File size: 6,826 Bytes
c9019cd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import os.path as osp
import pickle
import shutil
import tempfile
import time

import mmcv
import torch
import torch.distributed as dist
from mmcv.image import tensor2imgs
from mmcv.runner import get_dist_info

from mmdet.core import encode_mask_results


def single_gpu_test(model,
                    data_loader,
                    show=False,
                    out_dir=None,
                    show_score_thr=0.3):
    model.eval()
    results = []
    dataset = data_loader.dataset
    prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)

        batch_size = len(result)
        if show or out_dir:
            if batch_size == 1 and isinstance(data['img'][0], torch.Tensor):
                img_tensor = data['img'][0]
            else:
                img_tensor = data['img'][0].data[0]
            img_metas = data['img_metas'][0].data[0]
            imgs = tensor2imgs(img_tensor, **img_metas[0]['img_norm_cfg'])
            assert len(imgs) == len(img_metas)

            for i, (img, img_meta) in enumerate(zip(imgs, img_metas)):
                h, w, _ = img_meta['img_shape']
                img_show = img[:h, :w, :]

                ori_h, ori_w = img_meta['ori_shape'][:-1]
                img_show = mmcv.imresize(img_show, (ori_w, ori_h))

                if out_dir:
                    out_file = osp.join(out_dir, img_meta['ori_filename'])
                else:
                    out_file = None

                model.module.show_result(
                    img_show,
                    result[i],
                    show=show,
                    out_file=out_file,
                    score_thr=show_score_thr)

        # encode mask results
        if isinstance(result[0], tuple):
            result = [(bbox_results, encode_mask_results(mask_results))
                      for bbox_results, mask_results in result]
        results.extend(result)

        for _ in range(batch_size):
            prog_bar.update()
    return results


def multi_gpu_test(model, data_loader, tmpdir=None, gpu_collect=False):
    """Test model with multiple gpus.

    This method tests model with multiple gpus and collects the results
    under two different modes: gpu and cpu modes. By setting 'gpu_collect=True'
    it encodes results to gpu tensors and use gpu communication for results
    collection. On cpu mode it saves the results on different gpus to 'tmpdir'
    and collects them by the rank 0 worker.

    Args:
        model (nn.Module): Model to be tested.
        data_loader (nn.Dataloader): Pytorch data loader.
        tmpdir (str): Path of directory to save the temporary results from
            different gpus under cpu mode.
        gpu_collect (bool): Option to use either gpu or cpu to collect results.

    Returns:
        list: The prediction results.
    """
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    time.sleep(2)  # This line can prevent deadlock problem in some cases.
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
            # encode mask results
            if isinstance(result[0], tuple):
                result = [(bbox_results, encode_mask_results(mask_results))
                          for bbox_results, mask_results in result]
        results.extend(result)

        if rank == 0:
            batch_size = len(result)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    if gpu_collect:
        results = collect_results_gpu(results, len(dataset))
    else:
        results = collect_results_cpu(results, len(dataset), tmpdir)
    return results


def collect_results_cpu(result_part, size, tmpdir=None):
    rank, world_size = get_dist_info()
    # create a tmp dir if it is not specified
    if tmpdir is None:
        MAX_LEN = 512
        # 32 is whitespace
        dir_tensor = torch.full((MAX_LEN, ),
                                32,
                                dtype=torch.uint8,
                                device='cuda')
        if rank == 0:
            mmcv.mkdir_or_exist('.dist_test')
            tmpdir = tempfile.mkdtemp(dir='.dist_test')
            tmpdir = torch.tensor(
                bytearray(tmpdir.encode()), dtype=torch.uint8, device='cuda')
            dir_tensor[:len(tmpdir)] = tmpdir
        dist.broadcast(dir_tensor, 0)
        tmpdir = dir_tensor.cpu().numpy().tobytes().decode().rstrip()
    else:
        mmcv.mkdir_or_exist(tmpdir)
    # dump the part result to the dir
    mmcv.dump(result_part, osp.join(tmpdir, f'part_{rank}.pkl'))
    dist.barrier()
    # collect all parts
    if rank != 0:
        return None
    else:
        # load results of all parts from tmp dir
        part_list = []
        for i in range(world_size):
            part_file = osp.join(tmpdir, f'part_{i}.pkl')
            part_list.append(mmcv.load(part_file))
        # sort the results
        ordered_results = []
        for res in zip(*part_list):
            ordered_results.extend(list(res))
        # the dataloader may pad some samples
        ordered_results = ordered_results[:size]
        # remove tmp dir
        shutil.rmtree(tmpdir)
        return ordered_results


def collect_results_gpu(result_part, size):
    rank, world_size = get_dist_info()
    # dump result part to tensor with pickle
    part_tensor = torch.tensor(
        bytearray(pickle.dumps(result_part)), dtype=torch.uint8, device='cuda')
    # gather all result part tensor shape
    shape_tensor = torch.tensor(part_tensor.shape, device='cuda')
    shape_list = [shape_tensor.clone() for _ in range(world_size)]
    dist.all_gather(shape_list, shape_tensor)
    # padding result part tensor to max length
    shape_max = torch.tensor(shape_list).max()
    part_send = torch.zeros(shape_max, dtype=torch.uint8, device='cuda')
    part_send[:shape_tensor[0]] = part_tensor
    part_recv_list = [
        part_tensor.new_zeros(shape_max) for _ in range(world_size)
    ]
    # gather all result part
    dist.all_gather(part_recv_list, part_send)

    if rank == 0:
        part_list = []
        for recv, shape in zip(part_recv_list, shape_list):
            part_list.append(
                pickle.loads(recv[:shape[0]].cpu().numpy().tobytes()))
        # sort the results
        ordered_results = []
        for res in zip(*part_list):
            ordered_results.extend(list(res))
        # the dataloader may pad some samples
        ordered_results = ordered_results[:size]
        return ordered_results