-
Notifications
You must be signed in to change notification settings - Fork 0
/
transforms.py
302 lines (255 loc) · 10.7 KB
/
transforms.py
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
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
import numpy as np
import oneflow as flow
import flowvision
from oneflow import nn, Tensor
from flowvision.transforms import functional as F
from flowvision.transforms import transforms as T
from typing import List, Tuple, Dict, Optional
def _flip_coco_person_keypoints(kps, width):
flip_inds = [0, 2, 1, 4, 3, 6, 5, 8, 7, 10, 9, 12, 11, 14, 13, 16, 15]
flipped_data = kps[:, flip_inds]
flipped_data[..., 0] = width - flipped_data[..., 0]
# Maintain COCO convention that if visibility == 0, then x, y = 0
inds = flipped_data[..., 2] == 0
flipped_data[inds] = 0
return flipped_data
class Compose:
def __init__(self, transforms):
self.transforms = transforms
def __call__(self, image, target):
for t in self.transforms:
image, target = t(image, target)
return image, target
class RandomHorizontalFlip(T.RandomHorizontalFlip):
def forward(
self, image: Tensor, target: Optional[Dict[str, Tensor]] = None
) -> Tuple[Tensor, Optional[Dict[str, Tensor]]]:
if flow.rand(1) < self.p:
image = F.hflip(image)
if target is not None:
width, _ = F._get_image_size(image)
# TODO (shijie wang): support setitem combining index.
# target["boxes"][:, [0, 2]] = width - target["boxes"][:, [2, 0]]
temp = target["boxes"].clone()
target["boxes"][:, 0] = width - temp[:, 2]
target["boxes"][:, 2] = width - temp[:, 0]
if "masks" in target:
target["masks"] = target["masks"].flip(-1)
if "keypoints" in target:
keypoints = target["keypoints"]
keypoints = _flip_coco_person_keypoints(keypoints, width)
target["keypoints"] = keypoints
return image, target
class ToTensor(nn.Module):
def forward(
self, image: Tensor, target: Optional[Dict[str, Tensor]] = None
) -> Tuple[Tensor, Optional[Dict[str, Tensor]]]:
image = F.pil_to_tensor(image)
image = F.convert_image_dtype(image)
return image, target
class RandomIoUCrop(nn.Module):
def __init__(
self,
min_scale: float = 0.3,
max_scale: float = 1.0,
min_aspect_ratio: float = 0.5,
max_aspect_ratio: float = 2.0,
sampler_options: Optional[List[float]] = None,
trials: int = 40,
):
super().__init__()
self.min_scale = min_scale
self.max_scale = max_scale
self.min_aspect_ratio = min_aspect_ratio
self.max_aspect_ratio = max_aspect_ratio
if sampler_options is None:
sampler_options = [0.0, 0.1, 0.3, 0.5, 0.7, 0.9, 1.0]
self.options = sampler_options
self.trials = trials
def forward(
self, image: Tensor, target: Optional[Dict[str, Tensor]] = None
) -> Tuple[Tensor, Optional[Dict[str, Tensor]]]:
if target is None:
raise ValueError("The targets can't be None for this transform.")
if isinstance(image, flow.Tensor):
if image.ndimension() not in {2, 3}:
raise ValueError(
"image should be 2/3 dimensional. Got {} dimensions.".format(
image.ndimension()
)
)
elif image.ndimension() == 2:
image = image.unsqueeze(0)
orig_w, orig_h = F._get_image_size(image)
boxes_np = target["boxes"].numpy()
while True:
# sample on option
idx = int(np.random.randint(low=0, high=len(self.options), size=(1,)))
min_jaccard_overlap = self.options[idx]
if (
min_jaccard_overlap >= 1.0
): # a value larger than 1 encodes the leave as-is option
return image, target
for _ in range(self.trials):
# check the aspect ratio limitations
r = self.min_scale + (self.max_scale - self.min_scale) * np.random.rand(
2
)
new_w = int(orig_w * r[0])
new_h = int(orig_h * r[1])
aspect_ratio = new_w / new_h
if not (self.min_aspect_ratio <= aspect_ratio <= self.max_aspect_ratio):
continue
# check for 0 area crops
r = np.random.rand(2)
left = int((orig_w - new_w) * r[0])
top = int((orig_h - new_h) * r[1])
right = left + new_w
bottom = top + new_h
if left == right or top == bottom:
continue
# check for any valid boxes with centers within the crop area
# cx = 0.5 * (boxes_flow[:, 0] + boxes_flow[:, 2])
# cy = 0.5 * (boxes_flow[:, 1] + boxes_flow[:, 3])
cx = 0.5 * (boxes_np[:, 0] + boxes_np[:, 2])
cy = 0.5 * (boxes_np[:, 1] + boxes_np[:, 3])
is_within_crop_area = (
(left < cx) & (cx < right) & (top < cy) & (cy < bottom)
)
if not is_within_crop_area.any():
continue
# check at least 1 box with jaccard limitations
boxes = boxes_np[is_within_crop_area]
ious = flowvision.layers.blocks.box_iou_np(
boxes, np.array([[left, top, right, bottom]], dtype=np.float32,)
)
# boxes = targets["boxes"][is_within_crop_area]
# ious = flowvision.layers.blocks.box_iou(
# boxes,
# flow.tensor(
# [[left, top, right, bottom]],
# dtype=boxes.dtype,
# device=boxes.device,
# ),
# )
if ious.max() < min_jaccard_overlap:
continue
# keep only valid boxes and perform cropping
target["boxes"] = flow.tensor(boxes)
target["labels"] = target["labels"][flow.tensor(is_within_crop_area)]
target["boxes"][:, 0::2] -= left
target["boxes"][:, 1::2] -= top
target["boxes"][:, 0::2].clamp(min=0, max=new_w)
target["boxes"][:, 1::2].clamp(min=0, max=new_h)
image = F.crop(image, top, left, new_h, new_w)
return image, target
class RandomZoomOut(nn.Module):
def __init__(
self,
fill: Optional[List[float]] = None,
side_range: Tuple[float, float] = (1.0, 4.0),
p: float = 0.5,
):
super().__init__()
if fill is None:
fill = [0.0, 0.0, 0.0]
self.fill = fill
self.side_range = side_range
if side_range[0] < 1.0 or side_range[0] > side_range[1]:
raise ValueError(
"Invalid canvas side range provided {}.".format(side_range)
)
self.p = p
def _get_fill_value(self, is_pil):
# type: (bool) -> int
return tuple(int(x) for x in self.fill) if is_pil else 0
def forward(
self, image: Tensor, target: Optional[Dict[str, Tensor]] = None
) -> Tuple[Tensor, Optional[Dict[str, Tensor]]]:
if isinstance(image, flow.Tensor):
if image.ndimension() not in {2, 3}:
raise ValueError(
"image should be 2/3 dimensional. Got {} dimensions.".format(
image.ndimension()
)
)
elif image.ndimension() == 2:
image = image.unsqueeze(0)
if flow.rand(1) < self.p:
return image, target
orig_w, orig_h = F._get_image_size(image)
r = self.side_range[0] + flow.rand(1) * (
self.side_range[1] - self.side_range[0]
)
canvas_width = int((orig_w * r).item())
canvas_height = int((orig_h * r).item())
r = flow.rand(2)
left = int(((canvas_width - orig_w) * r[0]).item())
top = int(((canvas_height - orig_h) * r[1]).item())
right = canvas_width - (left + orig_w)
bottom = canvas_height - (top + orig_h)
fill = self._get_fill_value(F._is_pil_image(image))
image = F.pad(image, [left, top, right, bottom], fill=fill)
if isinstance(image, flow.Tensor):
v = flow.tensor(self.fill, device=image.device, dtype=image.dtype).view(
-1, 1, 1
)
image[..., :top, :] = image[..., :, :left] = image[
..., (top + orig_h) :, :
] = image[..., :, (left + orig_w) :] = v
if target is not None:
target["boxes"][:, 0::2] += left
target["boxes"][:, 1::2] += top
return image, target
class RandomPhotometricDistort(nn.Module):
def __init__(
self,
contrast: Tuple[float] = (0.5, 1.5),
saturation: Tuple[float] = (0.5, 1.5),
hue: Tuple[float] = (-0.05, 0.05),
brightness: Tuple[float] = (0.875, 1.125),
p: float = 0.5,
):
super().__init__()
self._brightness = T.ColorJitter(brightness=brightness)
self._contrast = T.ColorJitter(contrast=contrast)
self._hue = T.ColorJitter(hue=hue)
self._saturation = T.ColorJitter(saturation=saturation)
self.p = p
def forward(
self, image: Tensor, target: Optional[Dict[str, Tensor]] = None
) -> Tuple[Tensor, Optional[Dict[str, Tensor]]]:
if isinstance(image, flow.Tensor):
if image.ndimension() not in (2, 3):
raise ValueError(
"image should be 2/3 dimensional. Got {} dimensions.".format(
image.ndimension()
)
)
elif image.ndimension() == 2:
image = image.unsqueeze(0)
r = flow.rand(7)
if r[0] < self.p:
image = self._brightness(image)
contrast_before = r[1] < 0.5
if contrast_before:
if r[2] < self.p:
image = self._contrast(image)
if r[3] < self.p:
image = self._saturation(image)
if r[4] < self.p:
image = self._hue(image)
if not contrast_before:
if r[5] < self.p:
image = self._contrast(image)
if r[6] < self.p:
channels = F._get_image_num_channels(image)
permutation = flow.randperm(channels)
is_pil = F._is_pil_image(image)
if is_pil:
image = F.pil_to_tensor(image)
image = F.convert_image_dtype(image)
image = image[..., permutation, :, :]
if is_pil:
image = F.to_pil_image(image)
return image, target