Update app.py

app.py

@@ -1,124 +1,75 @@
-import gradio as gr
-from transformers import AutoProcessor, AutoModelForCausalLM
-import re
-from PIL import Image 
 import os
-import numpy as np
-import spaces
+import re
 import subprocess
+import numpy as np
+from PIL import Image
+import gradio as gr
 import torch
+from transformers import AutoProcessor, AutoModelForCausalLM
 
 
-subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
+# Load model and processor, enabling trust_remote_code if needed
+model_name = "PJMixers-Images/Florence-2-base-Castollux-v0.5"
+model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True).eval()
+processor = AutoProcessor.from_pretrained(model_name, trust_remote_code=True)
 
-model = AutoModelForCausalLM.from_pretrained(
-    'PJMixers-Images/Florence-2-base-Castollux-v0.5',
-    trust_remote_code=True
-).eval()
-processor = AutoProcessor.from_pretrained(
-    'PJMixers-Images/Florence-2-base-Castollux-v0.5',
-    trust_remote_code=True
-)
+# Set device (GPU if available)
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
 
 TITLE = "# [PJMixers-Images/Florence-2-base-Castollux-v0.5](https://huggingface.co/PJMixers-Images/Florence-2-base-Castollux-v0.5)"
 
 
-@spaces.GPU
 def process_image(image):
-    if isinstance(image, np.ndarray):
-        image = Image.fromarray(image)
-    elif isinstance(image, str):
-        image = Image.open(image)
-    if image.mode != "RGB":
-        image = image.convert("RGB")
-    
-    inputs = processor(text="<CAPTION>", images=image, return_tensors="pt")
-    generated_ids = model.generate(
-        input_ids=inputs["input_ids"],
-        pixel_values=inputs["pixel_values"],
-        max_new_tokens=1024,
-        num_beams=5,
-        do_sample=True
-    )
-    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]
-
-    return processor.post_process_generation(generated_text, task="<CAPTION>", image_size=(image.width, image.height))
-
-
-def extract_frames(image_path, output_folder):
-    with Image.open(image_path) as img:
-        base_name = os.path.splitext(os.path.basename(image_path))[0]
-        frame_paths = []
-        
-        try:
-            for i in range(0, img.n_frames):
-                img.seek(i)
-                frame_path = os.path.join(output_folder, f"{base_name}_frame_{i:03d}.png")
-                img.save(frame_path)
-                frame_paths.append(frame_path)
-        except EOFError:
-            pass  # We've reached the end of the sequence
-        
-        return frame_paths
-
-
-def process_folder(folder_path):
-    if not os.path.isdir(folder_path):
-        return "Invalid folder path."
-    
-    processed_files = []
-    skipped_files = []
-    for filename in os.listdir(folder_path):
-        if filename.lower().endswith(('.png', '.jpg', '.jpeg', '.gif', '.bmp', '.webp', '.heic')):
-            image_path = os.path.join(folder_path, filename)
-            txt_filename = os.path.splitext(filename)[0] + '.txt'
-            txt_path = os.path.join(folder_path, txt_filename)
-            
-            # Check if the corresponding text file already exists
-            if os.path.exists(txt_path):
-                skipped_files.append(f"Skipped {filename} (text file already exists)")
-                continue
-            
-            # Check if the image has multiple frames
-            with Image.open(image_path) as img:
-                if getattr(img, "is_animated", False) and img.n_frames > 1:
-                    # Extract frames
-                    frames = extract_frames(image_path, folder_path)
-                    for frame_path in frames:
-                        frame_txt_filename = os.path.splitext(os.path.basename(frame_path))[0] + '.txt'
-                        frame_txt_path = os.path.join(folder_path, frame_txt_filename)
-                        
-                        # Check if the corresponding text file for the frame already exists
-                        if os.path.exists(frame_txt_path):
-                            skipped_files.append(f"Skipped {os.path.basename(frame_path)} (text file already exists)")
-                            continue
-                        
-                        caption = process_image(frame_path)
-                        
-                        with open(frame_txt_path, 'w', encoding='utf-8') as f:
-                            f.write(caption)
-                        
-                        processed_files.append(f"Processed {os.path.basename(frame_path)} -> {frame_txt_filename}")
-                else:
-                    # Process single image
-                    caption = process_image(image_path)
-                    
-                    with open(txt_path, 'w', encoding='utf-8') as f:
-                        f.write(caption)
-                    
-                    processed_files.append(f"Processed {filename} -> {txt_filename}")
-    
-    result = "\n".join(processed_files + skipped_files)
-
-    return result if result else "No image files found or all files were skipped in the specified folder."
+    """
+    Process a single image to generate a caption.
+    Supports image input as file path, numpy array, or PIL Image.
+    """
+    try:
+        # Convert input to PIL image if necessary
+        if isinstance(image, np.ndarray):
+            image = Image.fromarray(image)
+        elif isinstance(image, str):
+            image = Image.open(image)
+        if image.mode != "RGB":
+            image = image.convert("RGB")
+
+        # Prepare inputs for the model
+        inputs = processor(text="<CAPTION>", images=image, return_tensors="pt")
+        # Move tensors to the appropriate device
+        inputs = {k: v.to(device) for k, v in inputs.items()}
+
+        # Disable gradients during inference
+        with torch.no_grad():
+            generated_ids = model.generate(
+                input_ids=inputs["input_ids"],
+                pixel_values=inputs["pixel_values"],
+                max_new_tokens=1024,
+                num_beams=5,
+                do_sample=True,
+            )
+
+        # Decode and post-process the generated text
+        generated_text = processor.batch_decode(
+            generated_ids, skip_special_tokens=False
+        )[0]
+        caption = processor.post_process_generation(
+            generated_text, task="<CAPTION>", image_size=(image.width, image.height)
+        )
+        return caption
+
+    except Exception as e:
+        return f"Error processing image: {e}"
 
+
+# Custom CSS to style the output box
 css = """
 #output { height: 500px; overflow: auto; border: 1px solid #ccc; }
 """
 
 with gr.Blocks(css=css) as demo:
     gr.Markdown(TITLE)
-    
+
     with gr.Tab(label="Single Image Processing"):
         with gr.Row():
             with gr.Column():
@@ -126,7 +77,7 @@ with gr.Blocks(css=css) as demo:
                 submit_btn = gr.Button(value="Submit")
             with gr.Column():
                 output_text = gr.Textbox(label="Output Text")
-        
+
         gr.Examples(
             [
                 ["eval_img_1.jpg"],
@@ -136,22 +87,15 @@ with gr.Blocks(css=css) as demo:
                 ["eval_img_5.jpg"],
                 ["eval_img_6.jpg"],
                 ["eval_img_7.png"],
-                ["eval_img_8.jpg"]
+                ["eval_img_8.jpg"],
             ],
             inputs=[input_img],
             outputs=[output_text],
             fn=process_image,
-            label='Try captioning on below examples'
+            label="Try captioning on below examples",
         )
-        
-        submit_btn.click(process_image, [input_img], [output_text])
 
-    with gr.Tab(label="Batch Processing"):
-        with gr.Row():
-            folder_input = gr.Textbox(label="Input Folder Path")
-            batch_submit_btn = gr.Button(value="Process Folder")
-        batch_output = gr.Textbox(label="Batch Processing Results", lines=10)
-        
-        batch_submit_btn.click(process_folder, [folder_input], [batch_output])
+        submit_btn.click(process_image, [input_img], [output_text])
 
-demo.launch(debug=True)
+if __name__ == "__main__":
+    demo.launch(debug=True)