Update app.py

app.py

@@ -4,33 +4,16 @@ import numpy as np
 import gradio as gr
 
 
-siglip_checkpoint = "nielsr/siglip-base-patch16-224"
-clip_checkpoint = "openai/clip-vit-base-patch16"
+clip_checkpoint = "laion/CLIP-ViT-H-14-laion2B-s32B-b79K"
 clip_detector = pipeline(model=clip_checkpoint, task="zero-shot-image-classification")
-siglip_model = SiglipModel.from_pretrained("google/siglip-base-patch16-224")
-siglip_processor = AutoProcessor.from_pretrained("google/siglip-base-patch16-224")
 
 
 def postprocess(output):
   return {out["label"]: float(out["score"]) for out in output}
 
-def postprocess_siglip(output, labels):
-  return {labels[i]: float(np.array(output[0])[i]) for i in range(len(labels))}
-    
-def siglip_detector(image, texts):
-  inputs = siglip_processor(text=texts, images=image, return_tensors="pt",
-                     padding="max_length")
-
-  with torch.no_grad():
-    outputs = siglip_model(**inputs)
-    logits_per_image = outputs.logits_per_image
-    probs = torch.sigmoid(logits_per_image) 
-  return probs
-
 
 def infer(image, candidate_labels):
   candidate_labels = [label.lstrip(" ") for label in candidate_labels.split(",")]
-  siglip_out = siglip_detector(image, candidate_labels)
   clip_out = clip_detector(image, candidate_labels=candidate_labels)
   return postprocess(clip_out), postprocess_siglip(siglip_out, labels=candidate_labels)
 
@@ -46,14 +29,12 @@ with gr.Blocks() as demo:
 
     with gr.Column():
       clip_output = gr.Label(label = "CLIP Output", num_top_classes=3)
-      siglip_output = gr.Label(label = "SigLIP Output", num_top_classes=3)
       
   examples = [["./baklava.jpg", "baklava, souffle, tiramisu"]]
   gr.Examples(
         examples = examples, 
         inputs=[image_input, text_input],
         outputs=[clip_output, 
-                 siglip_output
                  ],
         fn=infer,
         cache_examples=True
@@ -61,7 +42,6 @@ with gr.Blocks() as demo:
   run_button.click(fn=infer,
                     inputs=[image_input, text_input],
                     outputs=[clip_output, 
-                             siglip_output
                              ])
 
 demo.launch()