|
|
coco_category_to_id_v1 = { |
|
|
0: 'road', |
|
|
1: 'sidewalk', |
|
|
2: 'building', |
|
|
3: 'wall', |
|
|
4: 'fence', |
|
|
5: 'pole', |
|
|
6: 'traffic light', |
|
|
7: 'traffic sign', |
|
|
8: 'vegetation', |
|
|
9: 'terrain', |
|
|
10: 'sky', |
|
|
11: 'person', |
|
|
12: 'rider', |
|
|
13: 'car', |
|
|
14: 'truck', |
|
|
15: 'bus', |
|
|
16: 'train', |
|
|
17: 'motorcycle', |
|
|
18: 'bicycle' |
|
|
} |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
classes = { |
|
|
0: 'background', |
|
|
1: 'person', |
|
|
2: 'bicycle', |
|
|
3: 'car', |
|
|
4: 'motorcycle', |
|
|
5: 'airplane', |
|
|
6: 'bus', |
|
|
7: 'train', |
|
|
8: 'truck', |
|
|
9: 'boat', |
|
|
10: 'traffic light', |
|
|
11: 'fire hydrant', |
|
|
12: 'stop sign', |
|
|
13: 'parking meter', |
|
|
14: 'bench', |
|
|
15: 'bird', |
|
|
16: 'cat', |
|
|
17: 'dog', |
|
|
18: 'horse', |
|
|
19: 'sheep', |
|
|
20: 'cow', |
|
|
21: 'elephant', |
|
|
22: 'bear', |
|
|
23: 'zebra', |
|
|
24: 'giraffe', |
|
|
25: 'backpack', |
|
|
26: 'umbrella', |
|
|
27: 'handbag', |
|
|
28: 'tie', |
|
|
29: 'suitcase', |
|
|
30: 'frisbee', |
|
|
31: 'skis', |
|
|
32: 'snowboard', |
|
|
33: 'sports ball', |
|
|
34: 'kite', |
|
|
35: 'baseball bat', |
|
|
36: 'baseball glove', |
|
|
37: 'skateboard', |
|
|
38: 'surfboard', |
|
|
39: 'tennis racket', |
|
|
40: 'bottle', |
|
|
41: 'wine glass', |
|
|
42: 'cup', |
|
|
43: 'fork', |
|
|
44: 'knife', |
|
|
45: 'spoon', |
|
|
46: 'bowl', |
|
|
47: 'banana', |
|
|
48: 'apple', |
|
|
49: 'sandwich', |
|
|
50: 'orange', |
|
|
51: 'broccoli', |
|
|
52: 'carrot', |
|
|
53: 'hot dog', |
|
|
54: 'pizza', |
|
|
55: 'donut', |
|
|
56: 'cake', |
|
|
57: 'chair', |
|
|
58: 'couch', |
|
|
59: 'potted plant', |
|
|
60: 'bed', |
|
|
61: 'dining table', |
|
|
62: 'toilet', |
|
|
63: 'TV', |
|
|
64: 'laptop', |
|
|
65: 'mouse', |
|
|
66: 'remote', |
|
|
67: 'keyboard', |
|
|
68: 'cell phone', |
|
|
69: 'microwave', |
|
|
70: 'oven', |
|
|
71: 'toaster', |
|
|
72: 'sink', |
|
|
73: 'refrigerator', |
|
|
74: 'book', |
|
|
75: 'clock', |
|
|
76: 'vase', |
|
|
77: 'scissors', |
|
|
78: 'teddy bear', |
|
|
79: 'hair drier', |
|
|
80: 'toothbrush' |
|
|
} |
|
|
|
|
|
|
|
|
opt = { |
|
|
'prompt': "a photo of a lion on a mountain top at sunset", |
|
|
'category': "lion", |
|
|
'outdir': "Results", |
|
|
'skip_grid': False, |
|
|
'skip_save': False, |
|
|
'ddim_steps': 1, |
|
|
'thread_num': 1, |
|
|
'prompt_root': "/", |
|
|
'fixed_code': False, |
|
|
'ddim_eta': 0.0, |
|
|
'n_each_class': 20, |
|
|
'H': 512, |
|
|
'W': 512, |
|
|
'C': 4, |
|
|
'f': 8, |
|
|
'n_samples': 1, |
|
|
'n_rows': 0, |
|
|
'scale': 7.5, |
|
|
'from_file': None, |
|
|
'config': "configs/stable-diffusion/v1-inference.yaml", |
|
|
'sd_ckpt': "stable_diffusion.ckpt", |
|
|
'grounding_ckpt': "gen_model.pth", |
|
|
'seed': 42, |
|
|
'precision': "autocast", |
|
|
'classes': { |
|
|
|
|
|
|
|
|
}, |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
} |
