SlowFast使用指南（二）——训练ava数据集

写在前面

ava 的数据集非常大，训练起来非常慢，这次我就把ava的数据集缩小到2个视频（1个作为验证集，一个作为训练集），这样做的目的是观察slowfast是如何训练ava数据集的。

训练所需数据文件

新建一个 avademo 目录，目录中包含annotations、frame_lists、frames三个目录

annotations

annotations 需要从官网进行下载。直接从annotations下载地址 下载

然后执行解压命令解压 tar 包

tar -xvf ava_annotations.tar

目录结构如下：

├── ava_annotations
│   ├── ava_action_list_v2.1_for_activitynet_2018.pbtxt
│   ├── ava_action_list_v2.2_for_activitynet_2019.pbtxt
│   ├── ava_action_list_v2.2.pbtxt
│   ├── ava_included_timestamps_v2.2.txt
│   ├── ava_test_excluded_timestamps_v2.1.csv
│   ├── ava_test_excluded_timestamps_v2.2.csv
│   ├── ava_test_v2.2.csv
│   ├── ava_train_excluded_timestamps_v2.1.csv
│   ├── ava_train_excluded_timestamps_v2.2.csv
│   ├── ava_train_v2.1.csv
│   ├── ava_train_v2.2.csv
│   ├── ava_val_excluded_timestamps_v2.1.csv
│   ├── ava_val_excluded_timestamps_v2.2.csv
│   ├── ava_val_v2.1.csv
│   ├── ava_val_v2.2.csv
│   ├── person_box_67091280_iou75
│   │   ├── ava_detection_test_boxes_and_labels.csv
│   │   ├── ava_detection_train_boxes_and_labels_include_negative.csv
│   │   ├── ava_detection_train_boxes_and_labels_include_negative_v2.1.csv
│   │   ├── ava_detection_train_boxes_and_labels_include_negative_v2.2.csv
│   │   ├── ava_detection_val_boxes_and_labels.csv
│   │   ├── ava_detection_val_for_training_boxes_and_labels_include_negative.csv
│   │   └── ava_detection_val_for_training_boxes_and_labels_include_negative_v2.2.csv
│   ├── person_box_67091280_iou90
│   │   ├── ava_action_list_v2.1_for_activitynet_2018.pbtxt
│   │   ├── ava_detection_test_boxes_and_labels.csv
│   │   ├── ava_detection_train_boxes_and_labels_include_n