Quantcast
Channel: TAO Toolkit - NVIDIA Developer Forums
Viewing all articles
Browse latest Browse all 497

Training poseclassification net with custom data

$
0
0

Please provide the following information when requesting support.

• Hardware (T4/V100/Xavier/Nano/etc) RTX4080
• Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc) poseclassificationnet
• TLT Version (Please run “tlt info --verbose” and share “docker_tag” here) nvcr.io/nvidia/tao/tao-toolkit:5.3.0-pyt

If I retrain with pretrained model “st-gcn_3dbp_nvidia.tlt”, I have size mismatch error.

size mismatch for fcn.weight: copying a param with shape torch.Size([6, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([4, 256, 1, 1]).
	size mismatch for fcn.bias: copying a param with shape torch.Size([6]) from checkpoint, the shape in current model is torch.Size([4]).

Customized data can’t use pretrained model?

1 post - 1 participant

Read full topic


Viewing all articles
Browse latest Browse all 497

Trending Articles