DeepLearningExamples
DeepLearningExamples copied to clipboard
NVIDIA
State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.
Related to **PyTorch/SpeechSynthesis/HiFiGAN** **Describe the bug** The class variable `lrelu_slope` is used in the class method `forward` but it is not defined. which raises an exception if HiFiGAN is trained...
Related to **BERT/TensorFlow2** On the hyperparameters used for BERT Large pretraining, the cmd in the doc is not aligned the config in `scripts/configs/pretrain_config.sh`. - doc: https://github.com/NVIDIA/DeepLearningExamples/blob/master/TensorFlow2/LanguageModeling/BERT/README.md#pre-training The following sample code...
Hello. Why the attention doesn't use speaker embeddings to find the alignment between text and mel spectrograms? This can vary greatly between speakers speaking in different styles.
Related to **Model/Framework(s)** *DeepLearningExamples-master/Tools/PyTorch/TimeSeriesPredictionPlatform* **Describe the bug** I need to use tspp for a research project, similar to the kaggle: [JPX Tokyo Stock Prediction with NVIDIA-TSPP](https://www.kaggle.com/code/anmolgupta11090/jpx-tokyo-stock-prediction-with-nvidia-tspp). I proceeded to download...
Related to brats22/nnunet/pytorch **the bug** `orig_lbl = load_data(self.data_path, "*_orig_lbl.npy") ` the line above which is line 51 in nnUNet/data_loading/data_module.py is producing an assertion error due to the assertion in the...
I tried to set the related arguments in `train.py` as `--sampling_rate 44100 --filter_length 2048 --hop_length 512 --win_length 2048`, but got the following error: ``` train.py:412: UserWarning: Using a target size...
Hello, I have a fatal error at kaldi tritonserver. Related to Kaldi **Describe the bug** ``` ERROR ([5.5]:SynchronizeGpu():cu-device.cc:638) cudaError_t 400 : "invalid resource handle" returned from 'cudaGetLastError()' [ Stack-Trace: ]...
