vfdev

README example is failing with "RuntimeError: input.size(-1) must be equal to input_size"

4

Hi, I'm executing the following code from the README and ```python import pandas as pd import matplotlib.pyplot as plt import torch print(torch.__version__) import gluonts from gluonts.dataset.common import ListDataset from gluonts.dataset.util...

## Description: OpenAI Gym changed the way to check if observation_space contains the observation, https://github.com/openai/gym/pull/2374 and thus tasks like `cartpole_discrete_balancing.py` are not working anymore due to float64 vs float32 inconsistent...

Hi Andreas, Thanks for the code! I wonder what do you think if it could be feasible to extend this method to image segmentation task (taking as a base this...

Code improvements

3

Hi @sally20921 As discussed before, I create an issue here to simplify the code: 1) Metrics. In Ignite we already have all necessary metrics. Please, take a look here: -...

Socket can't receive data in `discover_from_uuid_local`

1

I'm using Argus 3 Pro and trying to get the stream from this camera using neolink built from source on MacOSX. Discovery globally fails with messages like in https://github.com/thirtythreeforty/neolink/issues/293 While...

Description: - Fixed removal nvidia-ml.list Check list: - [ ] New tests are added (if a new feature is added) - [ ] New doc strings: description and/or example code...

CI test with Hvd, tests/ignite/metrics/test_recall.py::test_distrib_hvd - core dumped

1

Flaky core dump errors: - tests/ignite/metrics/test_recall.py::test_distrib_hvd - tests/ignite/metrics/test_ssim.py::test_distrib_hvd - tests/ignite/metrics/test_precision.py::test_distrib_hvd

Improvements for resuming from terminated engine

1

Current Engine's behaviour when we resume the run from terminated state is the following: ```python from ignite.engine import Engine, Events from ignite.utils import setup_logger, logging def func(engine, batch): print(engine.state.epoch, engine.state.iteration,...

[proto] Fixed fill type in AA

2

Description: - Fixed fill type in AA

Fill arg and _apply_grid_transform improvements

3

Few years ago we introduced non-const fill value handling in `_apply_grid_transform` using mask approach: https://github.com/pytorch/vision/blob/0d69e35c4e951109dbaa8b42b0a8416d199aee0b/torchvision/transforms/functional_tensor.py#L550-L568 There are few minor problems with this approach: 1) if we pass `fill = [0.0,...