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 import subprocess subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True) models = { 'microsoft/Florence-2-large-ft': AutoModelForCausalLM.from_pretrained('microsoft/Florence-2-large-ft', trust_remote_code=True).to("cuda").eval(), 'microsoft/Florence-2-large': AutoModelForCausalLM.from_pretrained('microsoft/Florence-2-large', trust_remote_code=True).to("cuda").eval(), 'microsoft/Florence-2-base-ft': AutoModelForCausalLM.from_pretrained('microsoft/Florence-2-base-ft', trust_remote_code=True).to("cuda").eval(), 'microsoft/Florence-2-base': AutoModelForCausalLM.from_pretrained('microsoft/Florence-2-base', trust_remote_code=True).to("cuda").eval(), } processors = { 'microsoft/Florence-2-large-ft': AutoProcessor.from_pretrained('microsoft/Florence-2-large-ft', trust_remote_code=True), 'microsoft/Florence-2-large': AutoProcessor.from_pretrained('microsoft/Florence-2-large', trust_remote_code=True), 'microsoft/Florence-2-base-ft': AutoProcessor.from_pretrained('microsoft/Florence-2-base-ft', trust_remote_code=True), 'microsoft/Florence-2-base': AutoProcessor.from_pretrained('microsoft/Florence-2-base', trust_remote_code=True), } DESCRIPTION = "# [Florence-2 Demo](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 run_example(task_prompt, image, text_input=None, model_id='microsoft/Florence-2-large'): model = models[model_id] processor = processors[model_id] if text_input is None: prompt = task_prompt else: prompt = task_prompt + text_input inputs = processor(text=prompt, images=image, return_tensors="pt").to("cuda") generated_ids = model.generate( input_ids=inputs["input_ids"], pixel_values=inputs["pixel_values"], max_new_tokens=1024, early_stopping=False, do_sample=False, num_beams=3, ) generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0] parsed_answer = processor.post_process_generation( generated_text, task=task_prompt, image_size=(image.width, image.height) ) return parsed_answer 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 def process_image(image, task_prompt, text_input=None, model_id='microsoft/Florence-2-large'): image = Image.fromarray(image) # Convert NumPy array to PIL Image if task_prompt == 'Caption': task_prompt = '