MCPcopy Create free account

hub / github.com/caoql98/DCPL / types & classes

Types & classes54 in github.com/caoql98/DCPL

⨍ Functions 184◇ Types & classes 54
↓ 11 callersClassLayerNorm
Subclass torch's LayerNorm to handle fp16.
clip/model.py:153
↓ 3 callersClassQuickGELU
clip/model.py:162
↓ 3 callersClassTransformer
clip/model.py:334
↓ 2 callersClassBottleneck
clip/model.py:10
↓ 2 callersClassResidualAttentionBlock_IVLP
clip/model.py:191
↓ 1 callersClassAttentionPool2d
clip/model.py:56
↓ 1 callersClassCLIP
clip/model.py:479
↓ 1 callersClassCustomCLIP
trainers/DCPL.py:198
↓ 1 callersClassCustomCLIP
trainers/independentVL.py:154
↓ 1 callersClassCustomCLIP
trainers/vpt.py:92
↓ 1 callersClassCustomCLIP
trainers/coop.py:188
↓ 1 callersClassCustomCLIP
trainers/maple.py:179
↓ 1 callersClassCustomCLIP
trainers/cocoop.py:167
↓ 1 callersClassFixedEmbeddings
trainers/vpt.py:67
↓ 1 callersClassModifiedResNet
A ResNet class that is similar to torchvision's but contains the following changes: - There are now 3 "stem" convolutions as opposed to 1, wi
clip/model.py:93
↓ 1 callersClassMultiModalPromptLearner
trainers/DCPL.py:69
↓ 1 callersClassMultiModalPromptLearner
trainers/maple.py:69
↓ 1 callersClassPromptLearner
trainers/coop.py:63
↓ 1 callersClassPromptLearner
trainers/cocoop.py:65
↓ 1 callersClassResidualAttentionBlock
clip/model.py:167
↓ 1 callersClassResidualAttentionBlock_MaPLe
clip/model.py:259
↓ 1 callersClassSimpleTokenizer
clip/simple_tokenizer.py:62
↓ 1 callersClassTextEncoder
trainers/DCPL.py:43
↓ 1 callersClassTextEncoder
trainers/independentVL.py:42
↓ 1 callersClassTextEncoder
trainers/vpt.py:44
↓ 1 callersClassTextEncoder
trainers/coop.py:40
↓ 1 callersClassTextEncoder
trainers/maple.py:43
↓ 1 callersClassTextEncoder
trainers/cocoop.py:42
↓ 1 callersClassVLPromptLearner
trainers/independentVL.py:65
↓ 1 callersClassVisionTransformer
clip/model.py:362
↓ 1 callersClassVisionTransformer_MaPLe
clip/model.py:425
ClassCaltech101
datasets/caltech101.py:20
ClassCoCoOp
trainers/cocoop.py:201
ClassCoOp
Context Optimization (CoOp). Learning to Prompt for Vision-Language Models https://arxiv.org/abs/2109.01134
trainers/coop.py:215
ClassDescribableTextures
datasets/dtd.py:12
ClassEuroSAT
datasets/eurosat.py:25
ClassFGVCAircraft
datasets/fgvc_aircraft.py:11
ClassFood101
datasets/food101.py:12
ClassIVLP
trainers/independentVL.py:183
ClassImageNet
datasets/imagenet.py:12
ClassImageNetA
ImageNet-A(dversarial). This dataset is used for testing only.
datasets/imagenet_a.py:12
ClassImageNetR
ImageNet-R(endition). This dataset is used for testing only.
datasets/imagenet_r.py:12
ClassImageNetSketch
ImageNet-Sketch. This dataset is used for testing only.
datasets/imagenet_sketch.py:10
ClassImageNetV2
ImageNetV2. This dataset is used for testing only.
datasets/imagenetv2.py:10
ClassMaPLe
trainers/DCPL.py:273
ClassMaPLe
trainers/maple.py:212
ClassOxfordFlowers
datasets/oxford_flowers.py:14
ClassOxfordPets
datasets/oxford_pets.py:12
ClassSUN397
datasets/sun397.py:11
ClassStanfordCars
datasets/stanford_cars.py:12
ClassUCF101
datasets/ucf101.py:12
ClassVPT
trainers/vpt.py:118
ClassZeroshotCLIP
trainers/zsclip.py:33
ClassZeroshotCLIP2
Prompt ensembling.
trainers/zsclip.py:64