Prokofiev Kirill
Prokofiev Kirill
This framework natively supports mobilenets only. To train with ResNet or other models, you need to add this support as it is done for mobilenet. So, you should add a...
Hello, First of all, in CelebA_Spoof paper, they are using a different model and some different setups for training. Also, when I trained on the single task the result on...
This function takes cosine from the last layer of the model. See class AngleSimpleLinear.
I haven't pushed code for this file generating. I just loop over the cropped dataset and check shapes.
Hello, Are you sure that you initiated the OpenVINO environment before running the script? Also, make sure that you properly installed OpenVINO (it's not like pip install) and you can...
Hello, guys, thanks for reporting the problem. I will fix it as soon as possible.
@yunchu , I investigated this issue and found some weird behavior in a test environment. This issue happens because of in `train_cls_incr` we change datasets, but the number of iterations...
BTW, This problem is not reproducible outside of tests. I tried the class incremental approach with the same data and everything is fine. The number of iterations is what it...
@take2rohit , hi! Have you managed to reproduce the results of the paper (or at least close to it)? I tried several times in this repository and tried to integrate...
https://github.com/kprokofi/ML-GCN - I couldn't reproduce the author's result, but it is got better. 93+ mAP