-
I trained a Motion Deeplab using the MOTChallenge according to the instructions. The training process seems to have run fine (sidenote: is it reasonable that I could only use batch size = 1 due to CUD…
-
### 🐛 Describe the bug
I am trying to inference a protein structure graph transformer model using PyTorch2 with rocm-5.4.3/5.5.1 on MI210 GPUs.
When I scale the batch size pass 250 per gpu I get…
-
I concurrently use Spyro and Devito tools to process the most simple velocity model. In Spyro, I obtained minimal data values in true_d.data, as shown below:
```
array([[0.00000000e+00, 0.00000000e+…
-
Hey,
First, thanks for the kind words in various places :). I came across your posts, which led me here.
I also spent quite some time working on similarity models. I think they're surprisingly d…
-
We plan to write a short summary for every implemented method in our wiki space.
Please follow the template below and write the draft here.
**Paper Title**
[![paper](https://img.shields.io/badg…
-
### 🐛 Describe the bug
I'm implementing an stft layer that is not trainable using 1d convolutions. One of the steps involves the normalization of a tensor. I'm finding that when I use the layer in a …
-
i got negative loss when training wavenet with THSCH-30 dataset.
```
Wavenet Train
###########################################################
Checkpoint_path: i:/data/voice/logs-Tacotron-2\…
-
Dear @r9y9,
I've trained a MoL wavenet to 1000k steps on ~30,000 audio samples from M-AI Labs data. I am using a pre-trained transformer from @kan-bayashi.
The resulting audio has rather intelli…
-
I use the default setting of [4,4,4,4] in 20180510_mixture_lj_checkpoint_step000320000_ema.json for umsample parameters, and I got an error from
```
if c is not None and self.upsample_net is not No…
-
environment : tensorflow 1.7.0, cuda 9.0, cudnn 7
I have tried to run train.py, but it is ended right after initiating train.
Here is the log.
Would you help me why it happens?
It stops duri…