cvnets package

Subpackages

• cvnets.anchor_generator package
  • Submodules
  • cvnets.anchor_generator.base_anchor_generator module
    • BaseAnchorGenerator
      • BaseAnchorGenerator.__init__()
      • BaseAnchorGenerator.add_arguments()
      • BaseAnchorGenerator.num_anchors_per_os()
      • BaseAnchorGenerator.forward()
  • cvnets.anchor_generator.ssd_anchor_generator module
    • SSDAnchorGenerator
      • SSDAnchorGenerator.__init__()
      • SSDAnchorGenerator.add_arguments()
      • SSDAnchorGenerator.num_anchors_per_os()
  • Module contents
    • arguments_anchor_gen()
    • build_anchor_generator()
• cvnets.image_projection_layers package
  • Submodules
  • cvnets.image_projection_layers.attention_pool_2d module
    • AttentionPool2dHead
      • AttentionPool2dHead.__init__()
      • AttentionPool2dHead.add_arguments()
      • AttentionPool2dHead.reset_parameters()
      • AttentionPool2dHead.forward()
  • cvnets.image_projection_layers.base_image_projection module
    • BaseImageProjectionHead
      • BaseImageProjectionHead.__init__()
      • BaseImageProjectionHead.add_arguments()
      • BaseImageProjectionHead.reset_parameters()
      • BaseImageProjectionHead.get_trainable_parameters()
      • BaseImageProjectionHead.forward()
    • get_in_feature_dimension()
  • cvnets.image_projection_layers.global_pool_2d module
    • GlobalPool2D
      • GlobalPool2D.__init__()
      • GlobalPool2D.add_arguments()
      • GlobalPool2D.reset_parameters()
      • GlobalPool2D.forward()
  • cvnets.image_projection_layers.simple_projection_head module
    • SimpleImageProjectionHead
      • SimpleImageProjectionHead.__init__()
      • SimpleImageProjectionHead.add_arguments()
      • SimpleImageProjectionHead.reset_parameters()
      • SimpleImageProjectionHead.forward()
  • Module contents
    • arguments_image_projection_head()
    • build_image_projection_head()
• cvnets.layers package
  • Subpackages
    • cvnets.layers.activation package
      • Submodules
      • 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
      • Module contents
    • cvnets.layers.normalization package
      • Submodules
      • 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
      • Module contents
  • Submodules
  • cvnets.layers.adaptive_pool module
    • AdaptiveAvgPool2d
      • AdaptiveAvgPool2d.__init__()
  • cvnets.layers.base_layer module
    • BaseLayer
      • BaseLayer.__init__()
      • BaseLayer.add_arguments()
      • BaseLayer.get_trainable_parameters()
      • BaseLayer.forward()
  • cvnets.layers.conv_layer module
    • Conv2d
      • Conv2d.__init__()
    • ConvLayer1d
      • ConvLayer1d.ndim
      • ConvLayer1d.module_cls
    • ConvLayer2d
      • ConvLayer2d.ndim
      • ConvLayer2d.module_cls
    • ConvLayer3d
      • ConvLayer3d.ndim
      • ConvLayer3d.module_cls
    • TransposeConvLayer2d
      • TransposeConvLayer2d.__init__()
      • TransposeConvLayer2d.forward()
    • NormActLayer
      • NormActLayer.__init__()
      • NormActLayer.forward()
    • SeparableConv1d
      • SeparableConv1d.conv_layer_cls
    • SeparableConv2d
      • SeparableConv2d.conv_layer_cls
    • SeparableConv3d
      • SeparableConv3d.conv_layer_cls
  • cvnets.layers.dropout module
    • Dropout
      • Dropout.__init__()
    • Dropout2d
      • Dropout2d.__init__()
  • cvnets.layers.embedding module
    • Embedding
      • Embedding.__init__()
      • Embedding.reset_parameters()
  • cvnets.layers.flatten module
    • Flatten
      • Flatten.__init__()
  • cvnets.layers.global_pool module
    • GlobalPool
      • GlobalPool.pool_types
      • GlobalPool.__init__()
      • GlobalPool.add_arguments()
      • GlobalPool.forward()
  • cvnets.layers.identity module
    • Identity
      • Identity.__init__()
      • Identity.forward()
  • cvnets.layers.linear_attention module
    • LinearSelfAttention
      • LinearSelfAttention.__init__()
      • LinearSelfAttention.visualize_context_scores()
      • LinearSelfAttention.forward()
  • cvnets.layers.linear_layer module
    • LinearLayer
      • LinearLayer.__init__()
      • LinearLayer.add_arguments()
      • LinearLayer.reset_params()
      • LinearLayer.forward()
    • GroupLinear
      • GroupLinear.__init__()
      • GroupLinear.add_arguments()
      • GroupLinear.reset_params()
      • GroupLinear.forward()
  • cvnets.layers.multi_head_attention module
    • MultiHeadAttention
      • MultiHeadAttention.__init__()
      • MultiHeadAttention.forward_tracing()
      • MultiHeadAttention.forward_default()
      • MultiHeadAttention.forward_pytorch()
      • MultiHeadAttention.forward()
  • cvnets.layers.normalization_layers module
    • AdjustBatchNormMomentum
      • AdjustBatchNormMomentum.round_places
      • AdjustBatchNormMomentum.__init__()
      • AdjustBatchNormMomentum.adjust_momentum()
  • cvnets.layers.pixel_shuffle module
    • PixelShuffle
      • PixelShuffle.__init__()
  • cvnets.layers.pooling module
    • MaxPool2d
      • MaxPool2d.__init__()
    • AvgPool2d
      • AvgPool2d.__init__()
  • cvnets.layers.positional_embedding module
    • PositionalEmbedding
      • PositionalEmbedding.__init__()
      • PositionalEmbedding.forward()
    • LearnablePositionalEmbedding
      • LearnablePositionalEmbedding.__init__()
      • LearnablePositionalEmbedding.reset_parameters()
      • LearnablePositionalEmbedding.forward()
    • SinusoidalPositionalEmbedding
      • SinusoidalPositionalEmbedding.__init__()
      • SinusoidalPositionalEmbedding.get_weights()
      • SinusoidalPositionalEmbedding.forward()
  • cvnets.layers.positional_encoding module
    • SinusoidalPositionalEncoding
      • SinusoidalPositionalEncoding.__init__()
      • SinusoidalPositionalEncoding.forward_patch_last()
      • SinusoidalPositionalEncoding.forward_others()
      • SinusoidalPositionalEncoding.forward()
    • LearnablePositionEncoding
      • LearnablePositionEncoding.__init__()
      • LearnablePositionEncoding.forward()
  • cvnets.layers.random_layers module
    • RandomApply
      • RandomApply.__init__()
      • RandomApply.forward()
  • cvnets.layers.single_head_attention module
    • SingleHeadAttention
      • SingleHeadAttention.__init__()
      • SingleHeadAttention.forward()
  • cvnets.layers.softmax module
    • Softmax
      • Softmax.__init__()
  • cvnets.layers.stochastic_depth module
    • StochasticDepth
      • StochasticDepth.__init__()
  • cvnets.layers.token_merging module
    • TokenMerging
      • TokenMerging.__init__()
      • TokenMerging.forward()
      • TokenMerging.extra_repr()
    • pad_x_and_mask()
  • cvnets.layers.upsample module
    • UpSample
      • UpSample.__init__()
  • Module contents
    • ConvLayer1d
      • ConvLayer1d.ndim
      • ConvLayer1d.module_cls
      • ConvLayer1d.training
    • ConvLayer2d
      • ConvLayer2d.ndim
      • ConvLayer2d.module_cls
      • ConvLayer2d.training
    • ConvLayer3d
      • ConvLayer3d.ndim
      • ConvLayer3d.module_cls
      • ConvLayer3d.training
    • SeparableConv1d
      • SeparableConv1d.conv_layer_cls
    • SeparableConv2d
      • SeparableConv2d.conv_layer_cls
    • SeparableConv3d
      • SeparableConv3d.conv_layer_cls
    • NormActLayer
      • NormActLayer.__init__()
      • NormActLayer.forward()
    • TransposeConvLayer2d
      • TransposeConvLayer2d.__init__()
      • TransposeConvLayer2d.forward()
    • LinearLayer
      • LinearLayer.__init__()
      • LinearLayer.add_arguments()
      • LinearLayer.reset_params()
      • LinearLayer.forward()
    • GroupLinear
      • GroupLinear.__init__()
      • GroupLinear.add_arguments()
      • GroupLinear.reset_params()
      • GroupLinear.forward()
    • GlobalPool
      • GlobalPool.pool_types
      • GlobalPool.__init__()
      • GlobalPool.add_arguments()
      • GlobalPool.forward()
      • GlobalPool.training
    • Identity
      • Identity.__init__()
      • Identity.forward()
    • PixelShuffle
      • PixelShuffle.__init__()
    • UpSample
      • UpSample.__init__()
    • MaxPool2d
      • MaxPool2d.__init__()
    • AvgPool2d
      • AvgPool2d.__init__()
    • Dropout
      • Dropout.__init__()
    • Dropout2d
      • Dropout2d.__init__()
    • AdjustBatchNormMomentum
      • AdjustBatchNormMomentum.round_places
      • AdjustBatchNormMomentum.__init__()
      • AdjustBatchNormMomentum.adjust_momentum()
    • Flatten
      • Flatten.__init__()
    • MultiHeadAttention
      • MultiHeadAttention.__init__()
      • MultiHeadAttention.forward_tracing()
      • MultiHeadAttention.forward_default()
      • MultiHeadAttention.forward_pytorch()
      • MultiHeadAttention.forward()
    • SingleHeadAttention
      • SingleHeadAttention.__init__()
      • SingleHeadAttention.forward()
    • Softmax
      • Softmax.__init__()
    • LinearSelfAttention
      • LinearSelfAttention.__init__()
      • LinearSelfAttention.visualize_context_scores()
      • LinearSelfAttention.forward()
    • Embedding
      • Embedding.__init__()
      • Embedding.reset_parameters()
    • PositionalEmbedding
      • PositionalEmbedding.__init__()
      • PositionalEmbedding.forward()
    • StochasticDepth
      • StochasticDepth.__init__()
    • get_normalization_layer()
• cvnets.matcher_det package
  • Submodules
  • cvnets.matcher_det.base_matcher module
    • BaseMatcher
      • BaseMatcher.__init__()
      • BaseMatcher.add_arguments()
  • cvnets.matcher_det.ssd_matcher module
    • SSDMatcher
      • SSDMatcher.__init__()
      • SSDMatcher.add_arguments()
      • SSDMatcher.convert_to_boxes()
    • check_variable()
  • Module contents
    • arguments_box_matcher()
    • build_matcher()
• cvnets.misc package
  • Subpackages
    • cvnets.misc.third_party package
      • Submodules
      • cvnets.misc.third_party.ssd_utils module
      • Module contents
  • Submodules
  • cvnets.misc.averaging_utils module
    • EMA
      • EMA.__init__()
      • EMA.update_parameters()
    • arguments_ema()
  • cvnets.misc.box_utils module
    • convert_locations_to_boxes()
    • convert_boxes_to_locations()
    • center_form_to_corner_form()
    • corner_form_to_center_form()
  • cvnets.misc.common module
    • clean_strip()
    • load_pretrained_model()
    • parameter_list()
    • freeze_module()
    • freeze_modules_based_on_opts()
    • get_tensor_sizes()
  • cvnets.misc.init_utils module
    • initialize_conv_layer()
    • initialize_fc_layer()
    • initialize_norm_layers()
    • initialize_weights()
  • Module contents
• cvnets.models package
  • Subpackages
    • cvnets.models.audio_classification package
      • Submodules
      • cvnets.models.audio_classification.audio_byteformer module
      • cvnets.models.audio_classification.base_audio_classification module
      • Module contents
    • cvnets.models.classification package
      • Subpackages
      • Submodules
      • cvnets.models.classification.base_image_encoder module
      • cvnets.models.classification.byteformer 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
      • Module contents
    • cvnets.models.detection package
      • Subpackages
      • Submodules
      • cvnets.models.detection.base_detection module
      • cvnets.models.detection.mask_rcnn module
      • cvnets.models.detection.ssd module
      • Module contents
    • cvnets.models.multi_modal_img_text package
      • Submodules
      • cvnets.models.multi_modal_img_text.base_multi_modal_img_text module
      • cvnets.models.multi_modal_img_text.clip module
      • Module contents
    • cvnets.models.segmentation package
      • Subpackages
      • Submodules
      • cvnets.models.segmentation.base_seg module
      • cvnets.models.segmentation.enc_dec module
      • Module contents
  • Submodules
  • cvnets.models.base_model module
    • BaseAnyNNModel
      • BaseAnyNNModel.__init__()
      • BaseAnyNNModel.add_arguments()
      • BaseAnyNNModel.reset_parameters()
      • BaseAnyNNModel.forward()
      • BaseAnyNNModel.get_trainable_parameters()
      • BaseAnyNNModel.dummy_input_and_label()
      • BaseAnyNNModel.get_exportable_model()
      • BaseAnyNNModel.freeze_norm_layers()
      • BaseAnyNNModel.build_model()
      • BaseAnyNNModel.info()
  • Module contents
    • get_model()
    • arguments_model()
• cvnets.modules package
  • Submodules
  • cvnets.modules.aspp_block module
    • ASPP
      • ASPP.__init__()
      • ASPP.forward()
    • ASPPConv2d
      • ASPPConv2d.__init__()
      • ASPPConv2d.adjust_atrous_rate()
    • ASPPSeparableConv2d
      • ASPPSeparableConv2d.__init__()
      • ASPPSeparableConv2d.adjust_atrous_rate()
    • ASPPPooling
      • ASPPPooling.__init__()
      • ASPPPooling.forward()
  • cvnets.modules.base_module module
    • BaseModule
      • BaseModule.__init__()
      • BaseModule.forward()
  • cvnets.modules.efficientnet module
    • EfficientNetBlock
      • EfficientNetBlock.__init__()
      • EfficientNetBlock.forward()
  • cvnets.modules.fastvit module
    • convolutional_stem()
    • PatchEmbed
      • PatchEmbed.__init__()
      • PatchEmbed.forward()
    • RepMixer
      • RepMixer.__init__()
      • RepMixer.forward()
      • RepMixer.reparameterize()
    • ConvFFN
      • ConvFFN.__init__()
      • ConvFFN.forward()
    • RepMixerBlock
      • RepMixerBlock.__init__()
      • RepMixerBlock.forward()
    • AttentionBlock
      • AttentionBlock.__init__()
      • AttentionBlock.forward()
    • RepCPE
      • RepCPE.__init__()
      • RepCPE.forward()
      • RepCPE.reparameterize()
  • cvnets.modules.feature_pyramid module
    • FeaturePyramidNetwork
      • FeaturePyramidNetwork.__init__()
      • FeaturePyramidNetwork.reset_weights()
      • FeaturePyramidNetwork.forward()
  • cvnets.modules.mobilenetv2 module
    • InvertedResidualSE
      • InvertedResidualSE.__init__()
      • InvertedResidualSE.forward()
    • InvertedResidual
      • InvertedResidual.__init__()
      • InvertedResidual.forward()
  • cvnets.modules.mobileone_block module
    • MobileOneBlock
      • MobileOneBlock.__init__()
      • MobileOneBlock.forward()
      • MobileOneBlock.reparameterize()
    • RepLKBlock
      • RepLKBlock.__init__()
      • RepLKBlock.forward()
      • RepLKBlock.reparameterize()
  • cvnets.modules.mobilevit_block module
    • MobileViTBlock
      • MobileViTBlock.__init__()
      • MobileViTBlock.unfolding()
      • MobileViTBlock.folding()
      • MobileViTBlock.forward_spatial()
      • MobileViTBlock.forward_temporal()
      • MobileViTBlock.forward()
    • MobileViTBlockv2
      • MobileViTBlockv2.__init__()
      • MobileViTBlockv2.unfolding_pytorch()
      • MobileViTBlockv2.folding_pytorch()
      • MobileViTBlockv2.unfolding_coreml()
      • MobileViTBlockv2.folding_coreml()
      • MobileViTBlockv2.resize_input_if_needed()
      • MobileViTBlockv2.forward_spatial()
      • MobileViTBlockv2.forward_temporal()
      • MobileViTBlockv2.forward()
  • cvnets.modules.pspnet_module module
    • PSP
      • PSP.__init__()
      • PSP.forward()
  • cvnets.modules.regnet_modules module
    • XRegNetBlock
      • XRegNetBlock.__init__()
      • XRegNetBlock.forward()
    • AnyRegNetStage
      • AnyRegNetStage.__init__()
      • AnyRegNetStage.forward()
  • cvnets.modules.resnet_modules module
    • BasicResNetBlock
      • BasicResNetBlock.expansion
      • BasicResNetBlock.__init__()
      • BasicResNetBlock.forward()
    • BottleneckResNetBlock
      • BottleneckResNetBlock.expansion
      • BottleneckResNetBlock.__init__()
      • BottleneckResNetBlock.forward()
  • cvnets.modules.squeeze_excitation module
    • SqueezeExcitation
      • SqueezeExcitation.__init__()
      • SqueezeExcitation.forward()
  • cvnets.modules.ssd_heads module
    • SSDHead
      • SSDHead.__init__()
      • SSDHead.reset_parameters()
      • SSDHead.forward()
    • SSDInstanceHead
      • SSDInstanceHead.__init__()
      • SSDInstanceHead.reset_parameters()
      • SSDInstanceHead.forward()
  • cvnets.modules.swin_transformer_block module
    • Permute
      • Permute.__init__()
      • Permute.forward()
    • PatchMerging
      • PatchMerging.__init__()
      • PatchMerging.forward()
    • shifted_window_attention()
    • ShiftedWindowAttention
      • ShiftedWindowAttention.__init__()
      • ShiftedWindowAttention.forward()
    • SwinTransformerBlock
      • SwinTransformerBlock.__init__()
      • SwinTransformerBlock.forward()
  • cvnets.modules.transformer module
    • TransformerEncoder
      • TransformerEncoder.__init__()
      • TransformerEncoder.forward()
    • LinearAttnFFN
      • LinearAttnFFN.__init__()
      • LinearAttnFFN.forward()
  • cvnets.modules.windowed_transformer module
    • window_partition()
    • window_partition_reverse()
    • get_windows_shift_mask()
    • window_x_and_key_padding_mask()
    • unwindow_x()
    • WindowedTransformerEncoder
      • WindowedTransformerEncoder.__init__()
      • WindowedTransformerEncoder.forward()
  • Module contents
    • InvertedResidual
      • InvertedResidual.__init__()
      • InvertedResidual.forward()
    • InvertedResidualSE
      • InvertedResidualSE.__init__()
      • InvertedResidualSE.forward()
    • BasicResNetBlock
      • BasicResNetBlock.expansion
      • BasicResNetBlock.__init__()
      • BasicResNetBlock.forward()
      • BasicResNetBlock.training
    • BottleneckResNetBlock
      • BottleneckResNetBlock.expansion
      • BottleneckResNetBlock.__init__()
      • BottleneckResNetBlock.forward()
      • BottleneckResNetBlock.training
    • ASPP
      • ASPP.__init__()
      • ASPP.forward()
    • TransformerEncoder
      • TransformerEncoder.__init__()
      • TransformerEncoder.forward()
    • WindowedTransformerEncoder
      • WindowedTransformerEncoder.__init__()
      • WindowedTransformerEncoder.forward()
    • SqueezeExcitation
      • SqueezeExcitation.__init__()
      • SqueezeExcitation.forward()
    • PSP
      • PSP.__init__()
      • PSP.forward()
    • MobileViTBlock
      • MobileViTBlock.__init__()
      • MobileViTBlock.unfolding()
      • MobileViTBlock.folding()
      • MobileViTBlock.forward_spatial()
      • MobileViTBlock.forward_temporal()
      • MobileViTBlock.forward()
    • MobileViTBlockv2
      • MobileViTBlockv2.__init__()
      • MobileViTBlockv2.unfolding_pytorch()
      • MobileViTBlockv2.folding_pytorch()
      • MobileViTBlockv2.unfolding_coreml()
      • MobileViTBlockv2.folding_coreml()
      • MobileViTBlockv2.resize_input_if_needed()
      • MobileViTBlockv2.forward_spatial()
      • MobileViTBlockv2.forward_temporal()
      • MobileViTBlockv2.forward()
    • MobileOneBlock
      • MobileOneBlock.__init__()
      • MobileOneBlock.forward()
      • MobileOneBlock.reparameterize()
    • RepLKBlock
      • RepLKBlock.__init__()
      • RepLKBlock.forward()
      • RepLKBlock.reparameterize()
    • FeaturePyramidNetwork
      • FeaturePyramidNetwork.__init__()
      • FeaturePyramidNetwork.reset_weights()
      • FeaturePyramidNetwork.forward()
    • SSDHead
      • SSDHead.__init__()
      • SSDHead.reset_parameters()
      • SSDHead.forward()
    • SSDInstanceHead
      • SSDInstanceHead.__init__()
      • SSDInstanceHead.reset_parameters()
      • SSDInstanceHead.forward()
    • EfficientNetBlock
      • EfficientNetBlock.__init__()
      • EfficientNetBlock.forward()
    • SwinTransformerBlock
      • SwinTransformerBlock.__init__()
      • SwinTransformerBlock.forward()
    • PatchMerging
      • PatchMerging.__init__()
      • PatchMerging.forward()
    • Permute
      • Permute.__init__()
      • Permute.forward()
    • XRegNetBlock
      • XRegNetBlock.__init__()
      • XRegNetBlock.forward()
    • AnyRegNetStage
      • AnyRegNetStage.__init__()
      • AnyRegNetStage.forward()
• cvnets.neural_augmentor package
  • Subpackages
    • cvnets.neural_augmentor.utils package
      • Submodules
      • cvnets.neural_augmentor.utils.neural_aug_utils module
      • Module contents
  • Submodules
  • cvnets.neural_augmentor.neural_aug module
    • BaseNeuralAugmentor
      • BaseNeuralAugmentor.__init__()
      • BaseNeuralAugmentor.get_trainable_parameters()
      • BaseNeuralAugmentor.add_arguments()
      • BaseNeuralAugmentor.forward()
    • BasicNeuralAugmentor
      • BasicNeuralAugmentor.__init__()
    • DistributionNeuralAugmentor
      • DistributionNeuralAugmentor.__init__()
    • build_neural_augmentor()
  • Module contents
    • arguments_neural_augmentor()
• cvnets.text_encoders package
  • Submodules
  • cvnets.text_encoders.base_text_encoder module
    • BaseTextEncoder
      • BaseTextEncoder.__init__()
      • BaseTextEncoder.add_arguments()
      • BaseTextEncoder.reset_parameters()
      • BaseTextEncoder.get_trainable_parameters()
      • BaseTextEncoder.freeze_norm_layers()
      • BaseTextEncoder.forward()
      • BaseTextEncoder.dummy_input_and_label()
  • cvnets.text_encoders.transformer module
    • TextTransformer
      • TextTransformer.__init__()
      • TextTransformer.reset_parameters_clip_style()
      • TextTransformer.add_arguments()
      • TextTransformer.forward_embedding()
      • TextTransformer.build_attention_mask()
      • TextTransformer.encode_text()
      • TextTransformer.forward_zero_shot()
      • TextTransformer.forward()
  • Module contents
    • arguments_text_encoder()
    • build_text_encoder()

Module contents

cvnets.modeling_arguments(parser: ArgumentParser) → ArgumentParser