Skip to content
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

path to scenes gt for -mapping in create_train_dataset #29

Closed
jeannedionisi opened this issue Dec 14, 2021 · 3 comments
Closed

path to scenes gt for -mapping in create_train_dataset #29

jeannedionisi opened this issue Dec 14, 2021 · 3 comments

Comments

@jeannedionisi
Copy link

Hi,
First of all, thank you very much for this work.
I have a question that may be a bit silly, but I couldn't find an answer. Indeed, I would like to run the code corresponding to create_train_dataset here , however I can't understand how to fill the mapping_fn parameter : could you tell me what is /path/to/scenes/gt please ? :) I really don't have any idea which file to put...

@soCzech
Copy link
Owner

soCzech commented Jan 5, 2022

It is the file with ground truth for a given video.
It is created e.g. here https://github.com/soCzech/TransNetV2/blob/master/training/consolidate_datasets.py#L206.

@soCzech soCzech closed this as completed Jan 5, 2022
@jeannedionisi
Copy link
Author

Thank you for your answer

@runrunaway2020
Copy link

excuse me, have you re-implemented this network? could you please tell me how to solve this problem ? tensorflow.python.framework.errors_impl.InvalidArgumentError: Exception encountered when calling layer "bn" (type BatchNormalization).

input must be 4-dimensional[1,100,27,48,64] [Op:FusedBatchNormV3]

Call arguments received by layer "bn" (type BatchNormalization):
• inputs=tf.Tensor(shape=(1, 100, 27, 48, 64), dtype=float32)
• training=False
thank you very much

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants