Tanmay Gupta
Tanmay Gupta
Running mask-rcnn to compute these features takes some time. It would be great if you could provide these features to download and use directly. Thanks!
Would be great to have a README for cache directory similar to data/README.md! You could also provide all necessary download links in these READMEs so that one does not have...
The provided Mask rcnn feature extraction scripts used in Training step 2 assume the following structure ``` data |--images |--mscoco |--images (this second images folder is missing in the README)...
Config files for machine learning projects can often get quite long (data paths, model config, training hyper-parameters). In past projects, I have used frameworks like [Hydra](https://github.com/facebookresearch/hydra) to compose smaller config...
What is the recommended way to recache a step? I tried deleting the cached file and re-running as recommended by the error message, but I keep getting the following error:
Fixes #487 **Changes proposed in this pull request:** Lightly modified version of code pointed by @epwalsh [here](https://github.com/allenai/tango/blob/65f699d6b67a5afc05282cee1d190b8a30462328/tango/__main__.py#L797-L836) Adds the ability to display the executor output. Can be used as follows:...
I have been trying to use [Hydra](https://hydra.cc/docs/intro/) for config management (more flexible command line interface) and therefore create step graphs and register runs & workspaces programmatically as follows: ```python @hydra.main(version_base=None,config_path="./exp_configs",...
Hi, Thanks for the contribution! It would be great if you (or anybody in the community) could provide a summary of the major differences between the APIs in the 2...