Closed RahulB117 closed 5 years ago
You need to include the dense_params
settings in the config file.
As an example of a working config file (at least on my end), see owen.yaml
.
Hey, good morning,
Thank you so much for the swift reply. I’ll run the solution and let you know if it worked.
Cheers
Sent from my iPhone
On 31-Mar-2019, at 1:29 AM, Owen Jow notifications@github.com wrote:
Closed #2.
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or mute the thread.
Hi, I've been trying to run this project but after running python main.py extract ,
I got the following errors :
---------- BEGIN VIDEO DIRECTORY PROCESSING [o] Video directory: /Users/Rahul/hmm_activity_recognition/data/kth\boxing --- 0 [o] Video path: /Users/Rahul/hmm_activity_recognition/data/kth\boxing\person01_boxing_d1_uncomp.avi [o] including feature "edge" [o] including feature "centroid" [o] including feature "optical_flow" [o] including feature "freq_optical_flow" [o] including feature "dense_optical_flow" [o] including feature "freq_dense_optical_flow" [o] including feature "divergence" [o] including feature "curl" [o] including feature "avg_velocity" Traceback (most recent call last): File "main.py", line 73, in
eval(command)(config=config)
File "main.py", line 21, in extract_features
ef.process_all_video_dirs(ef_params['base_dir'], save_path=save_path, config=ef_params)
File "C:\Users\Rahul\hmm_activity_recognition\scripts\extract_features.py", line 460, in process_all_video_dirs
process_video_dir(fvideo_dir, save_path=os.path.join(save_dir, name + '.h5'), config=config)
File "C:\Users\Rahul\hmm_activity_recognition\scripts\extract_features.py", line 487, in process_video_dir
video_features_seq = process_video(video_path, save_path=None, config=config)
File "C:\Users\Rahul\hmm_activity_recognition\scripts\extract_features.py", line 691, in process_video
prev_img=prev_img, img=frame_edge, dense_params=dense_params, n_bins=div_n_bins)
File "C:\Users\Rahul\hmm_activity_recognition\scripts\extract_features.py", line 396, in feat_divergence
flow = compute_dense_optical_flow(prev_img, img, dense_params)
File "C:\Users\Rahul\hmm_activity_recognition\scripts\extract_features.py", line 252, in compute_dense_optical_flow
roi_h = int(h * dense_params['roi_h'])
TypeError: 'NoneType' object is not subscriptable
How do I solve this? Thanks in advance