Spaces:
Runtime error
Runtime error
| try: | |
| import detectron2 | |
| except: | |
| import os | |
| os.system('pip install git+https://github.com/facebookresearch/detectron2.git') | |
| import cv2 | |
| import torch | |
| from matplotlib.pyplot import axis | |
| import gradio as gr | |
| import requests | |
| import numpy as np | |
| from torch import nn | |
| import requests | |
| import torch | |
| from detectron2 import model_zoo | |
| from detectron2.engine import DefaultPredictor | |
| from detectron2.config import get_cfg | |
| from detectron2.utils.visualizer import Visualizer | |
| from detectron2.data import MetadataCatalog | |
| from detectron2.utils.visualizer import ColorMode | |
| model_path = "https://huggingface.co/asalhi85/Smartathon-Detectron2/resolve/9f4d573340b033e651d4937906f23850f9b6bc57/phase2_detectron_model.pth" | |
| cfg = get_cfg() | |
| cfg.merge_from_file("./faster_rcnn_X_101_32x8d_FPN_3x.yaml") | |
| cfg.MODEL.ROI_HEADS.NUM_CLASSES = 11 | |
| cfg.MODEL.WEIGHTS = model_path | |
| my_metadata = MetadataCatalog.get("dbmdz_coco_all") | |
| #my_metadata.thing_classes = ["GRAFFITI", "FADED_SIGNAGE","POTHOLES","GARBAGE","CONSTRUCTION_ROAD","BROKEN_SIGNAGE","BAD_STREETLIGHT","BAD_BILLBOARD","SAND_ON_ROAD","CLUTTER_SIDEWALK","UNKEPT_FACADE"] | |
| my_metadata.thing_classes = ["None", "BAD_BILLBOARD","BROKEN_SIGNAGE","CLUTTER_SIDEWALK","CONSTRUCTION_ROAD","FADED_SIGNAGE","GARBAGE","GRAFFITI","POTHOLES","SAND_ON_ROAD","UNKEPT_FACADE"] | |
| # #smart_dict={'GRAFFITI' : 0.0 , 'FADED_SIGNAGE': 1.0 , 'POTHOLES': 2.0, | |
| # 'GARBAGE' : 3.0 , 'CONSTRUCTION_ROAD': 4.0 , 'BROKEN_SIGNAGE': 5.0, | |
| # 'BAD_STREETLIGHT' : 6.0 , 'BAD_BILLBOARD': 7.0 , 'SAND_ON_ROAD':8.0, | |
| # 'CLUTTER_SIDEWALK' : 9.0 , 'UNKEPT_FACADE': 10.0} | |
| if not torch.cuda.is_available(): | |
| cfg.MODEL.DEVICE = "cpu" | |
| def inference(image_url, image, min_score): | |
| if image_url: | |
| r = requests.get(image_url) | |
| if r: | |
| im = np.frombuffer(r.content, dtype="uint8") | |
| im = cv2.imdecode(im, cv2.IMREAD_COLOR) | |
| else: | |
| im = cv2.imread(image) | |
| # Model expect BGR! | |
| #im = image[:,:,::-1] | |
| cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = min_score | |
| predictor = DefaultPredictor(cfg) | |
| outputs = predictor(im) | |
| v = Visualizer(im[:,:,::-1], my_metadata, scale=1.2, instance_mode=ColorMode.IMAGE ) | |
| out = v.draw_instance_predictions(outputs["instances"].to("cpu")) | |
| return out.get_image() | |
| title = "Smartathon Phase2 Demo - Baseer" | |
| description = "This demo introduces an interactive playground for our trained Detectron2 model." | |
| article = '<p>Detectron model is available from our repository <a href="https://github.com/asalhi/Smartathon-Baseer">here</a>.</p>' | |
| # gr.Interface( | |
| # inference, | |
| # [gr.inputs.Textbox(label="Image URL", placeholder=""), | |
| # gr.inputs.Image(type="filepath", image_mode="RGB", source="upload", optional=False, label="Input Image"), | |
| # gr.Slider(minimum=0.0, maximum=1.0, value=0.4, label="Minimum score"), | |
| # ], | |
| # gr.outputs.Image(type="pil", label="Output"), | |
| # #gr.Examples(['./d1.jpeg', './d2.jpeg', './d3.jpeg','./d4.jpeg','./d5.jpeg','./d6.jpeg'], inputs=gr.inputs.Image(type="filepath", image_mode="RGB", source="upload", optional=False, label="Input Image")), | |
| # title=title, | |
| # description=description, | |
| # article=article, | |
| # #examples=[['./d1.jpeg'], ['./d2.jpeg'], ['./d3.jpeg'],['./d4.jpeg'],['./d5.jpeg'],['./d6.jpeg']], | |
| # examples = gr.Examples(['./d1.jpeg', './d2.jpeg', './d3.jpeg','./d4.jpeg','./d5.jpeg','./d6.jpeg'], inputs=gr.inputs.Image(type="filepath", image_mode="RGB", source="upload", optional=False, label="Input Image")), | |
| # cache_examples=False).launch() | |
| # #examples=['./d1.jpeg', './d2.jpeg', './d3.jpeg','./d4.jpeg','./d5.jpeg','./d6.jpeg'] | |
| with gr.Blocks(title=title, | |
| css=".gradio-container {background:white;}" | |
| ) as demo: | |
| gr.HTML("""<h4 style="font-weight:bold; text-align:center; color:navy;">"Smartathon Phase2 Demo - Baseer"</h4>""") | |
| # # | |
| #gr.HTML("""<h5 style="color:navy;">1- Select an example by clicking a thumbnail below.</h5>""") | |
| gr.HTML("""<h5 style="color:navy;">1- Select an example by clicking a thumbnail below.<br> | |
| 2- Or upload an image by clicking on the canvas.<br> | |
| 3- Or insert direct url of an image.</h5>""") | |
| with gr.Row(): | |
| with gr.Column(): | |
| #gr.HTML("""<h5 style="color:navy;">3- Or insert direct url of an image.</h5>""") | |
| input_url = gr.Textbox(label="Image URL", placeholder="") | |
| #gr.HTML("""<h5 style="color:navy;">2- Or upload an image by clicking on the canvas.<br></h5>""") | |
| input_image = gr.Image(type="filepath", image_mode="RGB", source="upload", optional=False, label="Input Image") | |
| gr.HTML("""<h5 style="color:navy;">4- You can use this slider to control boxes min score: </h5>""") | |
| sliderr = gr.Slider(minimum=0.0, maximum=1.0, value=0.4, label="Minimum score") | |
| output_image = gr.Image(type="pil", label="Output") | |
| # gr.Interface( | |
| # inference, | |
| # [gr.inputs.Textbox(label="Image URL", placeholder=""), | |
| # gr.inputs.Image(type="filepath", image_mode="RGB", source="upload", optional=False, label="Input Image"), | |
| # gr.Slider(minimum=0.0, maximum=1.0, value=0.4, label="Minimum score"), | |
| # ], | |
| gr.Examples(['./d1.jpeg', './d2.jpeg', './d3.jpeg','./d4.jpeg','./d5.jpeg','./d6.jpeg'], inputs=input_image) | |
| #gr.HTML("""<br/>""") | |
| gr.HTML("""<h5 style="color:navy;">5- Then, click "Submit" button to predict object instances. It will take about 15-20 seconds (on cpu)</h5>""") | |
| send_btn = gr.Button("Submit") | |
| send_btn.click(fn=inference, inputs=[input_url,input_image,sliderr], outputs=[output_image], api_name="find") | |
| #gr.HTML("""<h5 style="color:navy;">Reference</h5>""") | |
| #gr.HTML("""<ul>""") | |
| gr.HTML("""<h5 style="color:navy;">Detectron model is available from our repository <a href="https://github.com/asalhi/Smartathon-Baseer">here</a>.</h5>""") | |
| #gr.HTML("""</ul>""") | |
| #demo.queue() | |
| demo.launch() # debug=True) | |