Enric Moreu
Enric Moreu
**Link to the notebook** [pytorch_smdataparallel_mnist_demo](https://github.com/aws/amazon-sagemaker-examples/blob/main/training/distributed_training/pytorch/data_parallel/mnist/pytorch_smdataparallel_mnist_demo.ipynb) **What aspects of the notebook can be improved?** This notebook is not working anymore with `ml.p3dn.24xlarge` instances : `botocore.exceptions.ClientError: An error occurred (ValidationException) when calling...
I compared training with `train_mixed.sh` using the normal model and the `--small` For some reason, the small takes longer (I also increased the batch size). Which parameters should I use...
I tried to reproduce your results following your README instructions. I used the default `UACANet-L` config with a batch size of 8 instead of 32. The mDICE I get on...
When `pretrained: True` the pretrained weights in `data/backbone_ckpt/res2net50_v1b_26w_4s-3cf99910.pth` are used. Where do these weights come from? Are they pretrained on colon images by you, or they are pretrained just on...
Just `docker run -it --name jitsi-meet -p 443:443 robertoandrade/jitsi-meet` But no video and sound in Firefox / Chrome and Linux / Windows Thanks!
$ `docker-compose build sova-tts` ``` ... Step 11/18 : RUN pip3 install -r requirements.txt ---> Running in 17d95bfc1375 Obtaining TPS from git+https://github.com/sovaai/[email protected]#egg=TPS (from -r requirements.txt (line 19)) Cloning https://github.com/sovaai/sova-tts-tps (to...