Python Module Index

c | d | e | l | m | o | u


	c
	`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`

	d
	`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`
	`data.sampler.chain_sampler`
	`data.sampler.multi_scale_sampler`
	`data.sampler.utils`
	`data.sampler.variable_batch_sampler`
	`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`

	e
	`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`

	l
	`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`

	m
	`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`

	o
	`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`

	u
	`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`