Václav Volhejn

Pruning only works for small batch sizes

4

**Describe the bug** When using `prune_low_magnitude()`, my model is not pruned if the batch size is low. **System information** TensorFlow version (installed from source or binary): 2.8.0 installed via pip...

Crash when importing

13

I installed deepsparse using Pip. When I try to import it, Python immediately crashes: ``` (venv) vvolhejn@eu-login-21 ~> python3 Python 3.8.5 (default, Sep 27 2021, 10:10:37) [GCC 8.2.0] on linux...

When quantizing a 1D CNN, I found that excluding normalization (layer norm followed by learnable scale and shift) from quantization improves the accuracy quite a bit. Then I tried to...

save_dataset_statistics broken with DDSP 3.2.0?

8

Hi, I'm trying to run the code from the [`train_autoencoder` notebook](https://github.com/magenta/ddsp/blob/main/ddsp/colab/demos/train_autoencoder.ipynb) with a newer DDSP version (3.2.0). I made a little script that wraps `save_dataset_statistics`: ```python import argparse import os...

Hi, for my Master's thesis, I'm looking into accelerating the inference of neural audio synthesis models. Since the DDSP plugin manages to run in real-time on my CPU (very cool!),...

Hi, in FastNEWT, the continuous array index is computed as ([code](https://github.com/ben-hayes/neural-waveshaping-synthesis/blob/main/neural_waveshaping_synthesis/models/modules/shaping.py#L137)): ```python idx = self.table_size * (x - self.table_min) / (self.table_max - self.table_min) ``` I believe the correct version would...

Hey, I'm running Wilds on a `p2.8xlarge` AWS EC2 instance with 8 K80 GPUs. I noticed that when I try to run `run_expt.py` and use the `--device` argument to divide...

### Current Behavior I'm using SimpleMesh to stretch an image based on a grid that defines the distortion. I had a working solution but when I increased the grid size...

[CLI]: Adding dict-valued keys to a run's summary doesn't work

4

### Describe the bug I have a use case where I'm evaluating models after they've finished training. I'm trying to take a finished run and add new keys to the...

Op names aren't shown in tensorflow_stats

1

Hi, I'm trying to profile the inference performance of my model on CPU to figure out where the bottlenecks are. However, when I run the profiler and open tensorflow_stats, it...