Viktor Ivanov

ImageSequenceClip does not close gifs properly

3

The problem is here: https://github.com/Zulko/moviepy/blob/v1.0.3/moviepy/video/io/gif_writers.py#L274 It opens a writer but never calls `writer.close()`. This can lead to `[WinError 32] The process cannot access the file because it is being used...

In the preprint it said the following regarding VSR generator's architecture: > CT(ln, 3, 64, 2), ReLU → lup2; CT(lup2, 3, 64, 2), ReLU → lup4; > C(lup4, 3, 3,...

Progress bar showing wrong step number

3

When `steps_per_execution` is used, the step number shown by a progress bar does not match how many steps were actually executed. See example here: [colab](https://colab.research.google.com/gist/itmo153277/358d490853d9b9cd662dca488834aafe/wrongstepnumber.ipynb) The step number does not...

TF+XLA+Mixed Precision: Keras fails to compute gradients

1

Keras fails to compute gradients for autoencoder-esce model using Tensorflow backend with mixed precision and jit compilation enabled. See code here: [colab](https://colab.research.google.com/gist/itmo153277/6f38f43d724e173a30115d12f2a40e07/upsamplerelugrad.ipynb). This is caused by `UpSampling2D` layer. When gradients...

Explicit quantization is slower than implicit quantization and produces invalid results

2

## Description Since implicit quantization is deprecated, I started migrating my model pipeline to explicit quantization. However, I encountered some issues: 1. Different behaviour with concat: With implicit quantization the...

Add some missing functions that are necessary for a proper GPU mode change. | Mode | gsync (inverted) | igpumode | |---------------|:----------------:|:--------:| | dGPU | 0 | 0 | |...