ik_vision

training 1_F network

12

Hi, I downloaded the recommended data and trained 1_F network for 1 million iteration, and it got:  Those error are consistent on the training data and test data....

vl_simplenn failure protection

1

vl_simple cannot handle empty input images, this is why I find this code useful: ``` if isempty(posbatch24.im) %disp('no24face'); continue; end res24c = vl_simplenn(net24_c, posbatch24.im) ; ``` Do you think a...

net24 and net48 are gpuArray

2

Hi, Thank you for your excellent work, clear code and easy to use and adapt. On Test branch, pretrained models **f24net-cpu.mat** and **f48net-cpu.mat** are saved in gpu mode. To avoid...

adding support for multi gpu and nasnet

2

NasNet is a new architecture achieving SOTA on ImageNet, I added support for it as a feature extractions I have added support for mutli_gpu based on Keras existing utility

The classification training results is impressive precision recall f1-score micro avg 0.766327 0.766327 0.766327 But the NER results are significantly lower precision recall f1-score micro avg 0.042444 0.042444 0.042444 What...

Exercise 4 - using validation data in train

2

@vedaldi Thank you for the detailed tutorial, I learned a lot by playing with it. In exercise 4 it seems the imageMean is calculated on all the data (train+validation). In...

It is a first attempt to extend the foundation model chronos from univariate to univariate with past_covariates. *Issue #, if available:* *Description of changes:* Extending chronos to use covariates input...