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 **Model** UNet_Industrial, TF1 **Describe the bug** I am following [the notebook for TF-TRT inference](https://github.com/NVIDIA/DeepLearningExamples/blob/master/TensorFlow/Segmentation/UNet_Industrial/notebooks/Colab_UNet_Industrial_TF_TFTRT_inference_demo.ipynb) for UNet_industrial. However, when I run the cell to download the pretrained model, it...
I believe I am currently having an issue when training from both scratch and the pre-trained tacotron2 model. I have collected 14 to 17 hours of pre-processed wav files of...
Related to "UNet Industrial for TensorFlow" **Describe** when I train this model with a custom dataset(5000 files) , my computer will get stuck. when 3150 files are used, the occupation...
Hello and so happy to see you use Pytorch-Lightning! :tada: Just wondering if you already heard about quite the new **Pytorch Lightning (PL) ecosystem CI** where we would like to...
**Describe the bug** I already trained a English & Chinese bilingual tacotron model with my own data on following source: https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/SpeechSynthesis/Tacotron2 And inference output is OK, my inference phrase like...
Related to **Mask R-CNN/PyTorch)** *Examples:* * *GNMT/PyTorch* **Is your feature request related to a problem? Please describe.** A clear and concise description of what the problem is. Ex. I'm always...
Changed the way we keep track of sentences counts in each shard training and test file to avoid re-calculating from scratch. This results in substantial speed-up of sharding on huge...
Hi. There is a `endpoint_detected` parameter in `PartialResultsCallback` of `Kaldi Backend`. It is `TRUE` when a `endpoint`(phrase end) is detected by `CUDA decoder`. Is it possible to get `lattice` from...
**Describe the bug** Train with 100 epochs, take a snapshot and try the inference with pretrainined waveglow. Validation loss is 3.09584379196167 at the end. But all I get is noise...
