umich-curly / 3dmapping Goto Github PK

When I tried to run LMSC, I changed the model_name = "LMSC" and MODEL_PATH = 'Models/Weights/LMSC_11_T1B/Epoch19.pt',
however, it shows the following runtimeError.

Can you help? Thanks!
Tao

RuntimeError: Error(s) in loading state_dict for LMSCNet_SS:
size mismatch for Encoder_block1.0.weight: copying a param with shape torch.Size([8, 8, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 32, 3, 3]).
size mismatch for Encoder_block1.0.bias: copying a param with shape torch.Size([8]) from checkpoint, the shape in current model is torch.Size([32]).
size mismatch for Encoder_block1.2.weight: copying a param with shape torch.Size([8, 8, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 32, 3, 3]).
size mismatch for Encoder_block1.2.bias: copying a param with shape torch.Size([8]) from checkpoint, the shape in current model is torch.Size([32]).
size mismatch for Encoder_block2.1.weight: copying a param with shape torch.Size([12, 8, 3, 3]) from checkpoint, the shape in current model is torch.Size([48, 32, 3, 3]).
size mismatch for Encoder_block2.1.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([48]).
size mismatch for Encoder_block2.3.weight: copying a param with shape torch.Size([12, 12, 3, 3]) from checkpoint, the shape in current model is torch.Size([48, 48, 3, 3]).
size mismatch for Encoder_block2.3.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([48]).
size mismatch for Encoder_block3.1.weight: copying a param with shape torch.Size([16, 12, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 48, 3, 3]).
size mismatch for Encoder_block3.1.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for Encoder_block3.3.weight: copying a param with shape torch.Size([16, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 3, 3]).
size mismatch for Encoder_block3.3.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for Encoder_block4.1.weight: copying a param with shape torch.Size([20, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([80, 64, 3, 3]).
size mismatch for Encoder_block4.1.bias: copying a param with shape torch.Size([20]) from checkpoint, the shape in current model is torch.Size([80]).
size mismatch for Encoder_block4.3.weight: copying a param with shape torch.Size([20, 20, 3, 3]) from checkpoint, the shape in current model is torch.Size([80, 80, 3, 3]).
size mismatch for Encoder_block4.3.bias: copying a param with shape torch.Size([20]) from checkpoint, the shape in current model is torch.Size([80]).
size mismatch for conv_out_scale_1_8.weight: copying a param with shape torch.Size([1, 20, 3, 3]) from checkpoint, the shape in current model is torch.Size([4, 80, 3, 3]).
size mismatch for conv_out_scale_1_8.bias: copying a param with shape torch.Size([1]) from checkpoint, the shape in current model is torch.Size([4]).
size mismatch for deconv_1_8__1_2.weight: copying a param with shape torch.Size([1, 1, 4, 4]) from checkpoint, the shape in current model is torch.Size([4, 4, 4, 4]).
size mismatch for deconv_1_8__1_2.bias: copying a param with shape torch.Size([1]) from checkpoint, the shape in current model is torch.Size([4]).
size mismatch for deconv_1_8__1_1.weight: copying a param with shape torch.Size([1, 1, 8, 8]) from checkpoint, the shape in current model is torch.Size([4, 4, 8, 8]).
size mismatch for deconv_1_8__1_1.bias: copying a param with shape torch.Size([1]) from checkpoint, the shape in current model is torch.Size([4]).
size mismatch for deconv1_8.weight: copying a param with shape torch.Size([1, 1, 6, 6]) from checkpoint, the shape in current model is torch.Size([4, 4, 6, 6]).
size mismatch for deconv1_8.bias: copying a param with shape torch.Size([1]) from checkpoint, the shape in current model is torch.Size([4]).
size mismatch for conv1_4.weight: copying a param with shape torch.Size([16, 17, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 68, 3, 3]).
size mismatch for conv1_4.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for conv_out_scale_1_4.weight: copying a param with shape torch.Size([2, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([8, 64, 3, 3]).
size mismatch for conv_out_scale_1_4.bias: copying a param with shape torch.Size([2]) from checkpoint, the shape in current model is torch.Size([8]).
size mismatch for deconv_1_4__1_1.weight: copying a param with shape torch.Size([2, 2, 4, 4]) from checkpoint, the shape in current model is torch.Size([8, 8, 4, 4]).
size mismatch for deconv_1_4__1_1.bias: copying a param with shape torch.Size([2]) from checkpoint, the shape in current model is torch.Size([8]).
size mismatch for deconv1_4.weight: copying a param with shape torch.Size([2, 2, 6, 6]) from checkpoint, the shape in current model is torch.Size([8, 8, 6, 6]).
size mismatch for deconv1_4.bias: copying a param with shape torch.Size([2]) from checkpoint, the shape in current model is torch.Size([8]).
size mismatch for conv1_2.weight: copying a param with shape torch.Size([12, 15, 3, 3]) from checkpoint, the shape in current model is torch.Size([48, 60, 3, 3]).
size mismatch for conv1_2.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([48]).
size mismatch for conv_out_scale_1_2.weight: copying a param with shape torch.Size([4, 12, 3, 3]) from checkpoint, the shape in current model is torch.Size([16, 48, 3, 3]).
size mismatch for conv_out_scale_1_2.bias: copying a param with shape torch.Size([4]) from checkpoint, the shape in current model is torch.Size([16]).
size mismatch for deconv1_2.weight: copying a param with shape torch.Size([4, 4, 6, 6]) from checkpoint, the shape in current model is torch.Size([16, 16, 6, 6]).
size mismatch for deconv1_2.bias: copying a param with shape torch.Size([4]) from checkpoint, the shape in current model is torch.Size([16]).
size mismatch for conv1_1.weight: copying a param with shape torch.Size([8, 15, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 60, 3, 3]).
size mismatch for conv1_1.bias: copying a param with shape torch.Size([8]) from checkpoint, the shape in current model is torch.Size([32]).
size mismatch for seg_head_1_1.conv_classes.weight: copying a param with shape torch.Size([11, 8, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([20, 8, 3, 3, 3]).
size mismatch for seg_head_1_1.conv_classes.bias: copying a param with shape torch.Size([11]) from checkpoint, the shape in current model is torch.Size([20]).

Hello, could you please provide the BEV camera Setting (for example intrinsic or extrinsic matrix) for CarlaSC dataset?