Code clean up

app.py

@@ -1030,17 +1030,6 @@ precomputed_results = json.load(open("data/precomputed_results.json"))
 request_header = {
     "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Safari/537.36"
 }
-### Loading model; hard-coded to mSigLIP for now.
-
-# if not precomputed_results:
-#     open_clip_model, open_clip_pretrained = "ViT-B-16-SigLIP-i18n-256", "webli"
-#     model, _, transform = open_clip.create_model_and_transforms(
-#         open_clip_model, pretrained=open_clip_pretrained
-#     )
-#     tokenizer = open_clip.get_tokenizer(open_clip_model)
-
-#     device = "cuda" if torch.cuda.is_available() else "cpu"
-#     model = model.to(device)
 
 
 def change_language(randomize_imgs, randomize_labels):
@@ -1048,14 +1037,6 @@ def change_language(randomize_imgs, randomize_labels):
     labels = babel_imagenet["EN"][1]
     class_order = list(range(len(labels)))
     np.random.shuffle(class_order)
-    ### We use no prompt ensembling for now
-    # if not precomputed_results:
-    #     text_tokens = tokenizer(labels).to(device)
-    #     with torch.no_grad():
-    #         text_features = model.encode_text(text_tokens).float()
-    #         text_features /= text_features.norm(dim=-1, keepdim=True)
-    #         text_features = text_features.cpu().numpy()
-    # else:
     text_features = None
     correct_text = gr.Text(
         f"Correct was: ''. Question 1/{len(babel_imagenet['EN'][0])} ", label="Game"
@@ -1119,35 +1100,10 @@ def prepare(raw_idx, text_embeddings, class_order):
         class_idx = lang_class_idxs[idx]
 
     img_idx = 0
-    img_idx = np.random.choice(
-        min(len(babelnet_images[class_idx]), max_image_choices)
-    )
+    img_idx = np.random.choice(min(len(babelnet_images[class_idx]), max_image_choices))
     img_url = babelnet_images[class_idx][img_idx]["url"]
     class_labels = openai_en_classes
 
-    # if not precomputed_results:
-    #     try:
-    #         image_input = (
-    #             transform(
-    #                 Image.open(
-    #                     requests.get(img_url, stream=True, headers=request_header).raw
-    #                 ).convert("RGB")
-    #             )
-    #             .unsqueeze(0)
-    #             .to(device)
-    #         )
-    #         with torch.no_grad():
-    #             image_features = model.encode_image(image_input).float()
-    #             image_features /= image_features.norm(dim=-1, keepdim=True)
-    #     except:
-    #         gr.Warning("There is a problem with the next class. Skipping it.")
-    #         return prepare(
-    #             raw_idx, text_embeddings, class_order
-    #         )
-
-    #     similarity = (text_embeddings @ image_features.cpu().numpy().T).squeeze()
-    #     choices = np.argsort(similarity)[-4:].tolist()
-    # else:
     choices = list(
         reversed(precomputed_results["EN"][idx][img_idx])
     )  # precomputing script uses torch.topk which sorts in reverse here
@@ -1194,35 +1150,10 @@ def reroll(raw_idx, text_embeddings, class_order):
     class_idx = lang_class_idxs[idx]
 
     img_idx = 0
-    img_idx = np.random.choice(
-        min(len(babelnet_images[class_idx]), max_image_choices)
-    )
+    img_idx = np.random.choice(min(len(babelnet_images[class_idx]), max_image_choices))
     img_url = babelnet_images[class_idx][img_idx]["url"]
     class_labels = openai_en_classes
 
-    # if not precomputed_results:
-    #     try:
-    #         image_input = (
-    #             transform(
-    #                 Image.open(
-    #                     requests.get(img_url, stream=True, headers=request_header).raw
-    #                 ).convert("RGB")
-    #             )
-    #             .unsqueeze(0)
-    #             .to(device)
-    #         )
-    #         with torch.no_grad():
-    #             image_features = model.encode_image(image_input).float()
-    #             image_features /= image_features.norm(dim=-1, keepdim=True)
-    #     except:
-    #         gr.Warning("There is a problem with the next class. Skipping it.")
-    #         return prepare(
-    #             raw_idx, text_embeddings, class_order
-    #         )
-
-    #     similarity = (text_embeddings @ image_features.cpu().numpy().T).squeeze()
-    #     choices = np.argsort(similarity)[-4:].tolist()
-    # else:
     choices = list(
         reversed(precomputed_results["EN"][idx][img_idx])
     )  # precomputing script uses torch.topk which sorts in reverse here
@@ -1283,19 +1214,7 @@ with gr.Blocks(title="Babel-ImageNet Quiz") as demo:
     )
 
     with gr.Row():
-        # language_select = gr.Dropdown(
-        #     choices=main_language_values,
-        #     value="EN",
-        #     interactive=True,
-        #     label="Select your language:",
-        # )
-        # randomize_classes = gr.Checkbox(
-        #     label="Randomize class order (or play in canonic order)", value=True
-        # )
-        # randomize_images = gr.Checkbox(
-        #     label="Randomize images (if unchecked, will always show the same image). Other images might be less relevant.",
-        #     value=True,
-        # )
+
         start_btn = gr.Button(value="Start", variant="primary")
 
     # quiz area
@@ -1378,7 +1297,4 @@ with gr.Blocks(title="Babel-ImageNet Quiz") as demo:
         outputs=[options, image, class_idx, correct_choice, model_choice, choices],
     )
 
-
-
-
-demo.launch()
+demo.launch()