Deivanayaki-S opened a new pull request, #17921: URL: https://github.com/apache/tvm/pull/17921
This PR adds support for avg_pool1d and avg_pool3d operations, extending the existing avg_pool2d functionality to handle 1D and 3D pooling. It includes the necessary mappings, and comprehensive tests for these new operations. Additionally, avgpool2d was refactored to match the result of pytorch implementation. By adding this support, the following models are now able to run successfully. 1. X3D 2. 3D ResNet 3. DGurgurov/im2latex (Image-To-Text) 4. microsoft/swin-tiny-patch4-window7-224 (Image Classification) 5. jonathandinu/face-parsing (Image Segmentation) -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
