Mask2Former / app.py
akhaliq's picture
akhaliq HF staff
Update app.py
0970ad6
raw history blame
No virus
3.35 kB
import os
import sys
os.system("pip install imutils")
os.system('pip install detectron2 -f https://dl.fbaipublicfiles.com/detectron2/wheels/cu102/torch1.9/index.html')
os.system("pip install git+https://github.com/cocodataset/panopticapi.git")
import gradio as gr
# check pytorch installation:
import detectron2
from detectron2.utils.logger import setup_logger
# import some common libraries
import numpy as np
import cv2
import torch
# import some common detectron2 utilities
from detectron2 import model_zoo
from detectron2.engine import DefaultPredictor
from detectron2.config import get_cfg
from detectron2.utils.visualizer import Visualizer, ColorMode
from detectron2.data import MetadataCatalog
from detectron2.projects.deeplab import add_deeplab_config
coco_metadata = MetadataCatalog.get("coco_2017_val_panoptic")
# import Mask2Former project
from mask2former import add_maskformer2_config
from PIL import Image
import imutils
cfg = get_cfg()
cfg.MODEL.DEVICE='cpu'
add_deeplab_config(cfg)
add_maskformer2_config(cfg)
cfg.merge_from_file("configs/coco/panoptic-segmentation/swin/maskformer2_swin_large_IN21k_384_bs16_100ep.yaml")
cfg.MODEL.WEIGHTS = 'https://dl.fbaipublicfiles.com/maskformer/mask2former/coco/panoptic/maskformer2_swin_large_IN21k_384_bs16_100ep/model_final_f07440.pkl'
cfg.MODEL.MASK_FORMER.TEST.SEMANTIC_ON = True
cfg.MODEL.MASK_FORMER.TEST.INSTANCE_ON = True
cfg.MODEL.MASK_FORMER.TEST.PANOPTIC_ON = True
predictor = DefaultPredictor(cfg)
os.system("wget https://i.imgur.com/Vj17K5z.jpg")
def inference(img):
im = cv2.imread(img)
im = imutils.resize(im, width=512)
outputs = predictor(im)
v = Visualizer(im[:, :, ::-1], coco_metadata, scale=1.2, instance_mode=ColorMode.IMAGE_BW)
panoptic_result = v.draw_panoptic_seg(outputs["panoptic_seg"][0].to("cpu"), outputs["panoptic_seg"][1]).get_image()
v = Visualizer(im[:, :, ::-1], coco_metadata, scale=1.2, instance_mode=ColorMode.IMAGE_BW)
instance_result = v.draw_instance_predictions(outputs["instances"].to("cpu")).get_image()
v = Visualizer(im[:, :, ::-1], coco_metadata, scale=1.2, instance_mode=ColorMode.IMAGE_BW)
semantic_result = v.draw_sem_seg(outputs["sem_seg"].argmax(0).to("cpu")).get_image()
return Image.fromarray(np.uint8(panoptic_result)).convert('RGB'),Image.fromarray(np.uint8(instance_result)).convert('RGB'),Image.fromarray(np.uint8(semantic_result)).convert('RGB')
title = "Mask2Former"
description = "Gradio demo for Mask2Former: Masked-attention Mask Transformer for Universal Image Segmentation. To use it, simply upload your image, or click one of the examples to load them. Read more at the links below."
article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2112.01527' target='_blank'>Masked-attention Mask Transformer for Universal Image Segmentation</a> | <a href='https://github.com/facebookresearch/Mask2Former' target='_blank'>Github Repo</a></p>"
examples = [['Vj17K5z.jpg']]
gr.Interface(inference, inputs=gr.inputs.Image(type="filepath"), outputs=[gr.outputs.Image(label="Panoptic segmentation",type="pil"),gr.outputs.Image(label="instance segmentation",type="pil"),gr.outputs.Image(label="semantic segmentation",type="pil")], title=title,
description=description,
article=article,
examples=examples).launch(enable_queue=True,cache_examples=True)