update app

app.py

@@ -8,25 +8,31 @@ from transformers import CLIPProcessor, CLIPModel
 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)
+cifar100 = CIFAR100(root=os.path.expanduser("~/.cache"), download=False, train=False)
 
-text_inputs = torch.cat([clip.tokenize(f"a photo of a {c}") for c in cifar100.classes])
-text_inputs_2 = ["a photo of a dog", "a photo of a cat"]
+text_inputs = []
 
+for c in cifar100.classes:
+    classes = "a photo of a " + c
+    print(classes)
+    text_inputs.append(classes)
 
-# TODO debug cette ligne pour avoir un affichage correct
+print(text_inputs)
 
-
-# TODO Finir l'affichage du résultat
+test = ["a photo of a dog", "a photo of a cat"]
 
 
 def send_inputs(img):
-    inputs = processor(text=text_inputs_2, images=img, return_tensors="pt", padding=True)
+    inputs = processor(text=test, images=img, return_tensors="pt", padding=True)
+
     outputs = model(**inputs)
     logits_per_image = outputs.logits_per_image
     probs = logits_per_image.softmax(dim=1)
-    print(probs)
-    return probs
+
+    result = probs.argmax(dim=1)
+    index = result.item()
+    print(test[index])
+    return test[index]
 
 
 if __name__ == "__main__":