Types & classes — github.com/OmkarThawakar/composed-video-retrieval

CodeHub MCPcopy Create free account

hub / github.com/OmkarThawakar/composed-video-retrieval / types & classes

Types & classes52 in github.com/OmkarThawakar/composed-video-retrieval

⨍ Functions 232◇ Types & classes 52

↓ 7 callersClasstransform_test

src/data/transforms.py:47

↓ 6 callersClassBertModel

The model can behave as an encoder (with only self-attention) as well as a decoder, in which case a layer of cross-attention is added between

src/model/med.py:636

↓ 4 callersClasstransform_train

src/data/transforms.py:11

↓ 3 callersClassCIRRDataset

src/data/cirr.py:118

↓ 3 callersClassFashionIQDataset

src/data/fashioniq.py:118

↓ 3 callersClassWebVidCoVRDataset

src/data/webvid_covr.py:156

↓ 2 callersClassBertAttention

src/model/med.py:286

↓ 2 callersClassFrameLoader

src/data/utils.py:136

↓ 2 callersClassRandomAugment

src/data/randaugment.py:320

↓ 2 callersClassVideoDataset

src/data/embs.py:63

↓ 2 callersClassVisionTransformer

Vision Transformer A PyTorch impl of : `An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale` - https://arxiv.org/a

src/model/vit.py:156

↓ 2 callersClassWebVidCoVRDatasetRuleBased

src/data/webvid_covr_rulebased.py:100

↓ 1 callersClassAttention

src/model/vit.py:49

↓ 1 callersClassBLIPEmbs

src/model/blip_embs.py:8

↓ 1 callersClassBLIP_Base

src/model/blip.py:25

↓ 1 callersClassBLIP_Decoder

src/model/blip.py:91

↓ 1 callersClassBertEmbeddings

Construct the embeddings from word and position embeddings.

src/model/med.py:47

↓ 1 callersClassBertEncoder

src/model/med.py:448

↓ 1 callersClassBertIntermediate

src/model/med.py:342

↓ 1 callersClassBertLMHeadModel

src/model/med.py:921

↓ 1 callersClassBertLMPredictionHead

src/model/med.py:583

↓ 1 callersClassBertLayer

src/model/med.py:371

↓ 1 callersClassBertOnlyMLMHead

src/model/med.py:603

↓ 1 callersClassBertOutput

src/model/med.py:357

↓ 1 callersClassBertPooler

src/model/med.py:551

↓ 1 callersClassBertPredictionHeadTransform

src/model/med.py:566

↓ 1 callersClassBertSelfAttention

src/model/med.py:106

↓ 1 callersClassBertSelfOutput

src/model/med.py:272

↓ 1 callersClassBlock

src/model/vit.py:110

↓ 1 callersClassCrossEntropyLoss

Hard Negative NCE loss for contrastive learning.

src/model/loss.py:6

↓ 1 callersClassImageDataset

src/data/embs.py:26

↓ 1 callersClassMlp

MLP as used in Vision Transformer, MLP-Mixer and related networks

src/model/vit.py:21

src/model/blip_cir.py:14

ClassBLIPCirTextOnly

src/model/blip_cir_text.py:13

ClassBLIPCirVisualOnly

src/model/blip_cir_visual.py:13

ClassBertPreTrainedModel

An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained models.

src/model/med.py:613

ClassCIRRDataModule

src/data/cirr.py:15

ClassCIRRTestDataModule

src/data/cirr.py:78

ClassCosineSchedule

src/tools/scheduler.py:4

ClassFashionIQDataModule

src/data/fashioniq.py:15

ClassFashionIQTestDataModule

src/data/fashioniq.py:76

ClassHardNegativeNCE

Hard-Negative NCE loss for contrastive learning. https://arxiv.org/pdf/2301.02280.pdf

src/model/loss.py:27

ClassStepSchedule

src/tools/scheduler.py:20

src/test/cirr.py:14

ClassTestFashionIQ

src/test/fashioniq.py:16

ClassTestWebVidCoVR

src/test/webvid_covr.py:13

ClassTestWebVidCoVRTextOnly

src/test/webvid_covr_exp.py:13

ClassTestWebVidCoVRVisualOnly

src/test/webvid_covr_exp.py:107

ClassTextDataset

src/data/embs.py:126

ClassWebVidCoVRDataModule

src/data/webvid_covr.py:18

ClassWebVidCoVRDataModuleRuleBased

src/data/webvid_covr_rulebased.py:19

ClassWebVidCoVRTestDataModule

src/data/webvid_covr.py:102