Mahdi Mohammadpour Fard

Hi @Sesota Whold you please share the same wheel files for wondows too? I have a lot of troubles with compiling tensorflow from the source code. Thanks.

Thanks, @Sesota . Fortunately I successfully compiled Tensorflow 2.5 with SSE2 optimization (without AVX, without CUDA) on Windows for Python 3.6. It took about 4 hours on my PC with...

Can somebody give a link to TF 2.4 no AVX for windows? @agkphysics Can you please help me?

Hi, After 10 epochs the transducer_loss is about 3.5 for my training data (300 hours). But the test results are not promising. What is the transducer_loss after 20 or 30...

`'i'` is declared in line 219 and it is not an error in my case. By the way you can replace `'i'` in line 247 with `count_of_total_train_items/your_batch_size` because at the...

I have trained this repo for several days with about 20k generated image but the results are not satisfactory. But if it works for one image, you can use it...

Yes, that's OK, 3 is the number of classes. The source code does not have bugs. But the results are poor. I've trained [MMNET]( https://github.com/hyperconnect/MMNet) and got better results.

Same issue: pytorch version: 1.10 cuda version: 10.1 ``` /usr/local/lib/python3.6/dist-packages/torch/distributed/launch.py:186: FutureWarning: The module torch.distributed.launch is deprecated and will be removed in future. Use torchrun. Note that --use_env is set by...

I tested it on another system with: pytorch version: 1.9.0 cuda: 11.1 and it worked.

Check this [repo](https://github.com/pourfard/FaceAntiSpoofing)