules.resnet_modules.BasicResNetBlock method) (cvnets.modules.resnet_modules.BottleneckResNetBlock method) (cvnets.modules.squeeze_excitation.SqueezeExcitation method) (cvnets.modules.SqueezeExcitation method) (cvnets.modules.ssd_heads.SSDHead method) (cvnets.modules.ssd_heads.SSDInstanceHead method) (cvnets.modules.SSDHead method) (cvnets.modules.SSDInstanceHead method) (cvnets.modules.swin_transformer_block.PatchMerging method) (cvnets.modules.swin_transformer_block.Permute method) (cvnets.modules.swin_transformer_block.ShiftedWindowAttention method) (cvnets.modules.swin_transformer_block.SwinTransformerBlock method) (cvnets.modules.SwinTransformerBlock method) (cvnets.modules.transformer.LinearAttnFFN method) (cvnets.modules.transformer.TransformerEncoder method) (cvnets.modules.TransformerEncoder method) (cvnets.modules.windowed_transformer.WindowedTransformerEncoder method) (cvnets.modules.WindowedTransformerEncoder method) (cvnets.modules.XRegNetBlock method) (cvnets.neural_augmentor.neural_aug.BaseNeuralAugmentor method) (cvnets.neural_augmentor.utils.neural_aug_utils.Clip method) (cvnets.neural_augmentor.utils.neural_aug_utils.FixedSampler method) (cvnets.neural_augmentor.utils.neural_aug_utils.Identity method) (cvnets.neural_augmentor.utils.neural_aug_utils.UniformSampler method) (cvnets.text_encoders.base_text_encoder.BaseTextEncoder method) (cvnets.text_encoders.transformer.TextTransformer method) (data.text_tokenizer.base_tokenizer.BaseTokenizer method) (data.text_tokenizer.clip_tokenizer.ClipTokenizer method) (loss_fn.base_criteria.BaseCriteria method) (loss_fn.classification.base_classification_criteria.BaseClassificationCriteria method) (loss_fn.composite_loss.CompositeLoss method) (loss_fn.detection.mask_rcnn_loss.MaskRCNNLoss method) (loss_fn.detection.ssd_multibox_loss.SSDLoss method) (loss_fn.distillation.base_distillation.BaseDistillationCriteria method) (loss_fn.multi_modal_img_text.contrastive_loss_clip.ContrastiveLossClip method) (loss_fn.neural_augmentation.NeuralAugmentation method) (loss_fn.segmentation.cross_entropy.SegCrossEntropy method)

forward_aux_head() (cvnets.models.segmentation.heads.base_seg_head.BaseSegHead method) forward_classifier() (cvnets.models.classification.base_image_encoder.BaseImageEncoder method) (cvnets.models.classification.vit.VisionTransformer method) forward_default() (cvnets.layers.multi_head_attention.MultiHeadAttention method) (cvnets.layers.MultiHeadAttention method) forward_embedding() (cvnets.text_encoders.transformer.TextTransformer method) forward_others() (cvnets.layers.positional_encoding.SinusoidalPositionalEncoding method) forward_patch_last() (cvnets.layers.positional_encoding.SinusoidalPositionalEncoding method) forward_pytorch() (cvnets.layers.multi_head_attention.MultiHeadAttention method) (cvnets.layers.MultiHeadAttention method) forward_seg_head() (cvnets.models.segmentation.heads.base_seg_head.BaseSegHead method) (cvnets.models.segmentation.heads.deeplabv3.DeeplabV3 method) (cvnets.models.segmentation.heads.pspnet.PSPNet method) (cvnets.models.segmentation.heads.simple_seg_head.SimpleSegHead method) forward_spatial() (cvnets.modules.mobilevit_block.MobileViTBlock method) (cvnets.modules.mobilevit_block.MobileViTBlockv2 method) (cvnets.modules.MobileViTBlock method) (cvnets.modules.MobileViTBlockv2 method) forward_temporal() (cvnets.modules.mobilevit_block.MobileViTBlock method) (cvnets.modules.mobilevit_block.MobileViTBlockv2 method) (cvnets.modules.MobileViTBlock method) (cvnets.modules.MobileViTBlockv2 method) forward_tracing() (cvnets.layers.multi_head_attention.MultiHeadAttention method) (cvnets.layers.MultiHeadAttention method) forward_zero_shot() (cvnets.text_encoders.transformer.TextTransformer method) freeze_module() (in module cvnets.misc.common) freeze_modules_based_on_opts() (in module cvnets.misc.common) freeze_norm_layers() (cvnets.models.base_model.BaseAnyNNModel class method) (cvnets.text_encoders.base_text_encoder.BaseTextEncoder method)

G

Gain (class in data.transforms.audio) gather() (in module utils.third_party.ddp_functional_utils) gather_all_features() (in module utils.tensor_utils) gather_features() (in module loss_fn.multi_modal_img_text.contrastive_loss_clip) gather_metrics() (metrics.intersection_over_union.IOUMetric method) (metrics.metric_base.AverageMetric method) (metrics.metric_base_test.DummyMetric method) (metrics.misc.GradNormMetric method) (metrics.misc.LossMetric method) (metrics.psnr.PSNRMetric method) (metrics.topk_accuracy.TopKMetric method) GELU (class in cvnets.layers.activation.gelu) general_lr_sch_args() (in module optim.scheduler) generate_anchors() (data.datasets.detection.coco_ssd.COCODetectionSSD method) generate_plots() (in module loss_landscape.landscape_utils) generate_text_prompts() (data.datasets.multi_modal_img_text.zero_shot.base_zero_shot.BaseZeroShotDataset static method) (data.datasets.multi_modal_img_text.zero_shot.imagenet.ImageNetDatasetZeroShot static method) generate_text_prompts_clip() (in module data.datasets.multi_modal_img_text.zero_shot.templates) get_aggregates() (metrics.image_text_retrieval.ImageTextRetrievalMetric method) (metrics.metric_base.EpochMetric method) get_augmentation_transforms() (data.datasets.dataset_base.BaseDataset method) get_augmented_tensor() (cvnets.models.detection.mask_rcnn.MaskRCNNEncoder method) get_backbone_features() (cvnets.models.detection.ssd.SingleShotMaskDetector method) get_backbone_inputs() (cvnets.models.classification.byteformer.ByteFormer method) get_basic_local_path() (in module utils.download_utils_base) get_batch_size() (in module engine.utils) get_batch_size_from_opts() (in module data.sampler.base_sampler) get_benchmarking_arguments() (in module options.opts) get_bit_at_idx() (utils.color_map.Colormap static method) get_box_color_codes() (utils.color_map.Colormap method) get_boxes_and_labels() (data.datasets.detection.coco_base.COCODetection method) get_color_map() (utils.color_map.Colormap method) get_color_map_list() (utils.color_map.Colormap method) get_configuration() (in module cvnets.models.classification.config.byteformer) (in module cvnets.models.classification.config.efficientnet) (in module cvnets.models.classification.config.fastvit) (in module cvnets.models.classification.config.mobilenetv1) (in module cvnets.models.classification.config.mobilenetv2) (in module cvnets.models.classification.config.mobilenetv3) (in module cvnets.models.classification.config.mobileone) (in module cvnets.models.classification.config.mobilevit) (in module cvnets.models.classification.config.mobilevit_v2) (in module cvnets.models.classification.config.regnet) (in module cvnets.models.classification.config.resnet) (in module cvnets.models.classification.config.swin_transformer) (in module cvnets.models.classification.config.vit) get_conversion_arguments() (in module options.opts) get_curr_time_stamp() (in module utils.logger) get_dataset() (data.datasets.multi_modal_img_text.base_multi_modal_img_text.BaseMultiModalImgText method) (data.datasets.multi_modal_img_text.flickr.FlickrDataset method) (data.datasets.multi_modal_img_text.img_text_tar_dataset.ImgTextTarDataset method) get_dataset_pair() (data.datasets.multi_modal_img_text.base_multi_modal_img_text.BaseMultiModalImgText method) (data.datasets.multi_modal_img_text.img_text_tar_dataset.ImgTextTarDataset method) get_downsampler() (cvnets.models.classification.byteformer.ByteFormer method) get_downsampler_name() (cvnets.models.classification.byteformer.ByteFormer method) get_encodings() (data.text_tokenizer.base_tokenizer.BaseTokenizer method) (data.text_tokenizer.clip_tokenizer.ClipTokenizer method) get_eot_token() (data.text_tokenizer.base_tokenizer.BaseTokenizer method) (data.text_tokenizer.clip_tokenizer.ClipTokenizer method) get_eval_arguments() (in module options.opts) get_exportable_model() (cvnets.models.base_model.BaseAnyNNModel method) (cvnets.models.classification.base_image_encoder.BaseImageEncoder method) (cvnets.models.classification.fastvit.FastViT method) (cvnets.models.classification.mobileone.MobileOne method) get_frame_transform() (data.video_reader.base_av_reader.BaseAVReader static method)

get_image() (data.datasets.detection.coco_base.COCODetection method) get_image_paths() (in module data.datasets.utils.common) get_in_feature_dimension() (in module cvnets.image_projection_layers.base_image_projection) get_indices() (data.sampler.base_sampler.BaseSampler method) get_indices_rank_i() (data.sampler.base_sampler.BaseSamplerDDP method) get_item_metadata() (data.datasets.dataset_base.BaseDataset method) (data.datasets.dataset_base.BaseVideoDataset method) get_log_writers() (in module engine.utils) get_loss_landscape_args() (in module options.opts) get_lr() (optim.scheduler.base_scheduler.BaseLRScheduler method) (optim.scheduler.cosine.CosineScheduler method) (optim.scheduler.cyclic.CyclicLRScheduler method) (optim.scheduler.fixed.FixedLRScheduler method) (optim.scheduler.multi_step.MultiStepLRScheduler method) (optim.scheduler.polynomial.PolynomialScheduler method) get_mfcc_features() (in module data.transforms.audio_aux.mfccs) get_mfccs() (in module data.transforms.audio_aux.mfccs) get_model() (in module cvnets.models) get_model_state_dict() (in module utils.checkpoint_utils) get_node_rank() (in module utils.ddp_utils) get_normalization_layer() (in module cvnets.layers) get_num_data_samples_as_int_or_mapping() (in module data.data_loaders) get_padded_features() (in module data.transforms.audio_aux.mfccs) get_params() (data.transforms.image_pil.RandomCrop static method) (data.transforms.video.RandomCrop method) (data.transforms.video.RandomResizedCrop method) (data.transforms.video.RandomShortSizeResizeCrop method) get_params_from_box() (data.transforms.image_pil.RandomCrop static method) get_params_from_mask() (data.transforms.image_pil.RandomCrop method) get_rrc_params() (data.transforms.image_pil.RandomResizedCrop method) get_sample() (data.datasets.audio_classification.speech_commands_v2.SpeechCommandsv2Dataset method) get_sample_indices() (data.loader.dataloader.CVNetsDataLoader method) get_sot_token() (data.text_tokenizer.base_tokenizer.BaseTokenizer method) (data.text_tokenizer.clip_tokenizer.ClipTokenizer method) get_tensor_sizes() (in module cvnets.misc.common) get_test_dataset() (in module data.datasets) get_train_val_datasets() (in module data.datasets) get_trainable_parameters() (cvnets.image_projection_layers.base_image_projection.BaseImageProjectionHead method) (cvnets.layers.base_layer.BaseLayer method) (cvnets.models.base_model.BaseAnyNNModel method) (cvnets.models.classification.base_image_encoder.BaseImageEncoder method) (cvnets.models.detection.mask_rcnn.MaskRCNNDetector method) (cvnets.models.detection.mask_rcnn.MaskRCNNEncoder method) (cvnets.models.multi_modal_img_text.clip.CLIP method) (cvnets.models.segmentation.enc_dec.SegEncoderDecoder method) (cvnets.models.segmentation.heads.base_seg_head.BaseSegHead method) (cvnets.neural_augmentor.neural_aug.BaseNeuralAugmentor method) (cvnets.text_encoders.base_text_encoder.BaseTextEncoder method) get_training_arguments() (in module options.opts) get_training_state() (in module utils.checkpoint_utils) get_transformed_sample() (data.datasets.audio_classification.speech_commands_v2.SpeechCommandsv2Dataset method) get_video_reader() (in module data.video_reader) get_vocab_size() (data.text_tokenizer.base_tokenizer.BaseTokenizer method) (data.text_tokenizer.clip_tokenizer.ClipTokenizer method) get_weights() (cvnets.layers.positional_embedding.SinusoidalPositionalEmbedding method) get_windows_shift_mask() (in module cvnets.modules.windowed_transformer) get_world_size() (in module utils.ddp_utils) get_zero_shot_dataset() (data.datasets.multi_modal_img_text.base_multi_modal_img_text.BaseMultiModalImgText method) get_zero_shot_pair() (data.datasets.multi_modal_img_text.base_multi_modal_img_text.BaseMultiModalImgText method) GlobalPool (class in cvnets.layers) (class in cvnets.layers.global_pool) GlobalPool2D (class in cvnets.image_projection_layers.global_pool_2d) GradNormMetric (class in metrics.misc) GroupLinear (class in cvnets.layers) (class in cvnets.layers.linear_layer) GroupNorm (class in cvnets.layers.normalization.group_norm)

H

hard_negative_mining() (in module cvnets.misc.third_party.ssd_utils) HardDistillationLoss (class in loss_fn.distillation.hard_distillation)

Hardsigmoid (class in cvnets.layers.activation.hard_sigmoid) Hardswish (class in cvnets.layers.activation.hard_swish) high (cvnets.neural_augmentor.utils.neural_aug_utils.UniformSampler property)

I

Identity (class in cvnets.layers) (class in cvnets.layers.identity) (class in cvnets.neural_augmentor.utils.neural_aug_utils) identity() (in module cvnets.neural_augmentor.utils.neural_aug_utils) ignore_bn() (in module loss_landscape.landscape_utils) ignore_exception_with_warning() (in module utils.logger) image_batch_pairs() (in module data.sampler.utils) image_classification_data_collate_fn() (in module data.collate_fns.collate_functions) image_size_from_opts() (in module utils.tensor_utils) ImageNetADataset (class in data.datasets.classification.imagenet_a) ImageNetDataset (class in data.datasets.classification.imagenet) ImageNetDatasetZeroShot (class in data.datasets.multi_modal_img_text.zero_shot.imagenet) ImageNetRDataset (class in data.datasets.classification.imagenet_r) ImageNetSketchDataset (class in data.datasets.classification.imagenet_sketch) Imagenetv2Dataset (class in data.datasets.classification.imagenet_v2) ImageTextRetrievalMetric (class in metrics.image_text_retrieval) ImgTextTarDataset (class in data.datasets.multi_modal_img_text.img_text_tar_dataset) import_modules_from_folder() (in module utils.import_utils) info() (cvnets.models.base_model.BaseAnyNNModel method) (in module utils.logger)

initialize_conv_layer() (in module cvnets.misc.init_utils) initialize_fc_layer() (in module cvnets.misc.init_utils) initialize_norm_layers() (in module cvnets.misc.init_utils) initialize_weights() (in module cvnets.misc.init_utils) InstanceNorm1d (class in cvnets.layers.normalization.instance_norm) InstanceNorm2d (class in cvnets.layers.normalization.instance_norm) InstanceProcessor (class in data.transforms.image_pil) intersect() (in module data.transforms.utils) InvertedResidual (class in cvnets.modules) (class in cvnets.modules.mobilenetv2) InvertedResidualSE (class in cvnets.modules) (class in cvnets.modules.mobilenetv2) IOUMetric (class in metrics.intersection_over_union) is_coreml_conversion() (in module utils.common_utils) is_iterable() (in module utils.object_utils) is_master() (in module utils.ddp_utils) is_pytest_environment() (in module utils.object_utils) is_start_rank_node() (in module utils.ddp_utils) items() (utils.registry.Registry method) iter_summary() (metrics.stats.Statistics method)

J

jaccard_numpy() (in module data.transforms.utils)

JsonValidator (class in options.parse_args)

K

K (metrics.topk_accuracy.Top1Metric attribute) (metrics.topk_accuracy.Top5Metric attribute) (metrics.topk_accuracy.TopKMetric attribute)

keys() (utils.registry.Registry method)

L

l2_distance_matrix() (in module metrics.retrieval_cmc) labels (cvnets.models.detection.DetectionPredTuple attribute) LambdaAudio (class in data.transforms.audio) LayerNorm (class in cvnets.layers.normalization.layer_norm) LayerNorm2D_NCHW (class in cvnets.layers.normalization.layer_norm) LayerNormFP32 (class in cvnets.layers.normalization.layer_norm) LeakyReLU (class in cvnets.layers.activation.leaky_relu) LearnablePositionalEmbedding (class in cvnets.layers.positional_embedding) LearnablePositionEncoding (class in cvnets.layers.positional_encoding) linear_curriculum() (in module loss_fn.neural_augmentation) LinearAttnFFN (class in cvnets.modules.transformer) LinearLayer (class in cvnets.layers) (class in cvnets.layers.linear_layer) LinearSelfAttention (class in cvnets.layers) (class in cvnets.layers.linear_attention) load_checkpoint() (in module utils.checkpoint_utils) load_config_file() (in module options.utils) load_from_server() (data.datasets.dataset_base.BaseDataset static method) load_model_state() (in module utils.checkpoint_utils) load_noise_files() (data.transforms.audio.Noise method) load_pretrained_model() (in module cvnets.misc.common) load_state_dict() (in module utils.checkpoint_utils) log() (in module utils.logger) log_metrics() (in module engine.utils) loss_fn module loss_fn.base_criteria module loss_fn.classification module loss_fn.classification.base_classification_criteria module loss_fn.classification.binary_cross_entropy module loss_fn.classification.cross_entropy module loss_fn.composite_loss module loss_fn.detection module

loss_fn.detection.base_detection_criteria module loss_fn.detection.mask_rcnn_loss module loss_fn.detection.ssd_multibox_loss module loss_fn.distillation module loss_fn.distillation.base_distillation module loss_fn.distillation.hard_distillation module loss_fn.distillation.soft_kl_distillation module loss_fn.multi_modal_img_text module loss_fn.multi_modal_img_text.base_multi_modal_img_text_criteria module loss_fn.multi_modal_img_text.contrastive_loss_clip module loss_fn.neural_augmentation module loss_fn.segmentation module loss_fn.segmentation.base_segmentation_criteria module loss_fn.segmentation.cross_entropy module loss_fn.utils module loss_fn.utils.build_helper module loss_fn.utils.class_weighting module loss_landscape module loss_landscape.landscape_utils module LossMetric (class in metrics.misc) low (cvnets.neural_augmentor.utils.neural_aug_utils.UniformSampler property)

M

main_detection_evaluation() (in module engine.eval_detection) main_segmentation_evaluation() (in module engine.eval_segmentation) make_divisible() (in module utils.math_utils) make_tuple_list() (in module data.sampler.utils) make_video_pairs() (in module data.sampler.utils) MaskPositions (class in data.transforms.image_bytes) MaskRCNNDetector (class in cvnets.models.detection.mask_rcnn) MaskRCNNEncoder (class in cvnets.models.detection.mask_rcnn) MaskRCNNHeads (class in cvnets.models.detection.utils.rcnn_utils) MaskRCNNLoss (class in loss_fn.detection.mask_rcnn_loss) MaskRCNNPredictor (class in cvnets.models.detection.utils.rcnn_utils) masks (cvnets.models.detection.DetectionPredTuple attribute) MaxPool2d (class in cvnets.layers) (class in cvnets.layers.pooling) maybe_seg_norm_layer() (cvnets.models.segmentation.base_seg.BaseSegmentation method) mean_ap() (in module metrics.retrieval_cmc) metrics module metrics.average_precision module metrics.coco_map module metrics.confusion_mat module metrics.image_text_retrieval module metrics.intersection_over_union module metrics.metric_base module metrics.metric_base_test module metrics.misc module metrics.probability_histograms module metrics.psnr module metrics.retrieval_cmc module metrics.stats module metrics.topk_accuracy module MFCCs (class in data.transforms.audio) MobileNetv1 (class in cvnets.models.classification.mobilenetv1) MobileNetV2 (class in cvnets.models.classification.mobilenetv2) MobileNetV3 (class in cvnets.models.classification.mobilenetv3) MobileOne (class in cvnets.models.classification.mobileone) MobileOneBlock (class in cvnets.modules) (class in cvnets.modules.mobileone_block) MobileViT (class in cvnets.models.classification.mobilevit) MobileViTBlock (class in cvnets.modules) (class in cvnets.modules.mobilevit_block) MobileViTBlockv2 (class in cvnets.modules) (class in cvnets.modules.mobilevit_block) MobileViTv2 (class in cvnets.models.classification.mobilevit_v2) modeling_arguments() (in module cvnets) module cvnets cvnets.anchor_generator cvnets.anchor_generator.base_anchor_generator cvnets.anchor_generator.ssd_anchor_generator cvnets.image_projection_layers cvnets.image_projection_layers.attention_pool_2d cvnets.image_projection_layers.base_image_projection cvnets.image_projection_layers.global_pool_2d cvnets.image_projection_layers.simple_projection_head cvnets.layers cvnets.layers.activation cvnets.layers.activation.gelu cvnets.layers.activation.hard_sigmoid cvnets.layers.activation.hard_swish cvnets.layers.activation.leaky_relu cvnets.layers.activation.prelu cvnets.layers.activation.relu cvnets.layers.activation.relu6 cvnets.layers.activation.sigmoid cvnets.layers.activation.swish cvnets.layers.activation.tanh cvnets.layers.adaptive_pool cvnets.layers.base_layer cvnets.layers.conv_layer cvnets.layers.dropout cvnets.layers.embedding cvnets.layers.flatten cvnets.layers.global_pool cvnets.layers.identity cvnets.layers.linear_attention cvnets.layers.linear_layer cvnets.layers.multi_head_attention cvnets.layers.normalization cvnets.layers.normalization.batch_norm cvnets.layers.normalization.group_norm cvnets.layers.normalization.instance_norm cvnets.layers.normalization.layer_norm cvnets.layers.normalization.sync_batch_norm cvnets.layers.normalization_layers cvnets.layers.pixel_shuffle cvnets.layers.pooling cvnets.layers.positional_embedding cvnets.layers.positional_encoding cvnets.layers.random_layers cvnets.layers.single_head_attention cvnets.layers.softmax cvnets.layers.stochastic_depth cvnets.layers.token_merging cvnets.layers.upsample cvnets.matcher_det cvnets.matcher_det.base_matcher cvnets.matcher_det.ssd_matcher cvnets.misc cvnets.misc.averaging_utils cvnets.misc.box_utils cvnets.misc.common cvnets.misc.init_utils cvnets.misc.third_party cvnets.misc.third_party.ssd_utils cvnets.models cvnets.models.audio_classification cvnets.models.audio_classification.audio_byteformer cvnets.models.audio_classification.base_audio_classification cvnets.models.base_model cvnets.models.classification cvnets.models.classification.base_image_encoder cvnets.models.classification.byteformer cvnets.models.classification.config cvnets.models.classification.config.byteformer cvnets.models.classification.config.efficientnet cvnets.models.classification.config.fastvit cvnets.models.classification.config.mobilenetv1 cvnets.models.classification.config.mobilenetv2 cvnets.models.classification.config.mobilenetv3 cvnets.models.classification.config.mobileone cvnets.models.classification.config.mobilevit cvnets.models.classification.config.mobilevit_v2 cvnets.models.classification.config.regnet cvnets.models.classification.config.resnet cvnets.models.classification.config.swin_transformer cvnets.models.classification.config.vit cvnets.models.classification.efficientnet cvnets.models.classification.fastvit cvnets.models.classification.mobilenetv1 cvnets.models.classification.mobilenetv2 cvnets.models.classification.mobilenetv3 cvnets.models.classification.mobileone cvnets.models.classification.mobilevit cvnets.models.classification.mobilevit_v2 cvnets.models.classification.regnet cvnets.models.classification.resnet cvnets.models.classification.swin_transformer cvnets.models.classification.vit cvnets.models.detection cvnets.models.detection.base_detection cvnets.models.detection.mask_rcnn cvnets.models.detection.ssd cvnets.models.detection.utils cvnets.models.detection.utils.rcnn_utils cvnets.models.multi_modal_img_text cvnets.models.multi_modal_img_text.base_multi_modal_img_text cvnets.models.multi_modal_img_text.clip cvnets.models.segmentation cvnets.models.segmentation.base_seg cvnets.models.segmentation.enc_dec cvnets.models.segmentation.heads cvnets.models.segmentation.heads.base_seg_head cvnets.models.segmentation.heads.deeplabv3 cvnets.models.segmentation.heads.pspnet cvnets.models.segmentation.heads.simple_seg_head cvnets.modules cvnets.modules.aspp_block cvnets.modules.base_module cvnets.modules.efficientnet cvnets.modules.fastvit cvnets.modules.feature_pyramid cvnets.modules.mobilenetv2 cvnets.modules.mobileone_block cvnets.modules.mobilevit_block cvnets.modules.pspnet_module cvnets.modules.regnet_modules cvnets.modules.resnet_modules cvnets.modules.squeeze_excitation cvnets.modules.ssd_heads cvnets.modules.swin_transformer_block cvnets.modules.transformer cvnets.modules.windowed_transformer cvnets.neural_augmentor cvnets.neural_augmentor.neural_aug cvnets.neural_augmentor.utils cvnets.neural_augmentor.utils.neural_aug_utils cvnets.text_encoders cvnets.text_encoders.base_text_encoder cvnets.text_encoders.transformer data data.collate_fns data.collate_fns.byteformer_collate_functions data.collate_fns.collate_functions data.data_loaders data.datasets data.datasets.audio_classification data.datasets.audio_classification.speech_commands_v2 data.datasets.classification data.datasets.classification.base_image_classification_dataset data.datasets.classification.base_imagenet_shift_dataset data.datasets.classification.imagenet data.datasets.classification.imagenet_a data.datasets.classification.imagenet_r data.datasets.classification.imagenet_sketch data.datasets.classification.imagenet_synsets data.datasets.classification.imagenet_v2 data.datasets.classification.places365 data.datasets.dataset_base data.datasets.detection data.datasets.detection.base_detection data.datasets.detection.coco_base data.datasets.detection.coco_mask_rcnn data.datasets.detection.coco_ssd data.datasets.multi_modal_img_text data.datasets.multi_modal_img_text.base_multi_modal_img_text data.datasets.multi_modal_img_text.flickr data.datasets.multi_modal_img_text.img_text_tar_dataset data.datasets.multi_modal_img_text.zero_shot data.datasets.multi_modal_img_text.zero_shot.base_zero_shot data.datasets.multi_modal_img_text.zero_shot.imagenet data.datasets.multi_modal_img_text.zero_shot.imagenet_class_names data.datasets.multi_modal_img_text.zero_shot.templates data.datasets.segmentation data.datasets.segmentation.ade20k data.datasets.segmentation.base_segmentation data.datasets.segmentation.coco_segmentation data.datasets.segmentation.pascal_voc data.datasets.utils data.datasets.utils.common data.datasets.utils.text data.datasets.utils.video data.loader data.loader.dataloader data.sampler data.sampler.base_sampler data.sampler.batch_sampler, [1] data.sampler.chain_sampler data.sampler.multi_scale_sampler, [1] data.sampler.utils data.sampler.variable_batch_sampler, [1] data.text_tokenizer data.text_tokenizer.base_tokenizer data.text_tokenizer.clip_tokenizer data.transforms data.transforms.audio data.transforms.audio_aux data.transforms.audio_aux.mfccs data.transforms.audio_bytes data.transforms.base_transforms data.transforms.common data.transforms.image_bytes data.transforms.image_pil data.transforms.image_torch data.transforms.utils data.transforms.video data.video_reader data.video_reader.base_av_reader data.video_reader.decord_reader data.video_reader.pyav_reader engine engine.detection_utils engine.detection_utils.coco_map engine.eval_detection engine.eval_segmentation engine.evaluation_engine engine.segmentation_utils engine.segmentation_utils.cityscapes_iou engine.training_engine engine.utils loss_fn loss_fn.base_criteria loss_fn.classification loss_fn.classification.base_classification_criteria loss_fn.classification.binary_cross_entropy loss_fn.classification.cross_entropy loss_fn.composite_loss loss_fn.detection loss_fn.detection.base_detection_criteria loss_fn.detection.mask_rcnn_loss loss_fn.detection.ssd_multibox_loss loss_fn.distillation loss_fn.distillation.base_distillation loss_fn.distillation.hard_distillation loss_fn.distillation.soft_kl_distillation loss_fn.multi_modal_img_text loss_fn.multi_modal_img_text.base_multi_modal_img_text_criteria loss_fn.multi_modal_img_text.contrastive_loss_clip loss_fn.neural_augmentation loss_fn.segmentation loss_fn.segmentation.base_segmentation_criteria loss_fn.segmentation.cross_entropy loss_fn.utils loss_fn.utils.build_helper loss_fn.utils.class_weighting loss_landscape loss_landscape.landscape_utils metrics metrics.average_precision metrics.coco_map metrics.confusion_mat metrics.image_text_retrieval metrics.intersection_over_union metrics.metric_base metrics.metric_base_test metrics.misc metrics.probability_histograms metrics.psnr metrics.retrieval_cmc metrics.stats metrics.topk_accuracy optim optim.adam optim.adamw optim.base_optim optim.scheduler optim.scheduler.base_scheduler optim.scheduler.cosine optim.scheduler.cyclic optim.scheduler.fixed optim.scheduler.multi_step optim.scheduler.polynomial optim.sgd options options.errors options.opts options.parse_args options.utils utils utils.checkpoint_utils utils.color_map utils.common_utils utils.ddp_utils utils.dict_utils utils.download_utils utils.download_utils_base utils.import_utils utils.logger utils.math_utils utils.object_utils utils.object_utils_test utils.pytorch_to_coreml utils.registry utils.registry_test utils.resources utils.tensor_utils utils.third_party utils.third_party.ddp_functional_utils utils.visualization_utils

module_cls (cvnets.layers.conv_layer.ConvLayer1d attribute) (cvnets.layers.conv_layer.ConvLayer2d attribute) (cvnets.layers.conv_layer.ConvLayer3d attribute) (cvnets.layers.ConvLayer1d attribute) (cvnets.layers.ConvLayer2d attribute) (cvnets.layers.ConvLayer3d attribute) move_to_device() (in module utils.common_utils) multi_modal_img_text_collate_fn() (in module data.datasets.multi_modal_img_text.base_multi_modal_img_text) MultiHeadAttention (class in cvnets.layers) (class in cvnets.layers.multi_head_attention) MultiScaleSampler (class in data.sampler.multi_scale_sampler), [1] MultiScaleSamplerDDP (class in data.sampler.multi_scale_sampler), [1] MultiStepLRScheduler (class in optim.scheduler.multi_step)

N

n_frames_per_clip (data.datasets.dataset_base.BaseVideoDataset property) ndim (cvnets.layers.conv_layer.ConvLayer1d attribute) (cvnets.layers.conv_layer.ConvLayer2d attribute) (cvnets.layers.conv_layer.ConvLayer3d attribute) (cvnets.layers.ConvLayer1d attribute) (cvnets.layers.ConvLayer2d attribute) (cvnets.layers.ConvLayer3d attribute)

NeuralAugmentation (class in loss_fn.neural_augmentation) Noise (class in data.transforms.audio) NormActLayer (class in cvnets.layers) (class in cvnets.layers.conv_layer) normalize_filter() (in module loss_landscape.landscape_utils) num_anchors_per_os() (cvnets.anchor_generator.base_anchor_generator.BaseAnchorGenerator method) (cvnets.anchor_generator.ssd_anchor_generator.SSDAnchorGenerator method) num_frames() (data.video_reader.base_av_reader.BaseAVReader method)

O

optim module optim.adam module optim.adamw module optim.base_optim module optim.scheduler module optim.scheduler.base_scheduler module optim.scheduler.cosine module optim.scheduler.cyclic module optim.scheduler.fixed module

optim.scheduler.multi_step module optim.scheduler.polynomial module optim.sgd module options module options.errors module options.opts module options.parse_args module options.utils module

P

pad_x_and_mask() (in module cvnets.layers.token_merging) parameter_list() (in module cvnets.misc.common) parse_key() (utils.registry.Registry method) parse_validation_metric_names() (in module options.parse_args) ParseKwargs (class in options.opts) parser_to_opts() (in module options.opts) PascalVOCDataset (class in data.datasets.segmentation.pascal_voc) PatchEmbed (class in cvnets.modules.fastvit) PatchMerging (class in cvnets.modules) (class in cvnets.modules.swin_transformer_block) Permute (class in cvnets.modules) (class in cvnets.modules.swin_transformer_block) PhotometricDistort (class in data.transforms.image_pil) PILSave (class in data.transforms.image_bytes) PixelShuffle (class in cvnets.layers) (class in cvnets.layers.pixel_shuffle) Places365Dataset (class in data.datasets.classification.places365) plot_save_graphs() (in module loss_landscape.landscape_utils) PolynomialScheduler (class in optim.scheduler.polynomial) pool_types (cvnets.layers.global_pool.GlobalPool attribute) (cvnets.layers.GlobalPool attribute) PositionalEmbedding (class in cvnets.layers) (class in cvnets.layers.positional_embedding) post_init_checks() (data.datasets.classification.base_imagenet_shift_dataset.BaseImageNetShiftDataset method)

postprocess_detections() (cvnets.models.detection.ssd.SingleShotMaskDetector method) predict() (cvnets.models.detection.mask_rcnn.MaskRCNNDetector method) (cvnets.models.detection.ssd.SingleShotMaskDetector method) predict_and_save() (in module engine.eval_detection) (in module engine.eval_segmentation) predict_image() (in module engine.eval_detection) (in module engine.eval_segmentation) predict_images_in_folder() (in module engine.eval_detection) (in module engine.eval_segmentation) predict_labeled_dataset() (in module engine.eval_detection) (in module engine.eval_segmentation) PReLU (class in cvnets.layers.activation.prelu) prepare_cache_results() (metrics.coco_map.COCOEvaluator method) preprocess_predictions() (metrics.metric_base.BaseMetric method) preprocess_targets() (metrics.metric_base.BaseMetric method) print_header() (in module utils.logger) print_header_minor() (in module utils.logger) ProbabilityHistogramMetric (class in metrics.probability_histograms) process_anchors_ar() (cvnets.models.detection.ssd.SingleShotMaskDetector static method) PSNRMetric (class in metrics.psnr) PSP (class in cvnets.modules) (class in cvnets.modules.pspnet_module) PSPNet (class in cvnets.models.segmentation.heads.pspnet) PyAVReader (class in data.video_reader.pyav_reader) pytorch_default_collate_fn() (in module data.collate_fns.collate_functions)

R

rand_basis() (in module loss_landscape.landscape_utils) RandAugment (class in data.transforms.image_pil) RandAugmentTimm (class in data.transforms.image_pil) random_brightness() (in module cvnets.neural_augmentor.utils.neural_aug_utils) random_contrast() (in module cvnets.neural_augmentor.utils.neural_aug_utils) random_noise() (in module cvnets.neural_augmentor.utils.neural_aug_utils) random_sampling() (data.video_reader.base_av_reader.BaseAVReader static method) RandomApply (class in cvnets.layers.random_layers) RandomCrop (class in data.transforms.image_pil) (class in data.transforms.video) RandomCutmix (class in data.transforms.image_torch) RandomErasing (class in data.transforms.image_pil) RandomGaussianBlur (class in data.transforms.image_pil) RandomHorizontalFlip (class in data.transforms.image_pil) (class in data.transforms.video) RandomMixup (class in data.transforms.image_torch) RandomOrder (class in data.transforms.image_pil) RandomResize (class in data.transforms.image_pil) RandomResizedCrop (class in data.transforms.image_pil) (class in data.transforms.video) RandomRotate (class in data.transforms.image_pil) RandomShortSizeResize (class in data.transforms.image_pil) RandomShortSizeResizeCrop (class in data.transforms.video) RandomUniformNoise (class in data.transforms.image_bytes) read_and_process_image() (in module engine.eval_detection) (in module engine.eval_segmentation) read_image_pil() (data.datasets.dataset_base.BaseImageDataset static method) read_mask_pil() (data.datasets.segmentation.base_segmentation.BaseImageSegmentationDataset static method) read_video() (data.video_reader.base_av_reader.BaseAVReader method) (data.video_reader.decord_reader.DecordAVReader method) (data.video_reader.pyav_reader.PyAVReader method) read_video_file_into_clips() (data.video_reader.base_av_reader.BaseAVReader method) reduce() (in module utils.third_party.ddp_functional_utils) reduce_scatter() (in module utils.third_party.ddp_functional_utils) reduce_tensor() (in module utils.tensor_utils) reduce_tensor_sum() (in module utils.tensor_utils) register() (utils.registry.Registry method) register_act_fn() (in module cvnets.layers.activation) register_norm_fn() (in module cvnets.layers.normalization) Registry (class in utils.registry) RegNet (class in cvnets.models.classification.regnet) ReLU (class in cvnets.layers.activation.relu) ReLU6 (class in cvnets.layers.activation.relu6) remove_param_name_key() (in module optim) reparameterize() (cvnets.modules.fastvit.RepCPE method) (cvnets.modules.fastvit.RepMixer method) (cvnets.modules.mobileone_block.MobileOneBlock method) (cvnets.modules.mobileone_block.RepLKBlock method) (cvnets.modules.MobileOneBlock method) (cvnets.modules.RepLKBlock method) RepCPE (class in cvnets.modules.fastvit) replace_syncbn_with_syncbnfp32() (in module cvnets.models.detection.utils.rcnn_utils)

RepLKBlock (class in cvnets.modules) (class in cvnets.modules.mobileone_block) RepMixer (class in cvnets.modules.fastvit) RepMixerBlock (class in cvnets.modules.fastvit) reset() (metrics.coco_map.COCOEvaluator method) (metrics.confusion_mat.ConfusionMatrix method) (metrics.image_text_retrieval.ImageTextRetrievalMetric method) (metrics.metric_base.AverageMetric method) (metrics.metric_base.BaseMetric method) (metrics.metric_base.EpochMetric method) reset_generalized_rcnn_transform() (cvnets.models.detection.mask_rcnn.MaskRCNNDetector method) reset_head_parameters() (cvnets.models.segmentation.heads.base_seg_head.BaseSegHead method) reset_layer_parameters() (cvnets.models.detection.base_detection.BaseDetection static method) reset_layers() (cvnets.models.detection.ssd.SingleShotMaskDetector static method) reset_norm_layer_opts() (cvnets.models.detection.mask_rcnn.MaskRCNNDetector method) reset_parameters() (cvnets.image_projection_layers.attention_pool_2d.AttentionPool2dHead method) (cvnets.image_projection_layers.base_image_projection.BaseImageProjectionHead method) (cvnets.image_projection_layers.global_pool_2d.GlobalPool2D method) (cvnets.image_projection_layers.simple_projection_head.SimpleImageProjectionHead method) (cvnets.layers.Embedding method) (cvnets.layers.embedding.Embedding method) (cvnets.layers.positional_embedding.LearnablePositionalEmbedding method) (cvnets.models.base_model.BaseAnyNNModel method) (cvnets.models.multi_modal_img_text.clip.CLIP method) (cvnets.modules.ssd_heads.SSDHead method) (cvnets.modules.ssd_heads.SSDInstanceHead method) (cvnets.modules.SSDHead method) (cvnets.modules.SSDInstanceHead method) (cvnets.text_encoders.base_text_encoder.BaseTextEncoder method) reset_parameters_clip_style() (cvnets.text_encoders.transformer.TextTransformer method) reset_params() (cvnets.layers.GroupLinear method) (cvnets.layers.linear_layer.GroupLinear method) (cvnets.layers.linear_layer.LinearLayer method) (cvnets.layers.LinearLayer method) reset_simple_fpn_params() (cvnets.models.classification.vit.VisionTransformer method) reset_unscaled_loss_values() (loss_fn.detection.ssd_multibox_loss.SSDLoss method) reset_weights() (cvnets.modules.feature_pyramid.FeaturePyramidNetwork method) (cvnets.modules.FeaturePyramidNetwork method) Resize (class in data.transforms.image_pil) (class in data.transforms.video) resize_input_if_needed() (cvnets.modules.mobilevit_block.MobileViTBlockv2 method) (cvnets.modules.MobileViTBlockv2 method) ResNet (class in cvnets.models.classification.resnet) RetrievalCMC (class in metrics.retrieval_cmc) retrieve_lr() (optim.scheduler.base_scheduler.BaseLRScheduler static method) Roll (class in data.transforms.audio) round_places (cvnets.layers.AdjustBatchNormMomentum attribute) (cvnets.layers.normalization_layers.AdjustBatchNormMomentum attribute) RPNHead (class in cvnets.models.detection.utils.rcnn_utils) run() (engine.evaluation_engine.Evaluator method) (engine.training_engine.Trainer method) run_loss_landscape() (engine.training_engine.Trainer method)

S

samples_in_dataset() (data.loader.dataloader.CVNetsDataLoader method) save_checkpoint() (in module utils.checkpoint_utils) save_interval_checkpoint() (in module utils.checkpoint_utils) save_video_with_annotations() (data.transforms.video.SaveInputs method) SaveInputs (class in data.transforms.video) ScaleJitter (class in data.transforms.image_pil) scatter() (in module utils.third_party.ddp_functional_utils) scores (cvnets.models.detection.DetectionPredTuple attribute) SegCrossEntropy (class in loss_fn.segmentation.cross_entropy) SegEncoderDecoder (class in cvnets.models.segmentation.enc_dec) select_random_subset() (in module data.datasets.utils.common) select_samples_by_category() (in module data.datasets.utils.common) SeparableConv1d (class in cvnets.layers) (class in cvnets.layers.conv_layer) SeparableConv2d (class in cvnets.layers) (class in cvnets.layers.conv_layer) SeparableConv3d (class in cvnets.layers) (class in cvnets.layers.conv_layer) set_default_norm_layer() (cvnets.models.segmentation.base_seg.BaseSegmentation method) set_epoch() (data.sampler.base_sampler.BaseSampler method) (data.sampler.base_sampler.BaseSamplerDDP method) (data.sampler.chain_sampler.ChainSampler method) set_model_specific_opts_before_model_building() (cvnets.models.segmentation.base_seg.BaseSegmentation class method) (in module cvnets.models.classification.base_image_encoder) (in module cvnets.models.segmentation.base_seg) set_norm_layer_opts() (cvnets.models.detection.mask_rcnn.MaskRCNNDetector method) SetFixedLength (class in data.transforms.audio) setup_size() (in module data.transforms.utils) SGDOptimizer (class in optim.sgd) share_dataset_arguments() (data.datasets.classification.base_image_classification_dataset.BaseImageClassificationDataset method) (data.datasets.dataset_base.BaseDataset method) (data.datasets.detection.coco_base.COCODetection method) (data.datasets.multi_modal_img_text.base_multi_modal_img_text.BaseMultiModalImgText method) shifted_window_attention() (in module cvnets.modules.swin_transformer_block) ShiftedWindowAttention (class in cvnets.modules.swin_transformer_block) ShuffleAudios (class in data.transforms.video)

ShuffleBytes (class in data.transforms.image_bytes) Sigmoid (class in cvnets.layers.activation.sigmoid) SimpleImageProjectionHead (class in cvnets.image_projection_layers.simple_projection_head) SimpleSegHead (class in cvnets.models.segmentation.heads.simple_seg_head) singe_dash_line() (in module utils.logger) SingleHeadAttention (class in cvnets.layers) (class in cvnets.layers.single_head_attention) SingleShotMaskDetector (class in cvnets.models.detection.ssd) SinusoidalPositionalEmbedding (class in cvnets.layers.positional_embedding) SinusoidalPositionalEncoding (class in cvnets.layers.positional_encoding) SoftKLLoss (class in loss_fn.distillation.soft_kl_distillation) Softmax (class in cvnets.layers) (class in cvnets.layers.softmax) SpeechCommandsv2Dataset (class in data.datasets.audio_classification.speech_commands_v2) SqueezeExcitation (class in cvnets.modules) (class in cvnets.modules.squeeze_excitation) ssd_forward() (cvnets.models.detection.ssd.SingleShotMaskDetector method) SSDAnchorGenerator (class in cvnets.anchor_generator.ssd_anchor_generator) SSDCroping (class in data.transforms.image_pil) SSDHead (class in cvnets.modules) (class in cvnets.modules.ssd_heads) SSDInstanceHead (class in cvnets.modules) (class in cvnets.modules.ssd_heads) SSDLoss (class in loss_fn.detection.ssd_multibox_loss) SSDMatcher (class in cvnets.matcher_det.ssd_matcher) StandardizeChannels (class in data.transforms.audio) Statistics (class in metrics.stats) StochasticDepth (class in cvnets.layers) (class in cvnets.layers.stochastic_depth) summarize_coco_results() (metrics.coco_map.COCOEvaluator method) SwinTransformer (class in cvnets.models.classification.swin_transformer) SwinTransformerBlock (class in cvnets.modules) (class in cvnets.modules.swin_transformer_block) Swish (class in cvnets.layers.activation.swish) SyncBatchNorm (class in cvnets.layers.normalization.sync_batch_norm) SyncBatchNormFP32 (class in cvnets.layers.normalization.sync_batch_norm)

T

Tanh (class in cvnets.layers.activation.tanh) tensor_to_python_float() (in module utils.tensor_utils) test_apply_on_values() (in module utils.object_utils_test) test_average_metric_distributed_batchsize() (in module metrics.metric_base_test) test_basic_registration() (in module utils.registry_test) test_flatten_to_dict() (in module utils.object_utils_test) test_functional_registry() (in module utils.registry_test) TextTransformer (class in cvnets.text_encoders.transformer) to_numpy() (in module utils.tensor_utils) TokenMerging (class in cvnets.layers.token_merging) Top1Metric (class in metrics.topk_accuracy) Top5Metric (class in metrics.topk_accuracy) top_k_accuracy() (in module metrics.topk_accuracy) TopKMetric (class in metrics.topk_accuracy) TorchaudioSave (class in data.transforms.audio_bytes) total_video_frames (data.datasets.dataset_base.VideoMetadataDict attribute)

ToTensor (class in data.transforms.image_pil) (class in data.transforms.video) train() (loss_fn.composite_loss.CompositeLoss method) train_epoch() (engine.training_engine.Trainer method) train_resolution (cvnets.models.classification.config.efficientnet.CompoundScalingConfig attribute) Trainer (class in engine.training_engine) training (cvnets.layers.ConvLayer1d attribute) (cvnets.layers.ConvLayer2d attribute) (cvnets.layers.ConvLayer3d attribute) (cvnets.layers.GlobalPool attribute) (cvnets.modules.BasicResNetBlock attribute) (cvnets.modules.BottleneckResNetBlock attribute) TransformerEncoder (class in cvnets.modules) (class in cvnets.modules.transformer) TransposeConvLayer2d (class in cvnets.layers) (class in cvnets.layers.conv_layer) TrivialAugmentWide (class in data.transforms.image_pil)

U

unfold_tokens() (in module cvnets.models.classification.byteformer) unfolding() (cvnets.modules.mobilevit_block.MobileViTBlock method) (cvnets.modules.MobileViTBlock method) unfolding_coreml() (cvnets.modules.mobilevit_block.MobileViTBlockv2 method) (cvnets.modules.MobileViTBlockv2 method) unfolding_pytorch() (cvnets.modules.mobilevit_block.MobileViTBlockv2 method) (cvnets.modules.MobileViTBlockv2 method) uniform_sampling() (data.video_reader.base_av_reader.BaseAVReader static method) UniformSampler (class in cvnets.neural_augmentor.utils.neural_aug_utils) unlabeled_image_data_collate_fn() (in module data.collate_fns.collate_functions) UnrecognizedYamlConfigEntry unset_model_specific_opts_after_model_building() (in module cvnets.models.classification.base_image_encoder) (in module cvnets.models.segmentation.base_seg) unwindow_x() (in module cvnets.modules.windowed_transformer) unwrap_model_fn() (in module utils.common_utils) update() (metrics.coco_map.COCOEvaluator method) (metrics.confusion_mat.ConfusionMatrix method) (metrics.image_text_retrieval.ImageTextRetrievalMetric method) (metrics.metric_base.AverageMetric method) (metrics.metric_base.BaseMetric method) (metrics.metric_base.EpochMetric method) (metrics.stats.Statistics method) update_classifier() (cvnets.models.classification.base_image_encoder.BaseImageEncoder method) (cvnets.models.segmentation.base_seg.BaseSegmentation method) (cvnets.models.segmentation.enc_dec.SegEncoderDecoder method) (cvnets.models.segmentation.heads.base_seg_head.BaseSegHead method) (cvnets.models.segmentation.heads.deeplabv3.DeeplabV3 method) (cvnets.models.segmentation.heads.pspnet.PSPNet method) update_image_classifier() (in module cvnets.models.multi_modal_img_text.clip) update_indices() (data.loader.dataloader.CVNetsDataLoader method) (data.sampler.base_sampler.BaseSampler method) (data.sampler.base_sampler.BaseSamplerDDP method) (data.sampler.chain_sampler.ChainSampler method) update_layer_norm_eps() (cvnets.models.classification.vit.VisionTransformer method) (cvnets.models.detection.mask_rcnn.MaskRCNNDetector method) update_lr() (optim.scheduler.base_scheduler.BaseLRScheduler method) update_parameters() (cvnets.misc.averaging_utils.EMA method) update_scales() (data.sampler.base_sampler.BaseSampler method) (data.sampler.base_sampler.BaseSamplerDDP method) (data.sampler.chain_sampler.ChainSampler method) (data.sampler.multi_scale_sampler.MultiScaleSampler method), [1] (data.sampler.multi_scale_sampler.MultiScaleSamplerDDP method), [1] (data.sampler.variable_batch_sampler.VariableBatchSampler method), [1] (data.sampler.variable_batch_sampler.VariableBatchSamplerDDP method), [1]

UpSample (class in cvnets.layers) (class in cvnets.layers.upsample) utils module utils.checkpoint_utils module utils.color_map module utils.common_utils module utils.ddp_utils module utils.dict_utils module utils.download_utils module utils.download_utils_base module utils.import_utils module utils.logger module utils.math_utils module utils.object_utils module utils.object_utils_test module utils.pytorch_to_coreml module utils.registry module utils.registry_test module utils.resources module utils.tensor_utils module utils.third_party module utils.third_party.ddp_functional_utils module utils.visualization_utils module

V

val_epoch() (engine.training_engine.Trainer method) VariableBatchSampler (class in data.sampler.variable_batch_sampler), [1] VariableBatchSamplerDDP (class in data.sampler.variable_batch_sampler), [1] video_duration (data.datasets.dataset_base.VideoMetadataDict attribute) video_fps (data.datasets.dataset_base.VideoMetadataDict attribute) video_size_from_opts() (in module utils.tensor_utils)

VideoDurationDoesNotMatchAudioDurationError VideoMetadataDict (class in data.datasets.dataset_base) VisionTransformer (class in cvnets.models.classification.vit) visualize_boxes_xyxy() (in module utils.visualization_utils) visualize_context_scores() (cvnets.layers.linear_attention.LinearSelfAttention static method) (cvnets.layers.LinearSelfAttention static method)

W

warning() (in module utils.logger) width_mult (cvnets.models.classification.config.efficientnet.CompoundScalingConfig attribute) window_partition() (in module cvnets.modules.windowed_transformer)

window_partition_reverse() (in module cvnets.modules.windowed_transformer) window_x_and_key_padding_mask() (in module cvnets.modules.windowed_transformer) WindowedTransformerEncoder (class in cvnets.modules) (class in cvnets.modules.windowed_transformer)

X

XRegNetBlock (class in cvnets.modules) (class in cvnets.modules.regnet_modules)