add refined tsn model

dygraph/tsn/data/dataset/kinetics400/build_kinetics400_file_list.py

-import argparse
-import os
-import glob
-import fnmatch
-import random
-
-
-def parse_directory(path,
-                    key_func=lambda x: x[-11:],
-                    rgb_prefix='img_',
-                    level=1):
-    """
-    Parse directories holding extracted frames from standard benchmarks
-    """
-    print('parse frames under folder {}'.format(path))
-    if level == 1:
-        frame_folders = glob.glob(os.path.join(path, '*'))
-    elif level == 2:
-        frame_folders = glob.glob(os.path.join(path, '*', '*'))
-    else:
-        raise ValueError('level can be only 1 or 2')
-
-    def count_files(directory, prefix_list):
-        lst = os.listdir(directory)
-        cnt_list = [len(fnmatch.filter(lst, x + '*')) for x in prefix_list]
-        return cnt_list
-
-    # check RGB
-    frame_dict = {}
-    for i, f in enumerate(frame_folders):
-        all_cnt = count_files(f, (rgb_prefix))
-        k = key_func(f)
-
-        x_cnt = all_cnt[1]
-        y_cnt = all_cnt[2]
-        if x_cnt != y_cnt:
-            raise ValueError('x and y direction have different number '
-                             'of flow images. video: ' + f)
-        if i % 200 == 0:
-            print('{} videos parsed'.format(i))
-
-        frame_dict[k] = (f, all_cnt[0], x_cnt)
-
-    print('frame folder analysis done')
-    return frame_dict
-
-
-def build_split_list(split, frame_info, shuffle=False):
-    def build_set_list(set_list):
-        rgb_list = list()
-        for item in set_list:
-            if item[0] not in frame_info:
-                # print("item:", item)
-                continue
-            elif frame_info[item[0]][1] > 0:
-                rgb_cnt = frame_info[item[0]][1]
-                rgb_list.append('{} {} {}\n'.format(item[0], rgb_cnt, item[1]))
-            else:
-                rgb_list.append('{} {}\n'.format(item[0], item[1]))
-        if shuffle:
-            random.shuffle(rgb_list)
-        return rgb_list
-
-    train_rgb_list = build_set_list(split[0])
-    test_rgb_list = build_set_list(split[1])
-    return (train_rgb_list, test_rgb_list)
-
-
-def parse_ucf101_splits(level):
-    class_ind = [x.strip().split() for x in open('./annotations/classInd.txt')]
-    class_mapping = {x[1]: int(x[0]) - 1 for x in class_ind}
-
-    def line2rec(line):
-        items = line.strip().split(' ')
-        vid = items[0].split('.')[0]
-        vid = '/'.join(vid.split('/')[-level:])
-        label = class_mapping[items[0].split('/')[0]]
-        return vid, label
-
-    splits = []
-    for i in range(1, 4):
-        train_list = [
-            line2rec(x)
-            for x in open('./annotations/trainlist{:02d}.txt'.format(i))
-        ]
-        test_list = [
-            line2rec(x)
-            for x in open('./annotations/testlist{:02d}.txt'.format(i))
-        ]
-        splits.append((train_list, test_list))
-    return splits
-
-
-def parse_args():
-    parser = argparse.ArgumentParser(description='Build file list')
-    parser.add_argument(
-        'frame_path', type=str, help='root directory for the frames')
-    parser.add_argument('--rgb_prefix', type=str, default='img_')
-    parser.add_argument('--num_split', type=int, default=3)
-    parser.add_argument(
-        '--subset', type=str, default='train',
-        choices=['train', 'val', 'test'])
-    parser.add_argument('--level', type=int, default=2, choices=[1, 2])
-    parser.add_argument(
-        '--format',
-        type=str,
-        default='rawframes',
-        choices=['rawframes', 'videos'])
-    parser.add_argument('--out_list_path', type=str, default='./')
-    parser.add_argument('--shuffle', action='store_true', default=False)
-    args = parser.parse_args()
-
-    return args
-
-
-def main():
-    args = parse_args()
-
-    if args.level == 2:
-
-        def key_func(x):
-            return '/'.join(x.split('/')[-2:])
-    else:
-
-        def key_func(x):
-            return x.split('/')[-1]
-
-    if args.format == 'rawframes':
-        frame_info = parse_directory(
-            args.frame_path,
-            key_func=key_func,
-            rgb_prefix=args.rgb_prefix,
-            level=args.level)
-    elif args.format == 'videos':
-        if args.level == 1:
-            video_list = glob.glob(os.path.join(args.frame_path, '*'))
-        elif args.level == 2:
-            video_list = glob.glob(os.path.join(args.frame_path, '*', '*'))
-        frame_info = {
-            os.path.relpath(x.split('.')[0], args.frame_path): (x, -1, -1)
-            for x in video_list
-        }
-
-    split_tp = parse_ucf101_splits(args.level)
-    assert len(split_tp) == args.num_split
-
-    out_path = args.out_list_path
-    if len(split_tp) > 1:
-        for i, split in enumerate(split_tp):
-            lists = build_split_list(
-                split_tp[i], frame_info, shuffle=args.shuffle)
-            filename = 'ucf101_train_split_{}_{}.txt'.format(i + 1, args.format)
-
-            with open(os.path.join(out_path, filename), 'w') as f:
-                f.writelines(lists[0])
-            filename = 'ucf101_val_split_{}_{}.txt'.format(i + 1, args.format)
-            with open(os.path.join(out_path, filename), 'w') as f:
-                f.writelines(lists[1])
-    else:
-        lists = build_split_list(split_tp[0], frame_info, shuffle=args.shuffle)
-        filename = '{}_{}_list_{}.txt'.format(args.dataset, args.subset,
-                                              args.format)
-        if args.subset == 'train':
-            ind = 0
-        elif args.subset == 'val':
-            ind = 1
-        elif args.subset == 'test':
-            ind = 2
-        with open(os.path.join(out_path, filename), 'w') as f:
-            f.writelines(lists[0][ind])
-
-
-if __name__ == "__main__":
-    main()

dygraph/tsn/data/dataset/kinetics400/extract_rawframes.py

-import argparse
-import sys
-import os
-import os.path as osp
-import glob
-from pipes import quote
-from multiprocessing import Pool, current_process
-import cv2
-
-
-def dump_frames(vid_item):
-    full_path, vid_path, vid_id = vid_item
-    vid_name = vid_path.split('.')[0]
-    out_full_path = osp.join(args.out_dir, vid_name)
-    try:
-        os.mkdir(out_full_path)
-    except OSError:
-        pass
-    vr = cv2.VideoCapture(full_path)
-    videolen = int(vr.get(cv2.CAP_PROP_FRAME_COUNT))
-    for i in range(videolen):
-        ret, frame = vr.read()
-        if ret == False:
-            continue
-        img = frame[:, :, ::-1]
-        # covert the BGR img into RGB img
-        img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
-        if img is not None:
-            cv2.imwrite('{}/img_{:05d}.jpg'.format(out_full_path, i + 1), img)
-        else:
-            print('[Warning] length inconsistent!'
-                  'Early stop with {} out of {} frames'.format(i + 1, videolen))
-            break
-    print('{} done with {} frames'.format(vid_name, videolen))
-    sys.stdout.flush()
-    return True
-
-
-def parse_args():
-    parser = argparse.ArgumentParser(description='extract optical flows')
-    parser.add_argument('src_dir', type=str)
-    parser.add_argument('out_dir', type=str)
-    parser.add_argument('--level', type=int, choices=[1, 2], default=2)
-    parser.add_argument('--num_worker', type=int, default=8)
-    parser.add_argument(
-        "--out_format",
-        type=str,
-        default='dir',
-        choices=['dir', 'zip'],
-        help='output format')
-    parser.add_argument(
-        "--ext",
-        type=str,
-        default='avi',
-        choices=['avi', 'mp4'],
-        help='video file extensions')
-    parser.add_argument(
-        "--new_width", type=int, default=0, help='resize image width')
-    parser.add_argument(
-        "--new_height", type=int, default=0, help='resize image height')
-    parser.add_argument(
-        "--resume",
-        action='store_true',
-        default=False,
-        help='resume optical flow extraction '
-        'instead of overwriting')
-    args = parser.parse_args()
-
-    return args
-
-
-if __name__ == '__main__':
-    args = parse_args()
-    if not osp.isdir(args.out_dir):
-        print('Creating folder: {}'.format(args.out_dir))
-        os.makedirs(args.out_dir)
-    if args.level == 2:
-        classes = os.listdir(args.src_dir)
-        for classname in classes:
-            new_dir = osp.join(args.out_dir, classname)
-            if not osp.isdir(new_dir):
-                print('Creating folder: {}'.format(new_dir))
-                os.makedirs(new_dir)
-
-    print('Reading videos from folder: ', args.src_dir)
-    print('Extension of videos: ', args.ext)
-    if args.level == 2:
-        fullpath_list = glob.glob(args.src_dir + '/*/*.' + args.ext)
-        done_fullpath_list = glob.glob(args.out_dir + '/*/*')
-    elif args.level == 1:
-        fullpath_list = glob.glob(args.src_dir + '/*.' + args.ext)
-        done_fullpath_list = glob.glob(args.out_dir + '/*')
-    print('Total number of videos found: ', len(fullpath_list))
-    if args.resume:
-        fullpath_list = set(fullpath_list).difference(set(done_fullpath_list))
-        fullpath_list = list(fullpath_list)
-        print('Resuming. number of videos to be done: ', len(fullpath_list))
-
-    if args.level == 2:
-        vid_list = list(
-            map(lambda p: osp.join('/'.join(p.split('/')[-2:])), fullpath_list))
-    elif args.level == 1:
-        vid_list = list(map(lambda p: p.split('/')[-1], fullpath_list))
-
-    pool = Pool(args.num_worker)
-    pool.map(dump_frames, zip(fullpath_list, vid_list, range(len(vid_list))))

dygraph/tsn/data/dataset/kinetics400/readme.md

-# extract_rawframes_opencv.py
-## 应用说明
-
-### 对于kinetics400数据
-运行脚本的命令如下 `python extract_rawframes_opencv.py ./video/ ./rawframes/ --level 2 --ext mp4` 或者`python extract_rawframes_opencv.py ./video/ ./rawframes/ --level 2 --ext mp4`
-
-### 参数说明
-`./video/`       ： 这个参数表示视频目录的地址
-`./rawframes`    ： 提取出的frames的存放目录
-`--level 1 or 2` ：  
-
-                        level 1，表示video的存储方式为
-
-                                ------ video
-                                        |------ xajhljklk.mp4
-                                        |------ jjkjlljjk.mp4
-                                        ....
-
-
-                        level 2, 表示video的存储方式为
-                        ------ video
-                                |------ class1
-                                        |-------- xajhljklk.mp4
-                                        |-------- jjkjlljjk.mp4
-                                ....
-`--ext 4`        : 表示视频文件的格式。

dygraph/tsn/multi-gpus-run.sh

@@ -6,9 +6,7 @@ use_gpu=True
 use_data_parallel=True
 
 export CUDA_VISIBLE_DEVICES=0,1,2,3
-export FLAGS_fast_eager_deletion_mode=1
-export FLAGS_eager_delete_tensor_gb=0.0
-export FLAGS_fraction_of_gpu_memory_to_use=0.98
+
 
 echo $mode "TSN" $configs  $resume $pretrain
 if [ "$resume"x != ""x ]; then

dygraph/tsn/run-eval.sh

@@ -3,9 +3,7 @@ use_gpu=True
 use_data_parallel=False
 
 export CUDA_VISIBLE_DEVICES=0
-export FLAGS_fast_eager_deletion_mode=1
-export FLAGS_eager_delete_tensor_gb=0.0
-export FLAGS_fraction_of_gpu_memory_to_use=0.98
+
 
 
 echo $mode $configs $weights

dygraph/tsn/single-gpu-run.sh

@@ -7,9 +7,7 @@ use_data_parallel=False
 weights="" #set the path of weights to enable eval and predicut, just ignore this when training
 
 export CUDA_VISIBLE_DEVICES=0
-export FLAGS_fast_eager_deletion_mode=1
-export FLAGS_eager_delete_tensor_gb=0.0
-export FLAGS_fraction_of_gpu_memory_to_use=0.98
+
 
 echo $mode "TSN" $configs  $resume $pretrain
 if [ "$resume"x != ""x ]; then