Update app.py

app.py

@@ -119,101 +119,14 @@ def draw_ocr_bboxes(image, prediction):
 
 def process_image(image, task_prompt, text_input=None, model_id='J-LAB/Florence-Idesire'):
     image = Image.fromarray(image)  # Convert NumPy array to PIL Image
-    if task_prompt == 'More Detailed Caption':
+    if task_prompt == 'Product Caption':
         task_prompt = '<MORE_DETAILED_CAPTION>'
         results = run_example(task_prompt, image, model_id=model_id)
         return results, None
-    elif task_prompt == 'Detailed Caption':
-        task_prompt = '<DETAILED_CAPTION>'
-        results = run_example(task_prompt, image, model_id=model_id)
-        return results, None
     elif task_prompt == 'More Detailed Caption':
         task_prompt = '<MORE_DETAILED_CAPTION>'
         results = run_example(task_prompt, image, model_id=model_id)
         return results, None
-    elif task_prompt == 'Caption + Grounding':
-        task_prompt = '<CAPTION>'
-        results = run_example(task_prompt, image, model_id=model_id)
-        text_input = results[task_prompt]
-        task_prompt = '<CAPTION_TO_PHRASE_GROUNDING>'
-        results = run_example(task_prompt, image, text_input, model_id)
-        results['<CAPTION>'] = text_input
-        fig = plot_bbox(image, results['<CAPTION_TO_PHRASE_GROUNDING>'])
-        return results, fig_to_pil(fig)
-    elif task_prompt == 'Detailed Caption + Grounding':
-        task_prompt = '<DETAILED_CAPTION>'
-        results = run_example(task_prompt, image, model_id=model_id)
-        text_input = results[task_prompt]
-        task_prompt = '<CAPTION_TO_PHRASE_GROUNDING>'
-        results = run_example(task_prompt, image, text_input, model_id)
-        results['<DETAILED_CAPTION>'] = text_input
-        fig = plot_bbox(image, results['<CAPTION_TO_PHRASE_GROUNDING>'])
-        return results, fig_to_pil(fig)
-    elif task_prompt == 'More Detailed Caption + Grounding':
-        task_prompt = '<MORE_DETAILED_CAPTION>'
-        results = run_example(task_prompt, image, model_id=model_id)
-        text_input = results[task_prompt]
-        task_prompt = '<CAPTION_TO_PHRASE_GROUNDING>'
-        results = run_example(task_prompt, image, text_input, model_id)
-        results['<MORE_DETAILED_CAPTION>'] = text_input
-        fig = plot_bbox(image, results['<CAPTION_TO_PHRASE_GROUNDING>'])
-        return results, fig_to_pil(fig)
-    elif task_prompt == 'Object Detection':
-        task_prompt = '<OD>'
-        results = run_example(task_prompt, image, model_id=model_id)
-        fig = plot_bbox(image, results['<OD>'])
-        return results, fig_to_pil(fig)
-    elif task_prompt == 'Dense Region Caption':
-        task_prompt = '<DENSE_REGION_CAPTION>'
-        results = run_example(task_prompt, image, model_id=model_id)
-        fig = plot_bbox(image, results['<DENSE_REGION_CAPTION>'])
-        return results, fig_to_pil(fig)
-    elif task_prompt == 'Region Proposal':
-        task_prompt = '<REGION_PROPOSAL>'
-        results = run_example(task_prompt, image, model_id=model_id)
-        fig = plot_bbox(image, results['<REGION_PROPOSAL>'])
-        return results, fig_to_pil(fig)
-    elif task_prompt == 'Caption to Phrase Grounding':
-        task_prompt = '<CAPTION_TO_PHRASE_GROUNDING>'
-        results = run_example(task_prompt, image, text_input, model_id)
-        fig = plot_bbox(image, results['<CAPTION_TO_PHRASE_GROUNDING>'])
-        return results, fig_to_pil(fig)
-    elif task_prompt == 'Referring Expression Segmentation':
-        task_prompt = '<REFERRING_EXPRESSION_SEGMENTATION>'
-        results = run_example(task_prompt, image, text_input, model_id)
-        output_image = copy.deepcopy(image)
-        output_image = draw_polygons(output_image, results['<REFERRING_EXPRESSION_SEGMENTATION>'], fill_mask=True)
-        return results, output_image
-    elif task_prompt == 'Region to Segmentation':
-        task_prompt = '<REGION_TO_SEGMENTATION>'
-        results = run_example(task_prompt, image, text_input, model_id)
-        output_image = copy.deepcopy(image)
-        output_image = draw_polygons(output_image, results['<REGION_TO_SEGMENTATION>'], fill_mask=True)
-        return results, output_image
-    elif task_prompt == 'Open Vocabulary Detection':
-        task_prompt = '<OPEN_VOCABULARY_DETECTION>'
-        results = run_example(task_prompt, image, text_input, model_id)
-        bbox_results = convert_to_od_format(results['<OPEN_VOCABULARY_DETECTION>'])
-        fig = plot_bbox(image, bbox_results)
-        return results, fig_to_pil(fig)
-    elif task_prompt == 'Region to Category':
-        task_prompt = '<REGION_TO_CATEGORY>'
-        results = run_example(task_prompt, image, text_input, model_id)
-        return results, None
-    elif task_prompt == 'Region to Description':
-        task_prompt = '<REGION_TO_DESCRIPTION>'
-        results = run_example(task_prompt, image, text_input, model_id)
-        return results, None
-    elif task_prompt == 'OCR':
-        task_prompt = '<OCR>'
-        results = run_example(task_prompt, image, model_id=model_id)
-        return results, None
-    elif task_prompt == 'OCR with Region':
-        task_prompt = '<OCR_WITH_REGION>'
-        results = run_example(task_prompt, image, model_id=model_id)
-        output_image = copy.deepcopy(image)
-        output_image = draw_ocr_bboxes(output_image, results['<OCR_WITH_REGION>'])
-        return results, output_image
     else:
         return "", None  # Return empty string and None for unknown task prompts
 
@@ -227,25 +140,10 @@ css = """
 
 
 single_task_list =[
-    'Caption', 'Detailed Caption', 'More Detailed Caption', 'Object Detection',
-    'Dense Region Caption', 'Region Proposal', 'Caption to Phrase Grounding',
-    'Referring Expression Segmentation', 'Region to Segmentation',
-    'Open Vocabulary Detection', 'Region to Category', 'Region to Description',
-    'OCR', 'OCR with Region'
-]
-
-cascased_task_list =[
-    'Caption + Grounding', 'Detailed Caption + Grounding', 'More Detailed Caption + Grounding'
+    'More Detailed Caption', 'Product Caption'
 ]
 
 
-def update_task_dropdown(choice):
-    if choice == 'Cascased task':
-        return gr.Dropdown(choices=cascased_task_list, value='Caption + Grounding')
-    else:
-        return gr.Dropdown(choices=single_task_list, value='Caption')
-
-
 
 with gr.Blocks(css=css) as demo:
     gr.Markdown(DESCRIPTION)
@@ -256,25 +154,12 @@ with gr.Blocks(css=css) as demo:
                 model_selector = gr.Dropdown(choices=list(models.keys()), label="Model", value='J-LAB/Florence-Idesire')
                 task_type = gr.Radio(choices=['Single task', 'Cascased task'], label='Task type selector', value='Single task')
                 task_prompt = gr.Dropdown(choices=single_task_list, label="Task Prompt", value="Caption")
-                task_type.change(fn=update_task_dropdown, inputs=task_type, outputs=task_prompt)
                 text_input = gr.Textbox(label="Text Input (optional)")
                 submit_btn = gr.Button(value="Submit")
             with gr.Column():
                 output_text = gr.Textbox(label="Output Text")
                 output_img = gr.Image(label="Output Image")
 
-        gr.Examples(
-            examples=[
-                ["image1.jpg", 'Object Detection'],
-                ["image2.jpg", 'OCR with Region']
-            ],
-            inputs=[input_img, task_prompt],
-            outputs=[output_text, output_img],
-            fn=process_image,
-            cache_examples=True,
-            label='Try examples'
-        )
-
         submit_btn.click(process_image, [input_img, task_prompt, text_input, model_selector], [output_text, output_img])
 
 demo.launch(debug=True)