-
Notifications
You must be signed in to change notification settings - Fork 21
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
OpenFace tool not found #16
Comments
请问您是否按照说明运行了 |
是的,因为无法连接到Google Drive,所以我下载了exts压缩文件将其解压后放到了E:\miniconda3\Lib\site-packages\MSA_FET路径下。 |
另外在运行如下代码时: 我将main文件中的160行代码: |
您好,请问您的问题解决了吗?我在使用openface时遇到了相同的问题,使用的是Windows 10系统和python3.8。同样无法连接到Google Drive,下载压缩文件后放到了\anaconda\envs\pytorch3.8\Lib\site-packages\MSA_FET\exts路径下 |
暂时还没有解决,依旧无法提取特征 |
您好,我根据另一条提问:提取视频特征打印不成功 中的方法,官网下载openface,替换了百度云下载的exts中openface文件夹中的文件,解决了openface tool not found 的问题 |
谢谢您的帮助,我替换之后显示还是需要下载CEN配置文件才能够运行,我正在下载。 |
您好,我也遇到了相同的问题,请问您解决这个问题了吗?我在官网中下载openface替换掉原先exts中的openface文件夹之后,出现了另一条issue“提取视频特征打印不成功“里的问题:FileNotFoundError: [WinError 2] 系统找不到指定的文件。 |
已解决,CEN文件确实是必需的。另外,”FileNotFoundError: [WinError 2] 系统找不到指定的文件“这个错误也有可能是ffmpeg这个软件包导致的。除了”ffmpeg-python“(我的是0.2.0版本)这个软件包之外,还需要从ffmpeg官网或者在conda中下载安装“ffmpeg”(我的是2.7.0版本),并将其正确配置到系统路径或虚拟环境中。 |
请问下载的cen文件放到了哪个位置啊 |
您好,原先exts下的openface内的三个文件需要删除 再把官网下载的openface放进去嘛?还是不用管。我两种情况都试了,还是报not found这个错误 |
您好,当我运行以下代码语句时:
from MSA_FET import FeatureExtractionTool
fet = FeatureExtractionTool("openface")
feature = fet.run_single('E:/CH-SIMS数据集/MSA Datasets/SIMS/Raw/video_0001/0001.mp4', out_file='E:/MME/feature_V.pkl',
return_type='pt')
出现了如下错误:
MMSA-FET - ========================== MMSA-FET Started ==========================
MMSA-FET - Temporary directory: C:\Users\Hugh.MMSA-FET/tmp
MMSA-FET - Log file: 'C:\Users\Hugh.MMSA-FET/log\MMSA-FET.log'
MMSA-FET - Config: {'video': {'tool': 'openface', 'fps': 25, 'multiFace': {'enable': False, 'device': 'cuda:0', 'facedetScale': 0.25, 'minTrack': 10, 'numFailedDet': 10, 'minFaceSize': 1, 'cropScale': 0.4}, 'average_over': 1, 'args': {'hogalign': False, 'simalign': False, 'nobadaligned': False, 'landmark_2D': True, 'landmark_3D': False, 'pdmparams': False, 'head_pose': True, 'action_units': True, 'gaze': False, 'tracked': False}}}
MMSA-FET - Initializing OpenFace video feature extractor...
MMSA-FET - Failed to initialize mediapipeExtractor.
MMSA-FET - An Error Occured:
Traceback (most recent call last):
File "E:\miniconda3\lib\site-packages\MSA_FET\main.py", line 299, in run_single
self.__init_extractors()
File "E:\miniconda3\lib\site-packages\MSA_FET\main.py", line 129, in __init_extractors
self.video_extractor = VIDEO_EXTRACTOR_MAP[extractor_name](video_cfg, self.logger)
File "E:\miniconda3\lib\site-packages\MSA_FET\extractors\video\openface.py", line 38, in init
raise e
File "E:\miniconda3\lib\site-packages\MSA_FET\extractors\video\openface.py", line 35, in init
raise FileNotFoundError("OpenFace tool not found.")
FileNotFoundError: OpenFace tool not found.
Traceback (most recent call last):
File "E:\MME\test.py", line 17, in
feature = fet.run_single('E:/CH-SIMS数据集/MSA Datasets/SIMS/Raw/video_0001/0001.mp4', out_file='E:/MME/feature_V.pkl',
File "E:\miniconda3\lib\site-packages\MSA_FET\main.py", line 335, in run_single
raise e
File "E:\miniconda3\lib\site-packages\MSA_FET\main.py", line 299, in run_single
self.__init_extractors()
File "E:\miniconda3\lib\site-packages\MSA_FET\main.py", line 129, in __init_extractors
self.video_extractor = VIDEO_EXTRACTOR_MAP[extractor_name](video_cfg, self.logger)
File "E:\miniconda3\lib\site-packages\MSA_FET\extractors\video\openface.py", line 38, in init
raise e
File "E:\miniconda3\lib\site-packages\MSA_FET\extractors\video\openface.py", line 35, in init
raise FileNotFoundError("OpenFace tool not found.")
FileNotFoundError: OpenFace tool not found.
我使用的是Windows 10系统和Python 3.9,能够正常提取音频特征,请问可能是什么原因导致视频特征提取报错呢?
The text was updated successfully, but these errors were encountered: