Revision 8e6823a071dd5f4b6210b9ba47d22041806f8cde authored by Leonardo Araneda Freccero on 29 April 2020, 11:21:35 UTC, committed by GitHub on 29 April 2020, 11:21:35 UTC
* Tuned hyperparameter num_batches_per_epoch for wavenet speedup Increases speed of wavenet by ~34% when testing accuracy * Increased the allowed accuracy due to flaky accuracy values * The test also runs for windows machines * Changed num_batches_per_epoch to 3 This was discussed [here](https://github.com/awslabs/gluon-ts/pull/793#discussion_r416680005)
1 parent ed06add
File | Mode | Size |
---|---|---|
.devtools | ||
.github | ||
ci | ||
docs | ||
env | ||
evaluations | ||
examples | ||
requirements | ||
src | ||
test | ||
.dockerignore | -rw-r--r-- | 178 bytes |
.gitignore | -rw-r--r-- | 1.8 KB |
.pylintrc | -rw-r--r-- | 14.7 KB |
.travis.yml | -rw-r--r-- | 901 bytes |
CODE_OF_CONDUCT.md | -rw-r--r-- | 309 bytes |
CONTRIBUTING.md | -rw-r--r-- | 5.0 KB |
Dockerfile | -rw-r--r-- | 111 bytes |
Dockerfile.gpu | -rw-r--r-- | 724 bytes |
LICENSE | -rw-r--r-- | 9.9 KB |
MANIFEST.in | -rw-r--r-- | 39 bytes |
Makefile | -rw-r--r-- | 2.3 KB |
NOTICE | -rw-r--r-- | 96 bytes |
README.md | -rw-r--r-- | 6.6 KB |
REFERENCES.md | -rw-r--r-- | 7.3 KB |
codecov.yml | -rw-r--r-- | 431 bytes |
conftest.py | -rw-r--r-- | 6.7 KB |
contributor.rst | -rw-r--r-- | 1.3 KB |
dev_setup.sh | -rwxr-xr-x | 1.4 KB |
pyproject.toml | -rw-r--r-- | 30 bytes |
pytest.ini | -rw-r--r-- | 369 bytes |
setup.cfg | -rw-r--r-- | 290 bytes |
setup.py | -rw-r--r-- | 7.5 KB |
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...