File size: 16,284 Bytes
9724c61
 
 
 
 
9951234
 
 
9724c61
 
 
e4f0b1d
 
 
 
 
 
 
 
9724c61
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9951234
9724c61
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9951234
9724c61
9951234
 
9724c61
9951234
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9724c61
 
 
9951234
 
 
 
 
 
 
9724c61
9951234
9724c61
 
 
 
9951234
 
 
9724c61
 
 
 
 
 
9951234
9724c61
 
9951234
9724c61
9951234
 
 
9724c61
 
 
 
 
9951234
9724c61
 
 
 
9951234
9724c61
9951234
9724c61
 
 
 
 
9951234
 
 
9724c61
 
9951234
 
9724c61
9951234
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9724c61
 
 
 
 
9951234
 
9724c61
 
 
 
9951234
9724c61
 
 
 
9951234
9724c61
 
 
 
9951234
9724c61
9951234
 
 
 
9724c61
 
 
9951234
 
 
 
9724c61
9951234
 
9724c61
 
9951234
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9724c61
 
9951234
 
 
 
9724c61
 
 
 
 
 
 
9951234
 
9724c61
 
 
 
9951234
9724c61
 
 
 
 
 
 
 
9951234
9724c61
9951234
9724c61
9951234
 
9724c61
 
 
9951234
 
 
 
9724c61
 
9951234
 
9724c61
 
 
 
 
 
 
9951234
 
 
 
 
 
 
 
 
 
 
 
 
 
9724c61
9951234
 
9724c61
9951234
 
 
 
 
 
e4f0b1d
 
9951234
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9724c61
 
 
 
 
 
 
e4f0b1d
9724c61
 
 
e4f0b1d
9724c61
 
 
 
e4f0b1d
9724c61
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9951234
9724c61
 
 
 
 
 
 
 
4b45202
9724c61
 
4b45202
9724c61
 
 
9951234
4b45202
9951234
4b45202
9724c61
 
 
 
e4f0b1d
 
9951234
 
 
 
 
 
 
 
e4f0b1d
 
 
 
 
 
 
 
 
 
 
 
 
 
9951234
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
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
import numpy as np
from PIL import Image
import matplotlib.pyplot as plt
import cv2
import torch
import os
import sys
import clip


def convert_box_xywh_to_xyxy(box):
    if len(box) == 4:
        return [box[0], box[1], box[0] + box[2], box[1] + box[3]]
    else:
        result = []
        for b in box:
            b = convert_box_xywh_to_xyxy(b)
            result.append(b)               
    return result


def segment_image(image, bbox):
    image_array = np.array(image)
    segmented_image_array = np.zeros_like(image_array)
    x1, y1, x2, y2 = bbox
    segmented_image_array[y1:y2, x1:x2] = image_array[y1:y2, x1:x2]
    segmented_image = Image.fromarray(segmented_image_array)
    black_image = Image.new("RGB", image.size, (255, 255, 255))
    # transparency_mask = np.zeros_like((), dtype=np.uint8)
    transparency_mask = np.zeros(
        (image_array.shape[0], image_array.shape[1]), dtype=np.uint8
    )
    transparency_mask[y1:y2, x1:x2] = 255
    transparency_mask_image = Image.fromarray(transparency_mask, mode="L")
    black_image.paste(segmented_image, mask=transparency_mask_image)
    return black_image


def format_results(result, filter=0):
    annotations = []
    n = len(result.masks.data)
    for i in range(n):
        annotation = {}
        mask = result.masks.data[i] == 1.0

        if torch.sum(mask) < filter:
            continue
        annotation["id"] = i
        annotation["segmentation"] = mask.cpu().numpy()
        annotation["bbox"] = result.boxes.data[i]
        annotation["score"] = result.boxes.conf[i]
        annotation["area"] = annotation["segmentation"].sum()
        annotations.append(annotation)
    return annotations


def filter_masks(annotations):  # filter the overlap mask
    annotations.sort(key=lambda x: x["area"], reverse=True)
    to_remove = set()
    for i in range(0, len(annotations)):
        a = annotations[i]
        for j in range(i + 1, len(annotations)):
            b = annotations[j]
            if i != j and j not in to_remove:
                # check if
                if b["area"] < a["area"]:
                    if (a["segmentation"] & b["segmentation"]).sum() / b[
                        "segmentation"
                    ].sum() > 0.8:
                        to_remove.add(j)

    return [a for i, a in enumerate(annotations) if i not in to_remove], to_remove


def get_bbox_from_mask(mask):
    mask = mask.astype(np.uint8)
    contours, hierarchy = cv2.findContours(
        mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE
    )
    x1, y1, w, h = cv2.boundingRect(contours[0])
    x2, y2 = x1 + w, y1 + h
    if len(contours) > 1:
        for b in contours:
            x_t, y_t, w_t, h_t = cv2.boundingRect(b)
            # 将多个bbox合并成一个
            x1 = min(x1, x_t)
            y1 = min(y1, y_t)
            x2 = max(x2, x_t + w_t)
            y2 = max(y2, y_t + h_t)
        h = y2 - y1
        w = x2 - x1
    return [x1, y1, x2, y2]


def fast_process(

    annotations, args, mask_random_color, bbox=None, points=None, edges=False

):
    if isinstance(annotations[0], dict):
        annotations = [annotation["segmentation"] for annotation in annotations]
    result_name = os.path.basename(args.img_path)
    image = cv2.imread(args.img_path)
    image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
    original_h = image.shape[0]
    original_w = image.shape[1]
    if sys.platform == "darwin":
            plt.switch_backend("TkAgg")
    plt.figure(figsize=(original_w/100, original_h/100))
    # Add subplot with no margin.
    plt.subplots_adjust(top=1, bottom=0, right=1, left=0, hspace=0, wspace=0)
    plt.margins(0, 0)
    plt.gca().xaxis.set_major_locator(plt.NullLocator())
    plt.gca().yaxis.set_major_locator(plt.NullLocator())
    plt.imshow(image)
    if args.better_quality == True:
        if isinstance(annotations[0], torch.Tensor):
            annotations = np.array(annotations.cpu())
        for i, mask in enumerate(annotations):
            mask = cv2.morphologyEx(
                mask.astype(np.uint8), cv2.MORPH_CLOSE, np.ones((3, 3), np.uint8)
            )
            annotations[i] = cv2.morphologyEx(
                mask.astype(np.uint8), cv2.MORPH_OPEN, np.ones((8, 8), np.uint8)
            )
    if args.device == "cpu":
        annotations = np.array(annotations)
        fast_show_mask(
            annotations,
            plt.gca(),
            random_color=mask_random_color,
            bbox=bbox,
            points=points,
            point_label=args.point_label,
            retinamask=args.retina,
            target_height=original_h,
            target_width=original_w,
        )
    else:
        if isinstance(annotations[0], np.ndarray):
            annotations = torch.from_numpy(annotations)
        fast_show_mask_gpu(
            annotations,
            plt.gca(),
            random_color=args.randomcolor,
            bbox=bbox,
            points=points,
            point_label=args.point_label,
            retinamask=args.retina,
            target_height=original_h,
            target_width=original_w,
        )
    if isinstance(annotations, torch.Tensor):
        annotations = annotations.cpu().numpy()
    if args.withContours == True:
        contour_all = []
        temp = np.zeros((original_h, original_w, 1))
        for i, mask in enumerate(annotations):
            if type(mask) == dict:
                mask = mask["segmentation"]
            annotation = mask.astype(np.uint8)
            if args.retina == False:
                annotation = cv2.resize(
                    annotation,
                    (original_w, original_h),
                    interpolation=cv2.INTER_NEAREST,
                )
            contours, hierarchy = cv2.findContours(
                annotation, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE
            )
            for contour in contours:
                contour_all.append(contour)
        cv2.drawContours(temp, contour_all, -1, (255, 255, 255), 2)
        color = np.array([0 / 255, 0 / 255, 255 / 255, 0.8])
        contour_mask = temp / 255 * color.reshape(1, 1, -1)
        plt.imshow(contour_mask)

    save_path = args.output
    if not os.path.exists(save_path):
        os.makedirs(save_path)
    plt.axis("off")
    fig = plt.gcf()
    plt.draw()
    
    try:
        buf = fig.canvas.tostring_rgb()
    except AttributeError:
        fig.canvas.draw()
        buf = fig.canvas.tostring_rgb()
    
    cols, rows = fig.canvas.get_width_height()
    img_array = np.fromstring(buf, dtype=np.uint8).reshape(rows, cols, 3)
    cv2.imwrite(os.path.join(save_path, result_name), cv2.cvtColor(img_array, cv2.COLOR_RGB2BGR))


# CPU post process
def fast_show_mask(

    annotation,

    ax,

    random_color=False,

    bbox=None,

    points=None,

    point_label=None,

    retinamask=True,

    target_height=960,

    target_width=960,

):
    msak_sum = annotation.shape[0]
    height = annotation.shape[1]
    weight = annotation.shape[2]
    # 将annotation 按照面积 排序
    areas = np.sum(annotation, axis=(1, 2))
    sorted_indices = np.argsort(areas)
    annotation = annotation[sorted_indices]

    index = (annotation != 0).argmax(axis=0)
    if random_color == True:
        color = np.random.random((msak_sum, 1, 1, 3))
    else:
        color = np.ones((msak_sum, 1, 1, 3)) * np.array(
            [30 / 255, 144 / 255, 255 / 255]
        )
    transparency = np.ones((msak_sum, 1, 1, 1)) * 0.6
    visual = np.concatenate([color, transparency], axis=-1)
    mask_image = np.expand_dims(annotation, -1) * visual

    show = np.zeros((height, weight, 4))
    h_indices, w_indices = np.meshgrid(
        np.arange(height), np.arange(weight), indexing="ij"
    )
    indices = (index[h_indices, w_indices], h_indices, w_indices, slice(None))
    # 使用向量化索引更新show的值
    show[h_indices, w_indices, :] = mask_image[indices]
    if bbox is not None:
        x1, y1, x2, y2 = bbox
        ax.add_patch(
            plt.Rectangle(
                (x1, y1), x2 - x1, y2 - y1, fill=False, edgecolor="b", linewidth=1
            )
        )
    # draw point
    if points is not None:
        plt.scatter(
            [point[0] for i, point in enumerate(points) if point_label[i] == 1],
            [point[1] for i, point in enumerate(points) if point_label[i] == 1],
            s=20,
            c="y",
        )
        plt.scatter(
            [point[0] for i, point in enumerate(points) if point_label[i] == 0],
            [point[1] for i, point in enumerate(points) if point_label[i] == 0],
            s=20,
            c="m",
        )

    if retinamask == False:
        show = cv2.resize(
            show, (target_width, target_height), interpolation=cv2.INTER_NEAREST
        )
    ax.imshow(show)


def fast_show_mask_gpu(

    annotation,

    ax,

    random_color=False,

    bbox=None,

    points=None,

    point_label=None,

    retinamask=True,

    target_height=960,

    target_width=960,

):
    msak_sum = annotation.shape[0]
    height = annotation.shape[1]
    weight = annotation.shape[2]
    areas = torch.sum(annotation, dim=(1, 2))
    sorted_indices = torch.argsort(areas, descending=False)
    annotation = annotation[sorted_indices]
    # 找每个位置第一个非零值下标
    index = (annotation != 0).to(torch.long).argmax(dim=0)
    if random_color == True:
        color = torch.rand((msak_sum, 1, 1, 3)).to(annotation.device)
    else:
        color = torch.ones((msak_sum, 1, 1, 3)).to(annotation.device) * torch.tensor(
            [30 / 255, 144 / 255, 255 / 255]
        ).to(annotation.device)
    transparency = torch.ones((msak_sum, 1, 1, 1)).to(annotation.device) * 0.6
    visual = torch.cat([color, transparency], dim=-1)
    mask_image = torch.unsqueeze(annotation, -1) * visual
    # 按index取数,index指每个位置选哪个batch的数,把mask_image转成一个batch的形式
    show = torch.zeros((height, weight, 4)).to(annotation.device)
    h_indices, w_indices = torch.meshgrid(
        torch.arange(height), torch.arange(weight), indexing="ij"
    )
    indices = (index[h_indices, w_indices], h_indices, w_indices, slice(None))
    # 使用向量化索引更新show的值
    show[h_indices, w_indices, :] = mask_image[indices]
    show_cpu = show.cpu().numpy()
    if bbox is not None:
        x1, y1, x2, y2 = bbox
        ax.add_patch(
            plt.Rectangle(
                (x1, y1), x2 - x1, y2 - y1, fill=False, edgecolor="b", linewidth=1
            )
        )
    # draw point
    if points is not None:
        plt.scatter(
            [point[0] for i, point in enumerate(points) if point_label[i] == 1],
            [point[1] for i, point in enumerate(points) if point_label[i] == 1],
            s=20,
            c="y",
        )
        plt.scatter(
            [point[0] for i, point in enumerate(points) if point_label[i] == 0],
            [point[1] for i, point in enumerate(points) if point_label[i] == 0],
            s=20,
            c="m",
        )
    if retinamask == False:
        show_cpu = cv2.resize(
            show_cpu, (target_width, target_height), interpolation=cv2.INTER_NEAREST
        )
    ax.imshow(show_cpu)


# clip
@torch.no_grad()
def retriev(

    model, preprocess, elements: [Image.Image], search_text: str, device

):
    preprocessed_images = [preprocess(image).to(device) for image in elements]
    tokenized_text = clip.tokenize([search_text]).to(device)
    stacked_images = torch.stack(preprocessed_images)
    image_features = model.encode_image(stacked_images)
    text_features = model.encode_text(tokenized_text)
    image_features /= image_features.norm(dim=-1, keepdim=True)
    text_features /= text_features.norm(dim=-1, keepdim=True)
    probs = 100.0 * image_features @ text_features.T
    return probs[:, 0].softmax(dim=0)


def crop_image(annotations, image_like):
    if isinstance(image_like, str):
        image = Image.open(image_like)
    else:
        image = image_like
    ori_w, ori_h = image.size
    mask_h, mask_w = annotations[0]["segmentation"].shape
    if ori_w != mask_w or ori_h != mask_h:
        image = image.resize((mask_w, mask_h))
    cropped_boxes = []
    cropped_images = []
    not_crop = []
    origin_id = []
    for _, mask in enumerate(annotations):
        if np.sum(mask["segmentation"]) <= 100:
            continue
        origin_id.append(_)
        bbox = get_bbox_from_mask(mask["segmentation"])  # mask 的 bbox
        cropped_boxes.append(segment_image(image, bbox))  # 保存裁剪的图片
        # cropped_boxes.append(segment_image(image,mask["segmentation"]))
        cropped_images.append(bbox)  # 保存裁剪的图片的bbox
    return cropped_boxes, cropped_images, not_crop, origin_id, annotations


def box_prompt(masks, bbox, target_height, target_width):
    h = masks.shape[1]
    w = masks.shape[2]
    if h != target_height or w != target_width:
        bbox = [
            int(bbox[0] * w / target_width),
            int(bbox[1] * h / target_height),
            int(bbox[2] * w / target_width),
            int(bbox[3] * h / target_height),
        ]
    bbox[0] = round(bbox[0]) if round(bbox[0]) > 0 else 0
    bbox[1] = round(bbox[1]) if round(bbox[1]) > 0 else 0
    bbox[2] = round(bbox[2]) if round(bbox[2]) < w else w
    bbox[3] = round(bbox[3]) if round(bbox[3]) < h else h

    # IoUs = torch.zeros(len(masks), dtype=torch.float32)
    bbox_area = (bbox[3] - bbox[1]) * (bbox[2] - bbox[0])

    masks_area = torch.sum(masks[:, bbox[1] : bbox[3], bbox[0] : bbox[2]], dim=(1, 2))
    orig_masks_area = torch.sum(masks, dim=(1, 2))

    union = bbox_area + orig_masks_area - masks_area
    IoUs = masks_area / union
    max_iou_index = torch.argmax(IoUs)

    return masks[max_iou_index].cpu().numpy(), max_iou_index


def point_prompt(masks, points, point_label, target_height, target_width):  # numpy 处理
    h = masks[0]["segmentation"].shape[0]
    w = masks[0]["segmentation"].shape[1]
    if h != target_height or w != target_width:
        points = [
            [int(point[0] * w / target_width), int(point[1] * h / target_height)]
            for point in points
        ]
    onemask = np.zeros((h, w))
    masks = sorted(masks, key=lambda x: x['area'], reverse=True)
    for i, annotation in enumerate(masks):
        if type(annotation) == dict:
            mask = annotation['segmentation']
        else:
            mask = annotation
        for i, point in enumerate(points):
            if mask[point[1], point[0]] == 1 and point_label[i] == 1:
                onemask[mask] = 1
            if mask[point[1], point[0]] == 1 and point_label[i] == 0:
                onemask[mask] = 0
    onemask = onemask >= 1
    return onemask, 0


def text_prompt(annotations, text, img_path, device, wider=False, threshold=0.9):
    cropped_boxes, cropped_images, not_crop, origin_id, annotations_ = crop_image(
        annotations, img_path
    )
    clip_model, preprocess = clip.load("./weights/CLIP_ViT_B_32.pt", device=device)
    scores = retriev(
        clip_model, preprocess, cropped_boxes, text, device=device
    )
    max_idx = scores.argsort()
    max_idx = max_idx[-1]
    max_idx = origin_id[int(max_idx)]

    # find the biggest mask which contains the mask with max score
    if wider:
        mask0 = annotations_[max_idx]["segmentation"]
        area0 = np.sum(mask0)
        areas = [(i, np.sum(mask["segmentation"])) for i, mask in enumerate(annotations_) if i in origin_id]
        areas = sorted(areas, key=lambda area: area[1], reverse=True)
        indices = [area[0] for area in areas]
        for index in indices:
            if index == max_idx or np.sum(annotations_[index]["segmentation"] & mask0) / area0 > threshold:
                max_idx = index
                break

    return annotations_[max_idx]["segmentation"], max_idx