update vit

ppcls/arch/backbone/__init__.py

@@ -48,7 +48,7 @@ from ppcls.arch.backbone.model_zoo.resnext101_wsl import ResNeXt101_32x8d_wsl, R
 from ppcls.arch.backbone.model_zoo.squeezenet import SqueezeNet1_0, SqueezeNet1_1
 from ppcls.arch.backbone.model_zoo.darknet import DarkNet53
 from ppcls.arch.backbone.model_zoo.regnet import RegNetX_200MF, RegNetX_4GF, RegNetX_32GF, RegNetY_200MF, RegNetY_4GF, RegNetY_32GF
-from ppcls.arch.backbone.model_zoo.vision_transformer import ViT_small_patch16_224, ViT_base_patch16_224, ViT_base_patch16_384, ViT_base_patch32_384, ViT_large_patch16_224, ViT_large_patch16_384, ViT_large_patch32_384, ViT_huge_patch16_224, ViT_huge_patch32_384
+from ppcls.arch.backbone.model_zoo.vision_transformer import ViT_small_patch16_224, ViT_base_patch16_224, ViT_base_patch16_384, ViT_base_patch32_384, ViT_large_patch16_224, ViT_large_patch16_384, ViT_large_patch32_384
 from ppcls.arch.backbone.model_zoo.distilled_vision_transformer import DeiT_tiny_patch16_224, DeiT_small_patch16_224, DeiT_base_patch16_224, DeiT_tiny_distilled_patch16_224, DeiT_small_distilled_patch16_224, DeiT_base_distilled_patch16_224, DeiT_base_patch16_384, DeiT_base_distilled_patch16_384
 from ppcls.arch.backbone.model_zoo.swin_transformer import SwinTransformer_tiny_patch4_window7_224, SwinTransformer_small_patch4_window7_224, SwinTransformer_base_patch4_window7_224, SwinTransformer_base_patch4_window12_384, SwinTransformer_large_patch4_window7_224, SwinTransformer_large_patch4_window12_384
 from ppcls.arch.backbone.model_zoo.mixnet import MixNet_S, MixNet_M, MixNet_L

ppcls/arch/backbone/model_zoo/vision_transformer.py

@@ -38,10 +38,6 @@ MODEL_URLS = {
     "https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ViT_large_patch16_384_pretrained.pdparams",
     "ViT_large_patch32_384":
     "https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ViT_large_patch32_384_pretrained.pdparams",
-    "ViT_huge_patch16_224":
-    "https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ViT_huge_patch16_224_pretrained.pdparams",
-    "ViT_huge_patch32_384":
-    "https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ViT_huge_patch32_384_pretrained.pdparams"
 }
 
 __all__ = list(MODEL_URLS.keys())
@@ -460,36 +456,3 @@ def ViT_large_patch32_384(pretrained=False, use_ssld=False, **kwargs):
         MODEL_URLS["ViT_large_patch32_384"],
         use_ssld=use_ssld)
     return model
-
-
-def ViT_huge_patch16_224(pretrained=False, use_ssld=False, **kwargs):
-    model = VisionTransformer(
-        patch_size=16,
-        embed_dim=1280,
-        depth=32,
-        num_heads=16,
-        mlp_ratio=4,
-        **kwargs)
-    _load_pretrained(
-        pretrained,
-        model,
-        MODEL_URLS["ViT_huge_patch16_224"],
-        use_ssld=use_ssld)
-    return model
-
-
-def ViT_huge_patch32_384(pretrained=False, use_ssld=False, **kwargs):
-    model = VisionTransformer(
-        img_size=384,
-        patch_size=32,
-        embed_dim=1280,
-        depth=32,
-        num_heads=16,
-        mlp_ratio=4,
-        **kwargs)
-    _load_pretrained(
-        pretrained,
-        model,
-        MODEL_URLS["ViT_huge_patch32_384"],
-        use_ssld=use_ssld)
-    return model