search

v-iashin / MDVC

PyTorch implementation of Multi-modal Dense Video Captioning (CVPR 2020 Workshops)
https://v-iashin.github.io/mdvc
142 stars 19 forks source link

Error video_stack_rgb and video_stack_flow all is None #8

Closed haoxiaopeng closed 4 years ago

haoxiaopeng commented 4 years ago

video_stack_rgb = feat_h5_video.get(f'{video_id}/i3d_features/rgb') video_stack_flow = feat_h5_video.get(f'{video_id}/i3d_features/flow') video_stack_rgb and video_stack_flow all is None video_id = 'v_QOlSCBRmfWY' h5='sub_activitynet_v1-3.i3d_25fps_stack24step24_2stream.hdf5'

v-iashin commented 4 years ago

Hi. Thanks for your interest in our work.

I don't understand the problem you are facing. Let's start with the code which might reproduce your error. I assume you do something like this.

$ conda activate mdvc
$ python

and you run there:

import h5py
import numpy as np
feat_h5_video = h5py.File('./data/sub_activitynet_v1-3.i3d_25fps_stack24step24_2stream.hdf5', 'r')
video_stack_rgb = feat_h5_video.get('v_QOlSCBRmfWY/i3d_features/rgb')
video_stack_flow = feat_h5_video.get('v_QOlSCBRmfWY/i3d_features/flow')
print(np.array(video_stack_rgb).sum())  # 17516.19
print(np.array(video_stack_flow).sum())  # 12495.1045

So, I cannot reproduce your error. Please, provide more details or double-check your setup.

haoxiaopeng commented 4 years ago

the md5 not equal with you 4f571fc943cfdf1c833c5fc9a95583e7 sub_activitynet_v1_3.i3d_25fps_stack24step24_2stream.hdf5

I am download again