getting this error when run with e2e_keypoint_rcnn_X-101-32x8d-FPN_s1x model.
load_detectron_weight(maskRCNN, load_detectron) File "/datadrive/Shridhar/detectron/mask-rcnn.pytorch/lib/utils/detectron_weight_helper.py", line 22, in load_detectron_weight p_tensor.copy_(torch.Tensor(src_blobs[d_name])) RuntimeError: The expanded size of the tensor (1024) must match the existing size (256) at non-singleton dimension 0
Where as ResNet model works flawlesly.
Does it supports ResNext models so far?
Thanks
getting this error when run with e2e_keypoint_rcnn_X-101-32x8d-FPN_s1x model.
load_detectron_weight(maskRCNN, load_detectron) File "/datadrive/Shridhar/detectron/mask-rcnn.pytorch/lib/utils/detectron_weight_helper.py", line 22, in load_detectron_weight p_tensor.copy_(torch.Tensor(src_blobs[d_name])) RuntimeError: The expanded size of the tensor (1024) must match the existing size (256) at non-singleton dimension 0
Where as ResNet model works flawlesly. Does it supports ResNext models so far? Thanks