Update app.py

app.py

@@ -2,17 +2,8 @@ import gradio as gr
 from transformers import AutoProcessor, AutoModelForCausalLM
 import spaces
 
-import requests
-import copy
-
-from PIL import Image, ImageDraw, ImageFont 
 import io
-import matplotlib.pyplot as plt
-import matplotlib.patches as patches
-
-import random
-import numpy as np
-
+from PIL import Image
 import subprocess
 subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
 
@@ -26,18 +17,8 @@ processors = {
     'J-LAB/Florence_2_L_FluxiAI_Product_Caption': AutoProcessor.from_pretrained('J-LAB/Florence_2_L_FluxiAI_Product_Caption', trust_remote_code=True)
 }
 
-
 DESCRIPTION = "# [Florence-2 Product Describe by Fluxi IA](https://huggingface.co/microsoft/Florence-2-large)"
 
-colormap = ['blue','orange','green','purple','brown','pink','gray','olive','cyan','red',
-            'lime','indigo','violet','aqua','magenta','coral','gold','tan','skyblue']
-
-def fig_to_pil(fig):
-    buf = io.BytesIO()
-    fig.savefig(buf, format='png')
-    buf.seek(0)
-    return Image.open(buf)
-
 @spaces.GPU
 def process_image(image, task_prompt, text_input=None, model_id='J-LAB/Florence_2_B_FluxiAI_Product_Caption'):
     image = Image.fromarray(image)  # Convert NumPy array to PIL Image
@@ -59,64 +40,7 @@ def process_image(image, task_prompt, text_input=None, model_id='J-LAB/Florence_
     # Convert newline characters to HTML line breaks
     output_text = output_text.replace("\n\n", "<br><br>").replace("\n", "<br>")
 
-    return output_text, None
-
-def plot_bbox(image, data):
-    fig, ax = plt.subplots()
-    ax.imshow(image)
-    for bbox, label in zip(data['bboxes'], data['labels']):
-        x1, y1, x2, y2 = bbox
-        rect = patches.Rectangle((x1, y1), x2-x1, y2-y1, linewidth=1, edgecolor='r', facecolor='none')
-        ax.add_patch(rect)
-        plt.text(x1, y1, label, color='white', fontsize=8, bbox=dict(facecolor='red', alpha=0.5))
-    ax.axis('off')
-    return fig
-
-def draw_polygons(image, prediction, fill_mask=False):
-
-    draw = ImageDraw.Draw(image)
-    scale = 1
-    for polygons, label in zip(prediction['polygons'], prediction['labels']):
-        color = random.choice(colormap)
-        fill_color = random.choice(colormap) if fill_mask else None
-        for _polygon in polygons:
-            _polygon = np.array(_polygon).reshape(-1, 2)
-            if len(_polygon) < 3:
-                print('Invalid polygon:', _polygon)
-                continue
-            _polygon = (_polygon * scale).reshape(-1).tolist()
-            if fill_mask:
-                draw.polygon(_polygon, outline=color, fill=fill_color)
-            else:
-                draw.polygon(_polygon, outline=color)
-            draw.text((_polygon[0] + 8, _polygon[1] + 2), label, fill=color)
-    return image
-
-def convert_to_od_format(data):
-    bboxes = data.get('bboxes', [])
-    labels = data.get('bboxes_labels', [])
-    od_results = {
-        'bboxes': bboxes,
-        'labels': labels
-    }
-    return od_results
-
-def draw_ocr_bboxes(image, prediction):
-    scale = 1
-    draw = ImageDraw.Draw(image)
-    bboxes, labels = prediction['quad_boxes'], prediction['labels']
-    for box, label in zip(bboxes, labels):
-        color = random.choice(colormap)
-        new_box = (np.array(box) * scale).tolist()
-        draw.polygon(new_box, width=3, outline=color)
-        draw.text((new_box[0]+8, new_box[1]+2),
-                  "{}".format(label),
-                  align="right",
-                  fill=color)
-    return image
-
-
-
+    return output_text
 
 css = """
   #output {
@@ -126,13 +50,10 @@ css = """
   }
 """
 
-
-single_task_list =[
+single_task_list = [
     'Product Caption', 'More Detailed Caption'
 ]
 
-
-
 with gr.Blocks(css=css) as demo:
     gr.Markdown(DESCRIPTION)
     with gr.Tab(label="Florence-2 Image Captioning"):
@@ -146,8 +67,7 @@ with gr.Blocks(css=css) as demo:
                 submit_btn = gr.Button(value="Submit")
             with gr.Column():
                 output_text = gr.HTML(label="Output Text")
-                output_img = gr.Image(label="Output Image")
 
-        submit_btn.click(process_image, [input_img, task_prompt, text_input, model_selector], [output_text, output_img])
+        submit_btn.click(process_image, [input_img, task_prompt, text_input, model_selector], [output_text])
 
 demo.launch(debug=True)