[feature] Add image_demo.py & get_flops.py (#22)

.gitignore

+
+.idea/
+
+.DS_Store

detection/get_flops.py

+# Copyright (c) OpenMMLab. All rights reserved.
+import argparse
+
+import numpy as np
+import torch
+from mmcv import Config, DictAction
+
+from mmdet.models import build_detector
+import mmcv_custom  # noqa: F401,F403
+import mmdet_custom  # noqa: F401,F403
+
+try:
+    from mmcv.cnn.utils.flops_counter import flops_to_string, params_to_string
+    from mmcv.cnn import get_model_complexity_info
+except ImportError:
+    raise ImportError('Please upgrade mmcv to >0.6.2')
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(description='Train a detector')
+    parser.add_argument('config', help='train config file path')
+    parser.add_argument(
+        '--shape',
+        type=int,
+        nargs='+',
+        default=[800, 1280],
+        help='input image size')
+    parser.add_argument(
+        '--cfg-options',
+        nargs='+',
+        action=DictAction,
+        help='override some settings in the used config, the key-value pair '
+             'in xxx=yyy format will be merged into config file. If the value to '
+             'be overwritten is a list, it should be like key="[a,b]" or key=a,b '
+             'It also allows nested list/tuple values, e.g. key="[(a,b),(c,d)]" '
+             'Note that the quotation marks are necessary and that no white space '
+             'is allowed.')
+    parser.add_argument(
+        '--size-divisor',
+        type=int,
+        default=32,
+        help='Pad the input image, the minimum size that is divisible '
+             'by size_divisor, -1 means do not pad the image.')
+    args = parser.parse_args()
+    return args
+
+
+def dcnv3_flops(n, k, c):
+    return 5 * n * k * c
+
+
+def get_flops(model, input_shape):
+    flops, params = get_model_complexity_info(model, input_shape, as_strings=False)
+    
+    backbone = model.backbone
+    backbone_name = type(backbone).__name__
+    _, H, W = input_shape
+    
+    temp = 0
+    if 'InternImage' in backbone_name:
+        depths = backbone.depths  # [4, 4, 18, 4]
+        for idx, depth in enumerate(depths):
+            channels = backbone.channels * (2 ** idx)
+            h = H / (4 * (2 ** idx))
+            w = W / (4 * (2 ** idx))
+            temp += depth * dcnv3_flops(n=h * w, k=3 * 3, c=channels)
+    
+    flops = flops + temp
+    return flops_to_string(flops), params_to_string(params)
+
+
+if __name__ == '__main__':
+    
+    args = parse_args()
+    
+    if len(args.shape) == 1:
+        h = w = args.shape[0]
+    elif len(args.shape) == 2:
+        h, w = args.shape
+    else:
+        raise ValueError('invalid input shape')
+    orig_shape = (3, h, w)
+    divisor = args.size_divisor
+    if divisor > 0:
+        h = int(np.ceil(h / divisor)) * divisor
+        w = int(np.ceil(w / divisor)) * divisor
+    
+    input_shape = (3, h, w)
+    
+    cfg = Config.fromfile(args.config)
+    if args.cfg_options is not None:
+        cfg.merge_from_dict(args.cfg_options)
+    
+    model = build_detector(
+        cfg.model,
+        train_cfg=cfg.get('train_cfg'),
+        test_cfg=cfg.get('test_cfg'))
+    
+    if torch.cuda.is_available():
+        model.cuda()
+    model.eval()
+    if hasattr(model, 'forward_dummy'):
+        model.forward = model.forward_dummy
+    else:
+        raise NotImplementedError(
+            'FLOPs counter is currently not currently supported with {}'.
+                format(model.__class__.__name__))
+    
+    flops, params = get_flops(model, input_shape)
+    split_line = '=' * 30
+    
+    if divisor > 0 and \
+            input_shape != orig_shape:
+        print(f'{split_line}\nUse size divisor set input shape '
+              f'from {orig_shape} to {input_shape}\n')
+    print(f'{split_line}\nInput shape: {input_shape}\n'
+          f'Flops: {flops}\nParams: {params}\n{split_line}')
+    print('!!!Please be cautious if you use the results in papers. '
+          'You may need to check if all ops are supported and verify that the '
+          'flops computation is correct.')

detection/image_demo.py

+# Copyright (c) OpenMMLab. All rights reserved.
+import asyncio
+from argparse import ArgumentParser
+
+from mmdet.apis import (async_inference_detector, inference_detector,
+                        init_detector, show_result_pyplot)
+import mmcv
+import mmcv_custom  # noqa: F401,F403
+import mmdet_custom  # noqa: F401,F403
+import os.path as osp
+
+
+def parse_args():
+    parser = ArgumentParser()
+    parser.add_argument('img', help='Image file')
+    parser.add_argument('config', help='Config file')
+    parser.add_argument('checkpoint', help='Checkpoint file')
+    parser.add_argument('--out', type=str, default="demo", help='out dir')
+    parser.add_argument(
+        '--device', default='cuda:0', help='Device used for inference')
+    parser.add_argument(
+        '--palette',
+        default='coco',
+        choices=['coco', 'voc', 'citys', 'random'],
+        help='Color palette used for visualization')
+    parser.add_argument(
+        '--score-thr', type=float, default=0.3, help='bbox score threshold')
+    parser.add_argument(
+        '--async-test',
+        action='store_true',
+        help='whether to set async options for async inference.')
+    args = parser.parse_args()
+    return args
+
+
+def main(args):
+    # build the model from a config file and a checkpoint file
+    model = init_detector(args.config, args.checkpoint, device=args.device)
+    # test a single image
+    result = inference_detector(model, args.img)
+    
+    mmcv.mkdir_or_exist(args.out)
+    out_file = osp.join(args.out, osp.basename(args.img))
+    # show the results
+    model.show_result(
+        args.img,
+        result,
+        score_thr=args.score_thr,
+        show=False,
+        bbox_color=args.palette,
+        text_color=(200, 200, 200),
+        mask_color=args.palette,
+        out_file=out_file
+    )
+    print(f"Result is save at {out_file}")
+
+
+
+if __name__ == '__main__':
+    args = parse_args()
+    main(args)
\ No newline at end of file

segmentation/get_flops.py

+# Copyright (c) OpenMMLab. All rights reserved.
+import argparse
+
+import numpy as np
+import torch
+from mmcv import Config, DictAction
+
+from mmseg.models import build_segmentor
+import mmcv_custom   # noqa: F401,F403
+import mmseg_custom   # noqa: F401,F403
+
+try:
+    from mmcv.cnn.utils.flops_counter import flops_to_string, params_to_string
+    from mmcv.cnn import get_model_complexity_info
+except ImportError:
+    raise ImportError('Please upgrade mmcv to >0.6.2')
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(description='Train a detector')
+    parser.add_argument('config', help='train config file path')
+    parser.add_argument(
+        '--shape',
+        type=int,
+        nargs='+',
+        default=[512, 2048],
+        help='input image size')
+    parser.add_argument(
+        '--cfg-options',
+        nargs='+',
+        action=DictAction,
+        help='override some settings in the used config, the key-value pair '
+        'in xxx=yyy format will be merged into config file. If the value to '
+        'be overwritten is a list, it should be like key="[a,b]" or key=a,b '
+        'It also allows nested list/tuple values, e.g. key="[(a,b),(c,d)]" '
+        'Note that the quotation marks are necessary and that no white space '
+        'is allowed.')
+    parser.add_argument(
+        '--size-divisor',
+        type=int,
+        default=32,
+        help='Pad the input image, the minimum size that is divisible '
+        'by size_divisor, -1 means do not pad the image.')
+    args = parser.parse_args()
+    return args
+
+def dcnv3_flops(n, k, c):
+    return 5 * n * k * c
+
+def get_flops(model, input_shape):
+    flops, params = get_model_complexity_info(model, input_shape, as_strings=False)
+
+    backbone = model.backbone
+    backbone_name = type(backbone).__name__
+    _, H, W = input_shape
+
+    temp = 0
+    if 'InternImage' in backbone_name:
+        depths = backbone.depths # [4, 4, 18, 4]
+        for idx, depth in enumerate(depths):
+            channels = backbone.channels * (2 ** idx)
+            h = H / (4 * (2 ** idx))
+            w = W / (4 * (2 ** idx))
+            temp += depth * dcnv3_flops(n=h*w, k=3*3, c=channels)
+
+    flops = flops + temp
+    return flops_to_string(flops), params_to_string(params)
+
+    
+if __name__ == '__main__':
+
+    args = parse_args()
+
+    if len(args.shape) == 1:
+        h = w = args.shape[0]
+    elif len(args.shape) == 2:
+        h, w = args.shape
+    else:
+        raise ValueError('invalid input shape')
+    orig_shape = (3, h, w)
+    divisor = args.size_divisor
+    if divisor > 0:
+        h = int(np.ceil(h / divisor)) * divisor
+        w = int(np.ceil(w / divisor)) * divisor
+
+    input_shape = (3, h, w)
+
+    cfg = Config.fromfile(args.config)
+    if args.cfg_options is not None:
+        cfg.merge_from_dict(args.cfg_options)
+
+    model = build_segmentor(
+        cfg.model,
+        train_cfg=cfg.get('train_cfg'),
+        test_cfg=cfg.get('test_cfg'))
+    
+    if torch.cuda.is_available():
+        model.cuda()
+    model.eval()
+    if hasattr(model, 'forward_dummy'):
+        model.forward = model.forward_dummy
+    else:
+        raise NotImplementedError(
+            'FLOPs counter is currently not currently supported with {}'.
+            format(model.__class__.__name__))
+
+    flops, params = get_flops(model, input_shape)
+    split_line = '=' * 30
+
+    if divisor > 0 and \
+            input_shape != orig_shape:
+        print(f'{split_line}\nUse size divisor set input shape '
+              f'from {orig_shape} to {input_shape}\n')
+    print(f'{split_line}\nInput shape: {input_shape}\n'
+          f'Flops: {flops}\nParams: {params}\n{split_line}')
+    print('!!!Please be cautious if you use the results in papers. '
+          'You may need to check if all ops are supported and verify that the '
+          'flops computation is correct.')

segmentation/image_demo.py

+# Copyright (c) OpenMMLab. All rights reserved.
+from argparse import ArgumentParser
+
+import mmcv
+
+import mmcv_custom   # noqa: F401,F403
+import mmseg_custom   # noqa: F401,F403
+from mmseg.apis import inference_segmentor, init_segmentor, show_result_pyplot
+from mmseg.core.evaluation import get_palette
+from mmcv.runner import load_checkpoint
+from mmseg.core import get_classes
+import cv2
+import os.path as osp
+
+
+def main():
+    parser = ArgumentParser()
+    parser.add_argument('img', help='Image file')
+    parser.add_argument('config', help='Config file')
+    parser.add_argument('checkpoint', help='Checkpoint file')
+    parser.add_argument('--out', type=str, default="demo", help='out dir')
+    parser.add_argument(
+        '--device', default='cuda:0', help='Device used for inference')
+    parser.add_argument(
+        '--palette',
+        default='ade20k',
+        choices=['ade20k', 'cityscapes', 'cocostuff'],
+        help='Color palette used for segmentation map')
+    parser.add_argument(
+        '--opacity',
+        type=float,
+        default=0.5,
+        help='Opacity of painted segmentation map. In (0, 1] range.')
+    args = parser.parse_args()
+
+    # build the model from a config file and a checkpoint file
+    
+    model = init_segmentor(args.config, checkpoint=None, device=args.device)
+    checkpoint = load_checkpoint(model, args.checkpoint, map_location='cpu')
+    if 'CLASSES' in checkpoint.get('meta', {}):
+        model.CLASSES = checkpoint['meta']['CLASSES']
+    else:
+        model.CLASSES = get_classes(args.palette)
+        
+    # test a single image
+    result = inference_segmentor(model, args.img)
+    # show the results
+    if hasattr(model, 'module'):
+        model = model.module
+    img = model.show_result(args.img, result,
+                            palette=get_palette(args.palette),
+                            show=False, opacity=args.opacity)
+    mmcv.mkdir_or_exist(args.out)
+    out_path = osp.join(args.out, osp.basename(args.img))
+    cv2.imwrite(out_path, img)
+    print(f"Result is save at {out_path}")
+
+if __name__ == '__main__':
+    main()
\ No newline at end of file