voxel-flow

voxel-flow copied to clipboard

FileNotFoundError: [Errno 2] No such file or directory: '/home/VoxelFlow/dataset/ucf101_triplets/137560/frame_1.png'

3

hello all I was trying to train code the following error occurred: FileNotFoundError: [Errno 2] No such file or directory: '/home/VoxelFlow/dataset/ucf101_triplets/137560/frame_1.png' where is the dataset to download? should it be...

samo313

DuplicateFlagError: The flag 'train_dir' is defined twice.

2

Hello thanks for sharing your nice code. I have a problem while I try to run "voxel_flow_train.py" the below error occurred. would you please give me some advice to solve...

samo313

extrapolation

3

Thanks for sharing.And I want to know how to modify the code to train the extrapolation‘s model?

huliyu1203

Figure 2 (e) and (f). I understand the output of decoder is F. But I don't know how to get the visual output of F[motion] and F[mask]...

nameless-mqc

trained model

4

thank you for sharing your implementation. i was looking for the trained model but unfortunately didn't find it. however, i would like to evaluate your approach fairly and would like...

stubborn-dwarf

training datasets

10

Hello. How to build the training dataset from UCF?

qingsenyangit

I'm so confused about how to generate the test frame.txt. And how to use the image to generate video.

fmbao

Is the mapping between sequence ids( as in file "data_list/ucf101_test_files_frame1.txt") and the original frame from the UCF dataset (i.e. which frame from which video) available?

saikatdutta

Why preidctiion.shape in voxel_flow_train.py is [2, 256, 256, 3]?

1

Thanks in advance. The question described as the title is always confusing me. I debugged the code for a week, but get no progress, so it's hard for me. And...

Informativeinform

is_train=True when testing?

3

https://github.com/liuziwei7/voxel-flow/blob/e796773c4a93ab5b8bf9671f0dd11b6ecfc12007/voxel_flow_train.py#L189 I am wondering why is_train=True when testing model. I compared the results between when is_train=True and when is_train=False. Oddly, is_train=True produces the correct result when testing.

LucyLu-LX