search

vt-vl-lab / FGVC

[ECCV 2020] Flow-edge Guided Video Completion
Other
1.55k stars 263 forks source link

Question:File "video_completion.py", line 165 #18

Closed yunzhongfei closed 3 years ago

yunzhongfei commented 3 years ago

python video_completion.py \

   --mode video_extrapolation \
   --path ../data/tennis \
   --outroot ../result/tennis_extrapolation \
   --H_scale 2 \
   --W_scale 2 \
   --seamless

Pytorch 1.6.0 for flow prediction

Finish Calculating flow. Traceback (most recent call last): File "video_completion.py", line 615, in main(args) File "video_completion.py", line 578, in main video_completion_seamless(args) File "video_completion.py", line 418, in video_completion_seamless video, corrFlowF, corrFlowB, flow_mask, mask_dilated, start_point, end_point = extrapolation(args, video, corrFlowF, corrFlowB) File "video_completion.py", line 165, in extrapolation corrFlowF[H_start : H_start + imgH, W_start : W_start + imgW, :] = corrFlowF_ori ValueError: could not broadcast input array from shape (512,960,2,0) into shape (512,960,2,69)

yunzhongfei commented 3 years ago

How can I solve this problem? Thanks

yunzhongfei commented 3 years ago

image

gaochen315 commented 3 years ago

From the error message you posted, I see either the video or the flow is not loaded correctly. Can you check the dimension of video, corrFlowF, and corrFlowB?

yunzhongfei commented 3 years ago

From the error message you posted, I see either the video or the flow is not loaded correctly. Can you check the dimension of video, corrFlowF, and corrFlowB?

image

yunzhongfei commented 3 years ago

python video_completion.py --mode object_removal --path ../data/tennis --path_mask ../data/tennis_mask --outroot ../result/tennis_removal --seamless Pytorch 1.6.0 for flow prediction

Finish Calculating flow. Please switch to Pytorch 0.4.0

python video_completion.py \

   --mode object_removal \
   --path ../data/tennis \
   --path_mask ../data/tennis_mask \
   --outroot ../result/tennis_removal \
   --seamless

Pytorch 1.6.0 for flow prediction

Finish Calculating flow. Please switch to Pytorch 0.4.0

yunzhongfei commented 3 years ago

I feel like there's something wrong with the previous step. @gaochen315

gaochen315 commented 3 years ago

It seems like you don't deactivate the raft environment by conda deactivate. Try deactivating it first and then activate the second environment.

gaochen315 commented 3 years ago

Please check the latest code. There is only one environment, i.e., Pytorch 1.6.0, CUDA 10.1. Let me know if you have any questions.

gaochen315 commented 3 years ago

I’m closing this issue because it has been inactive for a few months. Please reopen if you have other questions.

Thank you!

yunzhongfei commented 3 years ago

ok, thank you very much.