Demo / tasks /open_inst.py
MaureenZOU
init
e972e1f
raw
history blame
2.37 kB
# --------------------------------------------------------
# X-Decoder -- Generalized Decoding for Pixel, Image, and Language
# Copyright (c) 2022 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Xueyan Zou (xueyan@cs.wisc.edu)
# --------------------------------------------------------
import torch
import numpy as np
from PIL import Image
from torchvision import transforms
from utils.visualizer import Visualizer
from detectron2.utils.colormap import random_color
from detectron2.data import MetadataCatalog
from detectron2.structures import BitMasks
t = []
t.append(transforms.Resize(512, interpolation=Image.BICUBIC))
transform = transforms.Compose(t)
metadata = MetadataCatalog.get('ade20k_panoptic_train')
def open_instseg(model, image, texts, inpainting_text, *args, **kwargs):
thing_classes = [x.strip() for x in texts.split(',')]
thing_colors = [random_color(rgb=True, maximum=255).astype(np.int32).tolist() for _ in range(len(thing_classes))]
thing_dataset_id_to_contiguous_id = {x:x for x in range(len(thing_classes))}
MetadataCatalog.get("demo").set(
thing_colors=thing_colors,
thing_classes=thing_classes,
thing_dataset_id_to_contiguous_id=thing_dataset_id_to_contiguous_id,
)
with torch.no_grad():
model.model.sem_seg_head.predictor.lang_encoder.get_text_embeddings(thing_classes + ["background"], is_eval=True)
metadata = MetadataCatalog.get('demo')
model.model.metadata = metadata
model.model.sem_seg_head.num_classes = len(thing_classes)
image_ori = transform(image)
width = image_ori.size[0]
height = image_ori.size[1]
image = np.asarray(image_ori)
images = torch.from_numpy(image.copy()).permute(2,0,1).cuda()
batch_inputs = [{'image': images, 'height': height, 'width': width}]
outputs = model.forward(batch_inputs)
visual = Visualizer(image_ori, metadata=metadata)
inst_seg = outputs[-1]['instances']
inst_seg.pred_masks = inst_seg.pred_masks.cpu()
inst_seg.pred_boxes = BitMasks(inst_seg.pred_masks > 0).get_bounding_boxes()
demo = visual.draw_instance_predictions(inst_seg) # rgb Image
res = demo.get_image()
MetadataCatalog.remove('demo')
torch.cuda.empty_cache()
return Image.fromarray(res), '', None