Create app.py

app.py

@@ -0,0 +1,83 @@
+import gradio as gr
+from transformers import pipeline
+import os
+import spaces
+
+# Define some pre-populated vision models.
+PREDEFINED_MODELS = {
+    "ViT Base (google/vit-base-patch16-224)": "google/vit-base-patch16-224",
+    "DeiT Base (facebook/deit-base-distilled-patch16-224)": "facebook/deit-base-distilled-patch16-224",
+    "CLIP ViT Base (openai/clip-vit-base-patch32)": "openai/clip-vit-base-patch32"
+}
+
+@spaces.GPU
+def compare_vision_models(image, model1_choice, model1_custom, model2_choice, model2_custom):
+    """
+    For each model selection, use the pre-defined model identifier unless the user selects "Custom" and enters an identifier.
+    Then create an image-classification pipeline for each model and run inference on the provided image.
+    """
+    # Determine the model names to use:
+    model1_name = (
+        PREDEFINED_MODELS.get(model1_choice, model1_custom)
+        if model1_choice != "Custom" else model1_custom
+    )
+    model2_name = (
+        PREDEFINED_MODELS.get(model2_choice, model2_custom)
+        if model2_choice != "Custom" else model2_custom
+    )
+    
+    # Optionally, if you deploy on a GPU-enabled space (e.g. using ZeroGPU), you can set device=0.
+    # Here, we check an environment variable "USE_GPU" (set it to "1" in your Space's settings if needed).
+    device = 0 if os.environ.get("USE_GPU", "0") == "1" else -1
+
+    # Create pipelines. In this example we assume the models support image classification.
+    classifier1 = pipeline("image-classification", model=model1_name, device=device)
+    classifier2 = pipeline("image-classification", model=model2_name, device=device)
+
+    # Run inference
+    preds1 = classifier1(image)
+    preds2 = classifier2(image)
+
+    # Format the predictions as text (each line shows the predicted label and its confidence score)
+    result1 = "\n".join([f"{pred['label']}: {pred['score']:.3f}" for pred in preds1])
+    result2 = "\n".join([f"{pred['label']}: {pred['score']:.3f}" for pred in preds2])
+    
+    return result1, result2
+
+# Build the Gradio interface using Blocks.
+with gr.Blocks(title="Vision Model Comparison Tool") as demo:
+    gr.Markdown("## Vision Model Comparison Tool\nSelect two Hugging Face vision models to compare their outputs side-by-side!")
+    with gr.Row():
+        with gr.Column():
+            gr.Markdown("### Model 1")
+            model1_choice = gr.Dropdown(
+                choices=list(PREDEFINED_MODELS.keys()) + ["Custom"],
+                label="Select a pre-defined model or 'Custom'"
+            )
+            model1_custom = gr.Textbox(
+                label="Custom Hugging Face Model",
+                placeholder="e.g., username/model_name"
+            )
+        with gr.Column():
+            gr.Markdown("### Model 2")
+            model2_choice = gr.Dropdown(
+                choices=list(PREDEFINED_MODELS.keys()) + ["Custom"],
+                label="Select a pre-defined model or 'Custom'"
+            )
+            model2_custom = gr.Textbox(
+                label="Custom Hugging Face Model",
+                placeholder="e.g., username/model_name"
+            )
+    image_input = gr.Image(label="Input Image", type="pil")
+    compare_btn = gr.Button("Compare Models")
+    with gr.Row():
+        output1 = gr.Textbox(label="Model 1 Output")
+        output2 = gr.Textbox(label="Model 2 Output")
+
+    compare_btn.click(
+        fn=compare_vision_models,
+        inputs=[image_input, model1_choice, model1_custom, model2_choice, model2_custom],
+        outputs=[output1, output2]
+    )
+
+demo.launch()