weights/NLCDetection weight-loading fails about hifi_ifdl HOT 7 CLOSED

@JulieChoo @pabberpe
the localization_only file is HiFi_Net_loc.py, which calls models/NLCDetection_loc.py, and the corresponding weights can be found here
the localization and detection file is HiFi_Net.py, which calls models/NLCDetection_api.py. The corresponding weights are sitting here
Let me know if this can solve your concerns.

from hifi_ifdl.

@JulieChoo @pabberpe the localization_only file is HiFi_Net_loc.py, which calls models/NLCDetection_loc.py, and the corresponding weights can be found here
the localization and detection file is HiFi_Net.py, which calls models/NLCDetection_api.py. The corresponding weights are sitting here
Let me know if this can solve your concerns.

This solved my issue. I hadn't seen there were two different download links. Thank you!

from hifi_ifdl.

@JulieChoo @pabberpe If you are only doing localization on dataset such as CASIA, please follow this loc. if you want to produce result on HiFi-IFDL dataset, please go to det_and_loc, which uses different data preprocessing steps.

Hello author, thank you for your efforts and reply. I solved the problem and can visualize the results on the CASIA dataset.

from hifi_ifdl.

I have encountered the same problem, When removing the try/except block it returns the following error:

RuntimeError: Error(s) in loading state_dict for DataParallel: Missing key(s) in state_dict: "module.getmask.getmask.0.weight", "module.getmask.getmask.0.bias", "module.getmask.getmask.2.weight", "module.getmask.getmask.2.bias". Unexpected key(s) in state_dict: "module.FPN_LOC.smooth_s4.0.weight", "module.FPN_LOC.smooth_s4.0.bias", "module.FPN_LOC.smooth_s4.1.weight", "module.FPN_LOC.smooth_s4.1.bias", "module.FPN_LOC.smooth_s3.0.weight", "module.FPN_LOC.smooth_s3.0.bias", "module.FPN_LOC.smooth_s3.1.weight", "module.FPN_LOC.smooth_s3.1.bias", "module.FPN_LOC.smooth_s2.0.weight", "module.FPN_LOC.smooth_s2.0.bias", "module.FPN_LOC.smooth_s2.1.weight", "module.FPN_LOC.smooth_s2.1.bias", "module.FPN_LOC.smooth_s1.0.weight", "module.FPN_LOC.smooth_s1.0.bias", "module.FPN_LOC.smooth_s1.1.weight", "module.FPN_LOC.smooth_s1.1.bias", "module.FPN_LOC.fpn1.0.weight", "module.FPN_LOC.fpn1.1.weight", "module.FPN_LOC.fpn1.1.bias", "module.FPN_LOC.fpn1.1.running_mean", "module.FPN_LOC.fpn1.1.running_var", "module.FPN_LOC.fpn1.1.num_batches_tracked", "module.FPN_LOC.fpn2.0.weight", "module.FPN_LOC.fpn2.1.weight", "module.FPN_LOC.fpn2.1.bias", "module.FPN_LOC.fpn2.1.running_mean", "module.FPN_LOC.fpn2.1.running_var", "module.FPN_LOC.fpn2.1.num_batches_tracked", "module.FPN_LOC.fpn3.0.weight", "module.FPN_LOC.fpn3.1.weight", "module.FPN_LOC.fpn3.1.bias", "module.FPN_LOC.fpn3.1.running_mean", "module.FPN_LOC.fpn3.1.running_var", "module.FPN_LOC.fpn3.1.num_batches_tracked", "module.FPN_LOC.fpn4.0.weight", "module.FPN_LOC.fpn4.1.weight", "module.FPN_LOC.fpn4.1.bias", "module.FPN_LOC.fpn4.1.running_mean", "module.FPN_LOC.fpn4.1.running_var", "module.FPN_LOC.fpn4.1.num_batches_tracked", "module.getmask.conv_1.weight", "module.getmask.conv_1.bias", "module.getmask.conv_2.weight", "module.getmask.conv_2.bias". size mismatch for module.getmask.g.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([288, 288, 1, 1]). size mismatch for module.getmask.g.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([288]). size mismatch for module.getmask.theta.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([288, 288, 1, 1]). size mismatch for module.getmask.theta.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([288]). size mismatch for module.getmask.phi.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([288, 288, 1, 1]). size mismatch for module.getmask.phi.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([288]). size mismatch for module.getmask.W_s.weight: copying a param with shape torch.Size([64, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([18, 18, 1, 1]). size mismatch for module.getmask.W_s.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([18]). size mismatch for module.branch_cls_level_1.branch_cls.0.weight: copying a param with shape torch.Size([32, 317, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 271, 3, 3]).

from hifi_ifdl.

Hello author, thank you for your reply. I followed the steps here and used the corresponding weights to get the visualization. But when I use Casiav1's forged images for visualization, the effect I get is not good. May I ask where I went wrong?

from hifi_ifdl.

@JulieChoo @pabberpe
If you are only doing localization on dataset such as CASIA, please follow this loc.
if you want to produce result on HiFi-IFDL dataset, please go to det_and_loc, which uses different data preprocessing steps.

from hifi_ifdl.

@JulieChoo In fact, you can find both numerical results csv file and visualization in the same section.

from hifi_ifdl.