Update pytorch_model.bin

pytorch_model.bin

@@ -1,4 +1,55 @@
-from transformers import ViTForImageClassification
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+# Partly revised by YZ @UCL&Moorfields
+# --------------------------------------------------------
+
+from functools import partial
+
+import torch
+import torch.nn as nn
+
+import timm.models.vision_transformer
+
+
+class VisionTransformer(timm.models.vision_transformer.VisionTransformer):
+    """ Vision Transformer with support for global average pooling
+    """
+    def __init__(self, global_pool=False, **kwargs):
+        super(VisionTransformer, self).__init__(**kwargs)
+
+        self.global_pool = global_pool
+        if self.global_pool:
+            norm_layer = kwargs['norm_layer']
+            embed_dim = kwargs['embed_dim']
+            self.fc_norm = norm_layer(embed_dim)
+
+            del self.norm  # remove the original norm
+
+    def forward_features(self, x):
+        B = x.shape[0]
+        x = self.patch_embed(x)
+
+        cls_tokens = self.cls_token.expand(B, -1, -1)  # stole cls_tokens impl from Phil Wang, thanks
+        x = torch.cat((cls_tokens, x), dim=1)
+        x = x + self.pos_embed
+        x = self.pos_drop(x)
+
+        for blk in self.blocks:
+            x = blk(x)
+
+        if self.global_pool:
+            x = x[:, 1:, :].mean(dim=1)  # global pool without cls token
+            outcome = self.fc_norm(x)
+        else:
+            x = self.norm(x)
+            outcome = x[:, 0]
+
+        return outcome
+
+
+def vit_large_patch16(**kwargs):
+    model = VisionTransformer(
+        patch_size=16, embed_dim=1024, depth=24, num_heads=16, mlp_ratio=4, qkv_bias=True,
+        norm_layer=partial(nn.LayerNorm, eps=1e-6), **kwargs)
+    return model
 
-# Assuming you're loading the model using the ViTForImageClassification class
-model = ViTForImageClassification.from_pretrained('/home/user/.cache/huggingface/hub/models--rameye--1/snapshots/c2c5c38a641e6c048f33c2db25afa765727a04ed', from_tf=True)