Vivek Loganathan
Vivek Loganathan
> Finally, I modified the training_hooks configuration of the train.yaml file, and the changes are as follows: > > ``` > training_hooks: > lr_config: > policy: 'step' > step: [20,...
I have exactly the same problem for NTU-RGB-xsub dataset. Does anyone have a solution for it ?
``` training_hooks: lr_config: policy: 'step' step: [20, 30, 40, 50] log_config: interval: 100 hooks: - type: TextLoggerHook checkpoint_config: interval: 5 optimizer_config: grad_clip:
@hengck23 Can you kindly help me with resnet 18 pre-trained weights.
It is the joint confidence score. Not necessarily 100%.
Hi @ucas010 @Wazaki-Ou, I would very much like to know if this tool allows to add action classes. If not have you found a tool that will help ? It...
Hi, @StellarStorm: Were you able to fix the issue. I am giving the absolute path (eg. ) and still I only see the text. @mhils: Is the convertor (.. image::...
@briankardon I have the same issue were you able to solve it ?
-> npm audit fix --force -> sudo apt -y install libgconf2-4 This helped me fix the issue
Hi fabro66, Thank you very much for the tutorial. I have the same error "No module named hg_3d" even with pre-trained model placed in models directory