readme

README.md

@@ -13,9 +13,54 @@ A simple implementation of a CLIP that splits up an image into quandrants and th
 
 
 # Install
+`pip install mega-vit`
 
 # Usage
-
+- Simple usage,
+```python
+import torch
+from mega_vit.main import MegaVit
+
+v = MegaVit(
+    image_size = 256,
+    patch_size = 32,
+    num_classes = 1000,
+    dim = 1024,
+    depth = 6,
+    heads = 16,
+    mlp_dim = 2048,
+    dropout = 0.1,
+    emb_dropout = 0.1
+)
+
+img = torch.randn(1, 3, 256, 256)
+
+preds = v(img) # (1, 1000)
+print(preds)
+```
+
+- Hyperparams as stated in paper:
+```python
+import torch
+from mega_vit.main import MegaVit
+
+v = ViT(
+    image_size = 224,
+    patch_size = 14,
+    num_classes = 1000,
+    dim = 6144,
+    depth = 48,
+    heads = 48,
+    mlp_dim = 2048,
+    dropout = 0.1,
+    emb_dropout = 0.1
+)
+
+img = torch.randn(1, 3, 224, 224)
+
+preds = v(img) # (1, 1000)
+print(preds)
+```
 # Architecture
 
 # Dataset Strategy

example.py

@@ -0,0 +1,19 @@
+import torch
+from mega_vit.main import MegaVit
+
+v = MegaVit(
+    image_size = 256,
+    patch_size = 32,
+    num_classes = 1000,
+    dim = 1024,
+    depth = 6,
+    heads = 16,
+    mlp_dim = 2048,
+    dropout = 0.1,
+    emb_dropout = 0.1
+)
+
+img = torch.randn(1, 3, 256, 256)
+
+preds = v(img) # (1, 1000)
+print(preds)

mega_vit/__init__.py

@@ -0,0 +1 @@
+from mega_vit.main import MegaVit

mega_vit/main.py

@@ -107,7 +107,7 @@ def forward(self, x):
 
         return self.norm(x)
 
-class ViT(nn.Module):
+class MegaVit(nn.Module):
     def __init__(
         self, 
         *, 
@@ -189,22 +189,22 @@ def forward(self, img):
 # preds = v(img) # (1, 1000)
 # print(preds)
 
-import torch
-# from vit_pytorch import ViT
-
-v = ViT(
-    image_size = 256,
-    patch_size = 32,
-    num_classes = 1000,
-    dim = 1024,
-    depth = 6,
-    heads = 16,
-    mlp_dim = 2048,
-    dropout = 0.1,
-    emb_dropout = 0.1
-)
-
-img = torch.randn(1, 3, 256, 256)
-
-preds = v(img) # (1, 1000)
-print(preds)
+# import torch
+# # from vit_pytorch import ViT
+
+# v = MegaVit(
+#     image_size = 256,
+#     patch_size = 32,
+#     num_classes = 1000,
+#     dim = 1024,
+#     depth = 6,
+#     heads = 16,
+#     mlp_dim = 2048,
+#     dropout = 0.1,
+#     emb_dropout = 0.1
+# )
+
+# img = torch.randn(1, 3, 256, 256)
+
+# preds = v(img) # (1, 1000)
+# print(preds)

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "mega-vit"
-version = "0.0.1"
+version = "0.0.2"
 description = "mega-vit - Pytorch"
 license = "MIT"
 authors = ["Kye Gomez <[email protected]>"]