利用openpose提取自建数据集骨骼点训练st-gcn，复现st-gcn

利用openpose提取自建数据集骨骼点训练st-gcn，复现st-gcn

0、下载st-gcn

参考：
gitbub上fork后导入到gitee快些: st-gcn下载
也可以直接下载zip文件后解压

1、处理准备自己数据集

• 数据集要求将相同类别的视频放到同一文件夹,我这里用到一个较老的数据集：training_lib_KTH.zip，六种行为放到六个不同文件夹。
  
  用于st-gcn训练的数据集视频帧数不要超过300帧，5~6s的视频时长比较好，不要10几s的视频时长。要不然会报index 300 is out of bounds for axis 1 with size 300这种错误。因此对上面数据集进一步裁剪为6s的大概150帧（此视频帧率为25后面利用FFmpeg再次改变帧率为30时，时长会变长到8s）。裁剪后视频文件如下
  
  原始数据集和裁剪为6s的数据集放在链接：
  链接：https://pan.baidu.com/s/1oHQyo-c3e5YXb52b-O0STQ” />2、准备环境，搭建openpose环境
  • 搭建openpose环境是为了利用open pose提取knetics-skeleton视频的骨骼点，openpose环境的搭建可参考以下视频：
    openpose环境搭建
    以及参考博客：windows 10下，自编译openpose代码
  • 此处注意如果用cuda，最好先下载vs后再下载cuda

  3、利用openpose提取自己视频骨骼数据

  st-gcn作者有提供他们整理好并使用的kinetics-skeleton数据集，他们数据集格式如下图所示：
  
  接下来参考：用自建kinetics-skeleton行为识别数据集训练st-gcn网络流程记录中的2部分对视频数据进行resize至340×256的大小，30fps的帧率。然后调用openpose的进行骨骼点数据的检测和输出。

  #!/usr/bin/env python# coding:gbkimport osimport argparseimport jsonimport shutilimport numpy as npimport torchimport skvideo.io#from processor.io import IOimport toolsimport tools.utils as utils# if __name__ == '__main__':#class PreProcess(IO):class PreProcess():def start(self):work_dir = 'D:/st-gcn'type_number = 6action_filename_list = ['boxing', 'handclapping', 'handwaving', 'jogging', 'running', 'walking']for process_index in range(type_number):action_filename = action_filename_list[process_index]# 标签信息labelAction_name = '{}_{}'.format(action_filename,process_index)#labelAction_name = 'xxx_{}'.format(process_index)label_no = process_index# 视频所在文件夹originvideo_file = 'D:/dataSet/training_lib_KTH_cut_6s/{}/'.format(action_filename)# resized视频输出文件夹 需要自己创建几个动作的文件夹resizedvideo_file = './mydata/training_lib_KTH_cut_6s/resized/{}/'.format(action_filename)videos_file_names = os.listdir(originvideo_file)# 1. Resize文件夹下的视频到340x256 30fpsfor file_name in videos_file_names:video_path = '{}{}'.format(originvideo_file, file_name)outvideo_path = '{}{}'.format(resizedvideo_file, file_name)writer = skvideo.io.FFmpegWriter(outvideo_path, outputdict={'-f': 'mp4','-vcodec': 'libx264', '-s': '340x256', '-r': '30'})reader = skvideo.io.FFmpegReader(video_path)for frame in reader.nextFrame():writer.writeFrame(frame)writer.close()print('{} resize success'.format(file_name))# 2. 利用openpose提取每段视频骨骼点数据resizedvideos_file_names = os.listdir(resizedvideo_file)for file_name in resizedvideos_file_names:outvideo_path = '{}{}'.format(resizedvideo_file, file_name)# openpose = '{}/examples/openpose/openpose.bin'.format(self.arg.openpose)#openpose = '{}/OpenPoseDemo.exe'.format(self.arg.openpose)openpose = 'D:/openpose-master/build/x64/Release/OpenPoseDemo.exe'video_name = file_name.split('.')[0]output_snippets_dir = './mydata/training_lib_KTH_cut_6s/resized/snippets/{}'.format(video_name)output_sequence_dir = './mydata/training_lib_KTH_cut_6s/resized/data'output_sequence_path = '{}/{}.json'.format(output_sequence_dir, video_name)#label_name_path = '{}/resource/kinetics_skeleton/label_name_action.txt'.format(work_dir)#自己创建好标签文档，里面文档内写好动作名称label_name_path = '{}/resource/kinetics_skeleton/label_name_action{}.txt'.format(work_dir,process_index)with open(label_name_path) as f:label_name = f.readlines()label_name = [line.rstrip() for line in label_name]# pose estimationopenpose_args = dict(video=outvideo_path,write_json=output_snippets_dir,display=0,render_pose=0,model_pose='COCO')command_line = openpose + ' 'command_line += ' '.join(['--{} {}'.format(k, v) for k, v in openpose_args.items()])shutil.rmtree(output_snippets_dir, ignore_errors=True)os.makedirs(output_snippets_dir)os.system(command_line)# pack openpose ouputsvideo = utils.video.get_video_frames(outvideo_path)height, width, _ = video[0].shape# 这里可以修改label, label_indexvideo_info = utils.openpose.json_pack(output_snippets_dir, video_name, width, height, labelAction_name, label_no)if not os.path.exists(output_sequence_dir):os.makedirs(output_sequence_dir)with open(output_sequence_path, 'w') as outfile:json.dump(video_info, outfile)if len(video_info['data']) == 0:print('{} Can not find pose estimation results.'.format(file_name))returnelse:print('{} pose estimation complete.'.format(file_name))if __name__ == '__main__':p=PreProcess()p.start()

  运行代码之前提前再st-gcn里面建好/mydata/training_lib_KTH_cut_6s_resized文件夹，并在文件夹中将六种行为的文件夹也创建好，‘boxing’, ‘handclapping’, ‘handwaving’, ‘jogging’, ‘running’, ‘walking’。运行之前也需要创建标签文档0到5：
  
  每个文档里面是100个动作标签
  运行完如下所示：
  
  此时打开data能看到所有视频的骨骼数据，snippets里面每个json文件存的是单帧骨骼数据，data里面每个json文件都是一个视频的所有骨骼点数据。data里面json文件打开如下图所示：
  

  4、整理骨骼点数据，生成st-gcn运行的格式

  首先将data里面的数据分成训练集、验证集、测试集按照6：2：2划分.
  
  将01到15复制kinetics_train，16-20放到val，21-25放到test。

  import jsonimport osif __name__ == '__main__':train_json_path = './mydata/kinetics-skeleton/kinetics_train'val_json_path = './mydata/kinetics-skeleton/kinetics_val'test_json_path = './mydata/kinetics-skeleton/kinetics_test'output_train_json_path = './mydata/kinetics-skeleton/kinetics_train_label.json'output_val_json_path = './mydata/kinetics-skeleton/kinetics_val_label.json'output_test_json_path = './mydata/kinetics-skeleton/kinetics_test_label.json'#train_json_names = os.listdir(train_json_path)val_json_names = os.listdir(val_json_path)test_json_names = os.listdir(test_json_path)train_label_json = dict()val_label_json = dict()test_label_json = dict()for file_name in train_json_names:name = file_name.split('.')[0]json_file_path = '{}/{}'.format(train_json_path, file_name)json_file = json.load(open(json_file_path))file_label = dict()if len(json_file['data']) == 0:file_label['has_skeleton'] = Falseelse:file_label['has_skeleton'] = Truefile_label['label'] = json_file['label']file_label['label_index'] = json_file['label_index']train_label_json['{}'.format(name)] = file_labelprint('{} success'.format(file_name))with open(output_train_json_path, 'w') as outfile:json.dump(train_label_json, outfile)for file_name in val_json_names:name = file_name.split('.')[0]json_file_path = '{}/{}'.format(val_json_path, file_name)json_file = json.load(open(json_file_path))file_label = dict()if len(json_file['data']) == 0:file_label['has_skeleton'] = Falseelse:file_label['has_skeleton'] = Truefile_label['label'] = json_file['label']file_label['label_index'] = json_file['label_index']val_label_json['{}'.format(name)] = file_labelprint('{} success'.format(file_name))with open(output_val_json_path, 'w') as outfile:json.dump(val_label_json, outfile)for file_name in test_json_names:name = file_name.split('.')[0]json_file_path = '{}/{}'.format(test_json_path, file_name)json_file = json.load(open(json_file_path))file_label = dict()if len(json_file['data']) == 0:file_label['has_skeleton'] = Falseelse:file_label['has_skeleton'] = Truefile_label['label'] = json_file['label']file_label['label_index'] = json_file['label_index']test_label_json['{}'.format(name)] = file_labelprint('{} success'.format(file_name))with open(output_test_json_path, 'w') as outfile:json.dump(test_label_json, outfile)

  生成如下：
  
  再利用stgcn训练代码中自带了数据转换代码tools/kinetics_gendata.py,使用该脚本将kinetics-skleton数据集转换为训练使用的npy与pkl文件。
  这里参考博客：数据转换中的三数据转换。以下地方需要修改：

  num_person_in=1,#observe the first 5 personsnum_person_out=1,#then choose 2 persons with the highest score

  part = ['train', 'val','test']

  frame不用修改即可前面视频已经裁剪过
  运行脚本后：
  

  5、训练st-gcn网络

  这部分参考st-gcn训练自建行为识别数据集中的5、6部分即可
  我的train.yaml是这样修改的：

  work_dir: ./work_dir/recognition/kinetics_skeleton/ST_GCN# feederfeeder: feeder.feeder.Feedertrain_feeder_args:random_choose: Truerandom_move: Truewindow_size: 150 #data_path: ./data/Kinetics/kinetics-skeleton/train_data.npy#label_path: ./data/Kinetics/kinetics-skeleton/train_label.pkldata_path: ./mydata/kinetics-skeleton/train_data.npylabel_path: ./mydata/kinetics-skeleton/train_label.pkltest_feeder_args:#data_path: ./data/Kinetics/kinetics-skeleton/val_data.npy#label_path: ./data/Kinetics/kinetics-skeleton/val_label.pkldata_path: ./mydata/kinetics-skeleton/val_data.npylabel_path: ./mydata/kinetics-skeleton/val_label.pkl# modelmodel: net.st_gcn.Modelmodel_args:in_channels: 3num_class: 6edge_importance_weighting: Truegraph_args:layout: 'openpose'strategy: 'spatial'# training#device: [0,1,2,3]device: [0]batch_size: 32test_batch_size: 32#optimbase_lr: 0.1step: [20, 30, 40, 50]num_epoch: 50

  执行训练代码：

  python main.py recognition -c config/st_gcn/kinetics-skeleton/train.yaml

  6、测试

  可修改test.yaml利用刚刚自己的测试集进行测试

  weights: ./work_dir/recognition/kinetics_skeleton/ST_GCN/epoch50_model.pt#weights: ./models/st_gcn.kinetics.pt# feederfeeder: feeder.feeder.Feedertest_feeder_args:#data_path: ./data/Kinetics/kinetics-skeleton/val_data.npy#label_path: ./data/Kinetics/kinetics-skeleton/val_label.pkl#data_path: ./mydata/kinetics-skeleton/val_data.npy#label_path: ./mydata/kinetics-skeleton/val_label.pkldata_path: ./mydata/kinetics-skeleton/test_data.npylabel_path: ./mydata/kinetics-skeleton/test_label.pkl# modelmodel: net.st_gcn.Modelmodel_args:in_channels: 3num_class: 6edge_importance_weighting: Truegraph_args:layout: 'openpose'strategy: 'spatial'# test phase: testdevice: 0test_batch_size: 32

  然后执行

  python main.py recognition -c config/st_gcn/kinetics-skeleton/test.yaml

  注：作者也是一位初学者，此文章供参考讨论，有什么问题欢迎讨论多多指教！