pytorch
Custom transform support
This PR aims to change the FasterRCNN class to accept custom Transformations from the user, foregoing the generic GeneralizedRCNNTransform as the compulsory transform. Addresses #2263
Edit : I couldn't test this commit locally as I face this error with the bleeding edge version of torchvision. However, a similar implementation works fine with torchvision==0.4.0
Hi @fmassa I've made the changes you've suggested. Let me know what you think. I couldn't test it locally again due to the previously mentioned error. I'm sorry for burdening the CI. Once the builds finish, I will check again if there are errors and fix them
Hi @Sentient07!
Thank you for your pull request.
We require contributors to sign our Contributor License Agreement, and yours needs attention.
You currently have a record in our system, but the CLA is no longer valid, and will need to be resubmitted.
Process
In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.
Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.
If you have received this in error or have any questions, please contact us at [email protected]. Thanks!
