NLUT

NLUT copied to clipboard

加载下载的预训练模型时报错 Unexpected key(s) in state_dict: "blurer.op.1.weight", "SB1.conv1.conv2d.weight", "SB1.conv1.conv2d.bias", "SB1.conv1.bn.weight", "SB1.conv1.bn.bias", "SB1.conv1.bn.running_mean", "SB1.conv1.bn.running_var", "SB1.conv1.bn.num_batches_tracked", "SB1.conv2.conv2d.weight", "SB1.conv2.conv2d.bias", "SB1.conv2.bn.weight", "SB1.conv2.bn.bias", "SB1.conv2.bn.running_mean", "SB1.conv2.bn.running_var", "SB1.conv2.bn.num_batches_tracked". ，经检查 NLUTNet 模型定义时确实没有 blurer 和 SB1 相关的定义，辛苦作者 check 下代码和参数文件，谢谢！

unihornWwan

ImportError: libtorch_cuda_cu.so: cannot open shared object file: No such file or directory

xh-2000

inference_finetuning_image

1

inference_finetuning_image 没起作用 保存的图 跟原图没有任何区别

qijunf

FileNotFoundError: [Errno 2] No such file or directory: './finetuning_train/checkpoint/9_finetuning_style_lut.pth'

qijunf

iter 3700 time/iter: 0.50 lr: 0.000100 loss_mn: 0.0016 loss_c: 0.5781 loss_s: 2.8997 loss_mse: 0.0280 losses: 3.4793 iter 3800 time/iter: 0.50 lr: 0.000100 loss_mn: 0.0016 loss_c: 0.5784 loss_s: 2.9005 loss_mse: 0.0281...

luck111111111111111

请问为什么会出现nan的问题呀 iter 3500 time/iter: 0.50 lr: 0.000100 loss_mn: 0.0015 loss_c: 0.5787 loss_s: 2.9061 loss_mse: 0.0281 losses: 3.4864 iter 3600 time/iter: 0.50 lr: 0.000100 loss_mn: 0.0015 loss_c: 0.5785 loss_s: 2.9014 loss_mse:...

luck111111111111111

inference

1

How can just inference the model after finetuning I do not want each test to do finetuning?

maralzar

cube file

1

Any chance I can save a cube file from the LUT computed by the model?

darkzbaron

pre-trained checkpoint can not download

1

Hello, Thank you for sharing the code and weight .unfortunately, your pre-trained checkpoint can not download because it needs registration and this site can not allow overseas countries. could you...

maralzar