Hugging Face's logo

Spaces:
gatesla
/
Image-Segmentation-Various
Running

App Files Community
Image-Segmentation-Various
File size: 9,099 Bytes 
3f1bb3e
 
 
 
 
 
 
 
1fb67a9
 
3f1bb3e
a134e44
3f1bb3e
 
 
 
 
 
 
 
 
 
 
 
1fb67a9
 
 
 
 
 
 
 
3f1bb3e
1fb67a9
 
3f1bb3e
 
 
 
1fb67a9
 
 
 
 
 
3f1bb3e
 
 
1fb67a9
 
 
 
 
 
 
 
 
 
 
 
a134e44
 
 
 
1fb67a9
 
 
 
 
 
 
 
 
 
a134e44
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
 
import matplotlib.pyplot as plt
import requests, validators
import torch
import pathlib
import numpy as np
from PIL import Image

from transformers import DetrFeatureExtractor, DetrForSegmentation, MaskFormerImageProcessor, MaskFormerForInstanceSegmentation
# from transformers.models.detr.feature_extraction_detr import rgb_to_id
from transformers.image_transforms import rgb_to_id

TEST_IMAGE = Image.open(r"images/9999999_00783_d_0000358.jpg")
MODEL_NAME_DETR = "facebook/detr-resnet-50-panoptic"
MODEL_NAME_MASKFORMER = "facebook/maskformer-swin-large-coco"
DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")

#######
# Parameters
#######
image = TEST_IMAGE
model_name = MODEL_NAME_MASKFORMER

# Starting with MaskFormer

processor = MaskFormerImageProcessor.from_pretrained(model_name) # <class 'transformers.models.maskformer.image_processing_maskformer.MaskFormerImageProcessor'>
# DIR() --> ['__call__', '__class__', '__delattr__', '__dict__', '__dir__', '__doc__', '__eq__', '__format__', '__ge__', '__getattribute__', '__gt__', '__hash__', '__init__', 
#           '__init_subclass__', '__le__', '__lt__', '__module__', '__ne__', '__new__', '__reduce__', '__reduce_ex__', '__repr__', '__setattr__', '__sizeof__', '__str__', '__subclasshook__', 
#           '__weakref__', '_auto_class', '_create_repo', '_get_files_timestamps', '_max_size', '_pad_image', '_preprocess', '_preprocess_image', '_preprocess_mask', '_processor_class', 
#           '_set_processor_class', '_upload_modified_files', 'center_crop', 'convert_segmentation_map_to_binary_masks', 'do_normalize', 'do_reduce_labels', 'do_rescale', 'do_resize', 
#           'encode_inputs', 'fetch_images', 'from_dict', 'from_json_file', 'from_pretrained', 'get_image_processor_dict', 'ignore_index', 'image_mean', 'image_std', 'model_input_names', 
#           'normalize', 'pad', 'post_process_instance_segmentation', 'post_process_panoptic_segmentation', 'post_process_segmentation', 'post_process_semantic_segmentation', 'preprocess', 
#           'push_to_hub', 'register_for_auto_class', 'resample', 'rescale', 'rescale_factor', 'resize', 'save_pretrained', 'size', 'size_divisor', 'to_dict', 'to_json_file', 'to_json_string']

model = MaskFormerForInstanceSegmentation.from_pretrained(model_name) # <class 'transformers.models.maskformer.modeling_maskformer.MaskFormerForInstanceSegmentation'>
# DIR for model was too big
model.to(DEVICE)

# img = np.array(TEST_IMAGE)

inputs = processor(images=image, return_tensors="pt") # <class 'transformers.image_processing_utils.BatchFeature'>
# DIR() --> ['_MutableMapping__marker', '__abstractmethods__', '__class__', '__contains__', '__copy__', '__delattr__', '__delitem__', '__dict__', '__dir__', '__doc__', '__eq__', '__format__', 
#           '__ge__', '__getattr__', '__getattribute__', '__getitem__', '__getstate__', '__gt__', '__hash__', '__init__', '__init_subclass__', '__iter__', '__le__', '__len__', '__lt__', 
#           '__module__', '__ne__', '__new__', '__reduce__', '__reduce_ex__', '__repr__', '__reversed__', '__setattr__', '__setitem__', '__setstate__', '__sizeof__', '__slots__', '__str__', 
#           '__subclasshook__', '__weakref__', '_abc_impl', '_get_is_as_tensor_fns', 'clear', 'convert_to_tensors', 'copy', 'data', 'fromkeys', 'get', 'items', 'keys', 'pop', 'popitem', 
#           'setdefault', 'to', 'update', 'values']
inputs.to(DEVICE)


outputs = model(**inputs) # <class 'transformers.models.maskformer.modeling_maskformer.MaskFormerForInstanceSegmentationOutput'>
# Each element of this class is a <class 'torch.Tensor'>
# DIR() --> ['__annotations__', '__class__', '__contains__', '__dataclass_fields__', '__dataclass_params__', '__delattr__', '__delitem__', '__dict__', '__dir__', 
#           '__doc__', '__eq__', '__format__', '__ge__', '__getattribute__', '__getitem__', '__gt__', '__hash__', '__init__', '__init_subclass__', '__iter__', 
#           '__le__', '__len__', '__lt__', '__module__', '__ne__', '__new__', '__post_init__', '__reduce__', '__reduce_ex__', '__repr__', '__reversed__', '__setattr__', 
#           '__setitem__', '__sizeof__', '__str__', '__subclasshook__', 'attentions', 'auxiliary_logits', 'class_queries_logits', 'clear', 'copy', 'encoder_hidden_states', 
#           'encoder_last_hidden_state', 'fromkeys', 'get', 'hidden_states', 'items', 'keys', 'loss', 'masks_queries_logits', 'move_to_end', 'pixel_decoder_hidden_states', 
#           'pixel_decoder_last_hidden_state', 'pop', 'popitem', 'setdefault', 'to_tuple', 'transformer_decoder_hidden_states', 'transformer_decoder_last_hidden_state', 
#           'update', 'values']

results = processor.post_process_panoptic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
# <class 'dict'>
# Keys: dict_keys(['segmentation', 'segments_info'])
# type(results["segments_info"]) --> list
# type(results["segmentation"]) --> <class 'torch.Tensor'>



# From Tutorial (Box 79)
# def get_mask(segment_idx):
#     segment = results['segments_info'][segment_idx]
#     print("Visualizing mask for:", id2label[segment['label_id']])
#     mask = (predicted_panoptic_seg == segment['id'])
#     visual_mask = (mask * 255).astype(np.uint8)
#     return Image.fromarray(visual_mask)

# How to get ID

"""
>>> model.config.id2label
{0: 'person', 1: 'bicycle', 2: 'car', 3: 'motorcycle', 4: 'airplane', 5: 'bus', 6: 'train', 7: 'truck', 8: 'boat', 9: 'traffic light', 10: 'fire hydrant', 11: 'stop sign', 12: 'parking meter', 
13: 'bench', 14: 'bird', 15: 'cat', 16: 'dog', 17: 'horse', 18: 'sheep', 19: 'cow', 20: 'elephant', 21: 'bear', 22: 'zebra', 23: 'giraffe', 24: 'backpack', 25: 'umbrella', 26: 'handbag', 
27: 'tie', 28: 'suitcase', 29: 'frisbee', 30: 'skis', 31: 'snowboard', 32: 'sports ball', 33: 'kite', 34: 'baseball bat', 35: 'baseball glove', 36: 'skateboard', 37: 'surfboard', 38: 'tennis racket', 
39: 'bottle', 40: 'wine glass', 41: 'cup', 42: 'fork', 43: 'knife', 44: 'spoon', 45: 'bowl', 46: 'banana', 47: 'apple', 48: 'sandwich', 49: 'orange', 50: 'broccoli', 51: 'carrot', 52: 'hot dog', 53: 'pizza', 
54: 'donut', 55: 'cake', 56: 'chair', 57: 'couch', 58: 'potted plant', 59: 'bed', 60: 'dining table', 61: 'toilet', 62: 'tv', 63: 'laptop', 64: 'mouse', 65: 'remote', 66: 'keyboard', 67: 'cell phone', 
68: 'microwave', 69: 'oven', 70: 'toaster', 71: 'sink', 72: 'refrigerator', 73: 'book', 74: 'clock', 75: 'vase', 76: 'scissors', 77: 'teddy bear', 78: 'hair drier', 79: 'toothbrush', 80: 'banner', 81: 'blanket', 
82: 'bridge', 83: 'cardboard', 84: 'counter', 85: 'curtain', 86: 'door-stuff', 87: 'floor-wood', 88: 'flower', 89: 'fruit', 90: 'gravel', 91: 'house', 92: 'light', 93: 'mirror-stuff', 94: 'net', 95: 'pillow', 
96: 'platform', 97: 'playingfield', 98: 'railroad', 99: 'river', 100: 'road', 101: 'roof', 102: 'sand', 103: 'sea', 104: 'shelf', 105: 'snow', 106: 'stairs', 107: 'tent', 108: 'towel', 109: 'wall-brick', 
110: 'wall-stone', 111: 'wall-tile', 112: 'wall-wood', 113: 'water-other', 114: 'window-blind', 115: 'window-other', 116: 'tree-merged', 117: 'fence-merged', 118: 'ceiling-merged', 119: 'sky-other-merged', 
120: 'cabinet-merged', 121: 'table-merged', 122: 'floor-other-merged', 123: 'pavement-merged', 124: 'mountain-merged', 125: 'grass-merged', 126: 'dirt-merged', 127: 'paper-merged', 128: 'food-other-merged', 
129: 'building-other-merged', 130: 'rock-merged', 131: 'wall-other-merged', 132: 'rug-merged'}
>>> model.config.id2label[123]
'pavement-merged'
>>> results["segments_info"][1]
{'id': 2, 'label_id': 123, 'was_fused': False, 'score': 0.995813}
""" 
# Above labels don't correspond to anything ... https://github.com/nightrome/cocostuff/blob/master/labels.md
# This one was closest to helping: https://github.com/NielsRogge/Transformers-Tutorials/blob/master/MaskFormer/Inference/Inference_with_MaskFormer_for_semantic_%2B_panoptic_segmentation.ipynb

"""
>>> Image.fromarray((mask * 255).cpu().numpy().astype(np.uint8))
<PIL.Image.Image image mode=L size=2000x1500 at 0x7F07773691C0>
>>> temp = Image.fromarray((mask * 255).cpu().numpy().astype(np.uint8))
"""

"""
>>> mask = (results["segmentation"].cpu().numpy == 4)
>>> mask = (results["segmentation"].cpu().numpy() == 4)
>>> mask
array([[False, False, False, ..., False, False, False],
       [False, False, False, ..., False, False, False],
       [False, False, False, ..., False, False, False],
       ...,
       [False, False, False, ..., False, False, False],
       [False, False, False, ..., False, False, False],
       [False, False, False, ..., False, False, False]])
>>> visual_mask = (mask * 255).astype(np.uint8)
>>> visual_mask = Image.fromarray(visual_mask)
>>> plt.imshow(visual_mask)
<matplotlib.image.AxesImage object at 0x7f0761e78040>
>>> plt.show()
"""

"""
>>> mask = (results["segmentation"].cpu().numpy() == 1)
>>> visual_mask = (mask*255).astype(np.uint8)
>>> visual_mask = Image.fromarray(visual_mask)
>>> plt.imshow(visual_mask)
<matplotlib.image.AxesImage object at 0x7f0760298550>
>>> plt.show()
>>> results["segments_info"][0]
{'id': 1, 'label_id': 25, 'was_fused': False, 'score': 0.998022}
>>> 
"""