search

Deeachain / Segmentation-Pytorch

Semantic Segmentation in Pytorch. Network include: FCN、FCN_ResNet、SegNet、UNet、BiSeNet、BiSeNetV2、PSPNet、DeepLabv3_plus、 HRNet、DDRNet
459 stars 69 forks source link

Making inference from a pretrained HRNet? #29

Open Ainecop opened 1 year ago

Ainecop commented 1 year ago

Great Work. I was wondering How can I make inference from a pretrained HRNet. Please do provide a pretrained HRNet model or provide the link as the dimensions are mismatching when i downloaded hrnet pretrained from HRNet official. What parameters do you set for pretrained HRNet ? Waiting for a positive response.

Ainecop commented 1 year ago 
    size mismatch for transition1.1.0.1.running_mean: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([64]).
    size mismatch for transition1.1.0.1.running_var: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([64]).
    size mismatch for stage2.0.branches.0.0.conv1.weight: copying a param with shape torch.Size([48, 48, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 32, 1, 1]).
    size mismatch for stage2.0.branches.0.0.bn1.weight: copying a param with shape torch.Size([48]) from checkpoint, the shape in current

model is torch.Size([32]). size mismatch for stage2.0.branches.0.0.bn1.bias: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for stage2.0.branches.0.0.bn1.running_mean: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for stage2.0.branches.0.0.bn1.running_var: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for stage2.0.branches.0.0.conv2.weight: copying a param with shape torch.Size([48, 48, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 32, 3, 3]). size mismatch for stage2.0.branches.0.0.bn2.weight: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for stage2.0.branches.0.0.bn2.bias: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for stage2.0.branches.0.0.bn2.running_mean: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for stage2.0.branches.0.0.bn2.running_var: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([32]).