import os import sys os.system("pip install gdown") 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 from contextlib import ExitStack # import some common libraries import numpy as np import cv2 import torch import itertools # import some common detectron2 utilities from detectron2 import model_zoo from detectron2.config import get_cfg from detectron2.utils.visualizer import Visualizer, ColorMode, random_color from detectron2.data import MetadataCatalog from detectron2.projects.deeplab import add_deeplab_config coco_metadata = MetadataCatalog.get("coco_2017_val_panoptic") # import FCCLIP project from fcclip import add_maskformer2_config, add_fcclip_config from demo.predictor import DefaultPredictor, OpenVocabVisualizer from PIL import Image import imutils import json setup_logger() logger = setup_logger(name="fcclip") cfg = get_cfg() cfg.MODEL.DEVICE='cpu' add_deeplab_config(cfg) add_maskformer2_config(cfg) add_fcclip_config(cfg) cfg.merge_from_file("configs/coco/panoptic-segmentation/fcclip/fcclip_convnext_large_eval_ade20k.yaml") os.system("gdown 1-91PIns86vyNaL3CzMmDD39zKGnPMtvj") cfg.MODEL.WEIGHTS = './fcclip_cocopan.pth' cfg.MODEL.KMAX_DEEPLAB.TEST.SEMANTIC_ON = False cfg.MODEL.KMAX_DEEPLAB.TEST.INSTANCE_ON = False cfg.MODEL.KMAX_DEEPLAB.TEST.PANOPTIC_ON = True predictor = DefaultPredictor(cfg) # def inference(img): # im = cv2.imread(img) # #im = imutils.resize(im, width=512) # outputs = predictor(im) # v = OpenVocabVisualizer(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() # return Image.fromarray(np.uint8(panoptic_result)).convert('RGB') title = "FC-CLIP" description = """Gradio demo for FC-CLIP. To use it, simply upload your image, or click one of the examples to load them. FC-CLIP could perform open vocabulary segmentation, you may input more classes (separate by comma). The expected format is 'a1,a2;b1,b2', where a1,a2 are synonyms vocabularies for the first class. The first word will be displayed as the class name.Read more at the links below.""" article = "
" examples = [ [ "demo/examples/coco.jpg", "black pickup truck, pickup truck; blue sky, sky", ["COCO (133 categories)", "ADE (150 categories)", "LVIS (1203 categories)"], ], [ "demo/examples/ade.jpg", "luggage, suitcase, baggage;handbag", ["ADE (150 categories)"], ], [ "demo/examples/ego4d.jpg", "faucet, tap; kitchen paper, paper towels", ["COCO (133 categories)"], ], ] coco_metadata = MetadataCatalog.get("openvocab_coco_2017_val_panoptic_with_sem_seg") ade20k_metadata = MetadataCatalog.get("openvocab_ade20k_panoptic_val") lvis_classes = open("./fcclip/data/datasets/lvis_1203_with_prompt_eng.txt", 'r').read().splitlines() lvis_classes = [x[x.find(':')+1:] for x in lvis_classes] lvis_colors = list( itertools.islice(itertools.cycle(coco_metadata.stuff_colors), len(lvis_classes)) ) # rerrange to thing_classes, stuff_classes coco_thing_classes = coco_metadata.thing_classes coco_stuff_classes = [x for x in coco_metadata.stuff_classes if x not in coco_thing_classes] coco_thing_colors = coco_metadata.thing_colors coco_stuff_colors = [x for x in coco_metadata.stuff_colors if x not in coco_thing_colors] ade20k_thing_classes = ade20k_metadata.thing_classes ade20k_stuff_classes = [x for x in ade20k_metadata.stuff_classes if x not in ade20k_thing_classes] ade20k_thing_colors = ade20k_metadata.thing_colors ade20k_stuff_colors = [x for x in ade20k_metadata.stuff_colors if x not in ade20k_thing_colors] def build_demo_classes_and_metadata(vocab, label_list): extra_classes = [] if vocab: for words in vocab.split(";"): extra_classes.append([word.strip() for word in words.split(",")]) extra_colors = [random_color(rgb=True, maximum=1) for _ in range(len(extra_classes))] demo_thing_classes = extra_classes demo_stuff_classes = [] demo_thing_colors = extra_colors demo_stuff_colors = [] if any("COCO" in label for label in label_list): demo_thing_classes += coco_thing_classes demo_stuff_classes += coco_stuff_classes demo_thing_colors += coco_thing_colors demo_stuff_colors += coco_stuff_colors if any("ADE" in label for label in label_list): demo_thing_classes += ade20k_thing_classes demo_stuff_classes += ade20k_stuff_classes demo_thing_colors += ade20k_thing_colors demo_stuff_colors += ade20k_stuff_colors if any("LVIS" in label for label in label_list): demo_thing_classes += lvis_classes demo_thing_colors += lvis_colors MetadataCatalog.pop("fcclip_demo_metadata", None) demo_metadata = MetadataCatalog.get("fcclip_demo_metadata") demo_metadata.thing_classes = [c[0] for c in demo_thing_classes] demo_metadata.stuff_classes = [ *demo_metadata.thing_classes, *[c[0] for c in demo_stuff_classes], ] demo_metadata.thing_colors = demo_thing_colors demo_metadata.stuff_colors = demo_thing_colors + demo_stuff_colors demo_metadata.stuff_dataset_id_to_contiguous_id = { idx: idx for idx in range(len(demo_metadata.stuff_classes)) } demo_metadata.thing_dataset_id_to_contiguous_id = { idx: idx for idx in range(len(demo_metadata.thing_classes)) } demo_classes = demo_thing_classes + demo_stuff_classes return demo_classes, demo_metadata def inference(image_path, vocab, label_list): logger.info("building class names") demo_classes, demo_metadata = build_demo_classes_and_metadata(vocab, label_list) predictor.set_metadata(demo_metadata) im = cv2.imread(image_path) outputs = predictor(im) v = OpenVocabVisualizer(im[:, :, ::-1], demo_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() return Image.fromarray(np.uint8(panoptic_result)).convert('RGB') with gr.Blocks(title=title) as demo: gr.Markdown("