You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Now demo can load new pre-trained file in Pytorch 1.01 and Window 10 environment, thanks for upgrading!
But there is a error message as: "invalid argument 12: dilation should be greater than zero, but got dilationH: 508814473 dilationW: 0 at c:\a\w\1\s\windows\pytorch\aten\src\thcunn\generic/SpatialDilatedMaxPooling.cu:20"
The error is from:
auto [detections, mrcnn_mask] = model->Detect(molded_images, image_metas); => PredictInference(images, image_metas); => PredictRPN(images, config_->post_nms_rois_inference); => fpn_->forward(images); =>x = c1_->forward(x);
I use demo code as is, it seems model and weights are not matched, any clues?
The text was updated successfully, but these errors were encountered:
Sorry, I've tested demo on Linux and everything works in my environment. But I don't have Windows environment to test, it will be nice if you can send a patch to fix this problem.
Now demo can load new pre-trained file in Pytorch 1.01 and Window 10 environment, thanks for upgrading!
But there is a error message as: "invalid argument 12: dilation should be greater than zero, but got dilationH: 508814473 dilationW: 0 at c:\a\w\1\s\windows\pytorch\aten\src\thcunn\generic/SpatialDilatedMaxPooling.cu:20"
The error is from:
auto [detections, mrcnn_mask] = model->Detect(molded_images, image_metas); => PredictInference(images, image_metas); => PredictRPN(images, config_->post_nms_rois_inference); => fpn_->forward(images); =>x = c1_->forward(x);
I use demo code as is, it seems model and weights are not matched, any clues?
The text was updated successfully, but these errors were encountered: