add requirements.txt

app.py

@@ -1,17 +1,16 @@
-import clip
 import gradio as gr
 import os
 import torch
 from torchvision import transforms
 from PIL import Image
 from torchvision.datasets import CIFAR100
+from transformers import CLIPProcessor, CLIPModel
 
-model, preprocess = clip.load('ViT-B/32', "cpu")
-
+model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
+processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
 
 cifar100 = CIFAR100(root=os.path.expanduser("~/.cache"), download=True, train=False)
 
-
 IMG_SIZE = 32 if torch.cuda.is_available() else 32
 COMPOSED_TRANSFORMERS = transforms.Compose([
     transforms.Resize(IMG_SIZE),
@@ -35,10 +34,13 @@ def normalize_tensor(tensor: torch.tensor) -> torch.tensor:
 
 
 def send_inputs(img):
-    img = np_array_to_tensor_image(img)
-    img = normalize_tensor(img)
-    result = model(img)
-    return result
+    ##img = np_array_to_tensor_image(img)
+    ##img = normalize_tensor(img)
+    inputs = processor(images=img, return_tensors="pt", padding=True)
+    outputs = model(**inputs)
+    logits_per_image = outputs.logits_per_image
+    probs = logits_per_image.softmax(dim=1)
+    return probs
 
 
 if __name__ == "__main__":

requirements.txt

@@ -1,5 +1,5 @@
-clip~=0.2.0
 torch~=1.11.0
 torchvision~=0.12.0
 gradio~=3.0.2
-Pillow~=9.0.1
+Pillow~=9.0.1
+transformers~=4.19.4