Surprise! We've been running on hardware provided by BuyVM for a few months and wanted to show them a little appreciation.
Running a paste site comes with unique challenges, ones that aren't always obvious and hard to control. As such, BuyVM offered us a home where we could worry less about the hosting side of things and focus on maintaining a clean and useful service! Go check them out and show them some love!
Description: Pytorch :fused model cant be loaded becasue the parameters are different from the checkpoint
Submitted on January 28, 2020 at 06:05 AM

Download - Report

New Paste 1 (Text)

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657 
RuntimeError: Error(s) in loading state_dict for RetinaFace:
        While copying the parameter named "body.stage1.0.0.weight", whose dimensions in the model are torch.Size([8, 3, 3, 3]) and whose dimensions in the checkpoint are torch.Size([8, 3, 3, 3]).
        While copying the parameter named "body.stage1.1.0.weight", whose dimensions in the model are torch.Size([8, 1, 3, 3]) and whose dimensions in the checkpoint are torch.Size([8, 1, 3, 3]).
        While copying the parameter named "body.stage1.1.3.weight", whose dimensions in the model are torch.Size([16, 8, 1, 1]) and whose dimensions in the checkpoint are torch.Size([16, 8, 1, 1]).
        While copying the parameter named "body.stage1.2.0.weight", whose dimensions in the model are torch.Size([16, 1, 3, 3]) and whose dimensions in the checkpoint are torch.Size([16, 1, 3, 3]).
        While copying the parameter named "body.stage1.2.3.weight", whose dimensions in the model are torch.Size([32, 16, 1, 1]) and whose dimensions in the checkpoint are torch.Size([32, 16, 1, 1]).
        While copying the parameter named "body.stage1.3.0.weight", whose dimensions in the model are torch.Size([32, 1, 3, 3]) and whose dimensions in the checkpoint are torch.Size([32, 1, 3, 3]).
        While copying the parameter named "body.stage1.3.3.weight", whose dimensions in the model are torch.Size([32, 32, 1, 1]) and whose dimensions in the checkpoint are torch.Size([32, 32, 1, 1]).
        While copying the parameter named "body.stage1.4.0.weight", whose dimensions in the model are torch.Size([32, 1, 3, 3]) and whose dimensions in the checkpoint are torch.Size([32, 1, 3, 3]).
        While copying the parameter named "body.stage1.4.3.weight", whose dimensions in the model are torch.Size([64, 32, 1, 1]) and whose dimensions in the checkpoint are torch.Size([64, 32, 1, 1]).
        While copying the parameter named "body.stage1.5.0.weight", whose dimensions in the model are torch.Size([64, 1, 3, 3]) and whose dimensions in the checkpoint are torch.Size([64, 1, 3, 3]).
        While copying the parameter named "body.stage1.5.3.weight", whose dimensions in the model are torch.Size([64, 64, 1, 1]) and whose dimensions in the checkpoint are torch.Size([64, 64, 1, 1]).
        While copying the parameter named "body.stage2.0.0.weight", whose dimensions in the model are torch.Size([64, 1, 3, 3]) and whose dimensions in the checkpoint are torch.Size([64, 1, 3, 3]).
        While copying the parameter named "body.stage2.0.3.weight", whose dimensions in the model are torch.Size([128, 64, 1, 1]) and whose dimensions in the checkpoint are torch.Size([128, 64, 1, 1]).
        While copying the parameter named "body.stage2.1.0.weight", whose dimensions in the model are torch.Size([128, 1, 3, 3]) and whose dimensions in the checkpoint are torch.Size([128, 1, 3, 3]).
        While copying the parameter named "body.stage2.1.3.weight", whose dimensions in the model are torch.Size([128, 128, 1, 1]) and whose dimensions in the checkpoint are torch.Size([128, 128, 1, 1]).
        While copying the parameter named "body.stage2.2.0.weight", whose dimensions in the model are torch.Size([128, 1, 3, 3]) and whose dimensions in the checkpoint are torch.Size([128, 1, 3, 3]).
        While copying the parameter named "body.stage2.2.3.weight", whose dimensions in the model are torch.Size([128, 128, 1, 1]) and whose dimensions in the checkpoint are torch.Size([128, 128, 1, 1]).
        While copying the parameter named "body.stage2.3.0.weight", whose dimensions in the model are torch.Size([128, 1, 3, 3]) and whose dimensions in the checkpoint are torch.Size([128, 1, 3, 3]).
        While copying the parameter named "body.stage2.3.3.weight", whose dimensions in the model are torch.Size([128, 128, 1, 1]) and whose dimensions in the checkpoint are torch.Size([128, 128, 1, 1]).
        While copying the parameter named "body.stage2.4.0.weight", whose dimensions in the model are torch.Size([128, 1, 3, 3]) and whose dimensions in the checkpoint are torch.Size([128, 1, 3, 3]).
        While copying the parameter named "body.stage2.4.3.weight", whose dimensions in the model are torch.Size([128, 128, 1, 1]) and whose dimensions in the checkpoint are torch.Size([128, 128, 1, 1]).
        While copying the parameter named "body.stage2.5.0.weight", whose dimensions in the model are torch.Size([128, 1, 3, 3]) and whose dimensions in the checkpoint are torch.Size([128, 1, 3, 3]).
        While copying the parameter named "body.stage2.5.3.weight", whose dimensions in the model are torch.Size([128, 128, 1, 1]) and whose dimensions in the checkpoint are torch.Size([128, 128, 1, 1]).
        While copying the parameter named "body.stage3.0.0.weight", whose dimensions in the model are torch.Size([128, 1, 3, 3]) and whose dimensions in the checkpoint are torch.Size([128, 1, 3, 3]).
        While copying the parameter named "body.stage3.0.3.weight", whose dimensions in the model are torch.Size([256, 128, 1, 1]) and whose dimensions in the checkpoint are torch.Size([256, 128, 1, 1]).
        While copying the parameter named "body.stage3.1.0.weight", whose dimensions in the model are torch.Size([256, 1, 3, 3]) and whose dimensions in the checkpoint are torch.Size([256, 1, 3, 3]).
        While copying the parameter named "body.stage3.1.3.weight", whose dimensions in the model are torch.Size([256, 256, 1, 1]) and whose dimensions in the checkpoint are torch.Size([256, 256, 1, 1]).
        While copying the parameter named "fpn.output1.0.weight", whose dimensions in the model are torch.Size([64, 64, 1, 1]) and whose dimensions in the checkpoint are torch.Size([64, 64, 1, 1]).
        While copying the parameter named "fpn.output2.0.weight", whose dimensions in the model are torch.Size([64, 128, 1, 1]) and whose dimensions in the checkpoint are torch.Size([64, 128, 1, 1]).
        While copying the parameter named "fpn.output3.0.weight", whose dimensions in the model are torch.Size([64, 256, 1, 1]) and whose dimensions in the checkpoint are torch.Size([64, 256, 1, 1]).
        While copying the parameter named "fpn.merge1.0.weight", whose dimensions in the model are torch.Size([64, 64, 3, 3]) and whose dimensions in the checkpoint are torch.Size([64, 64, 3, 3]).
        While copying the parameter named "fpn.merge2.0.weight", whose dimensions in the model are torch.Size([64, 64, 3, 3]) and whose dimensions in the checkpoint are torch.Size([64, 64, 3, 3]).
        While copying the parameter named "ssh1.conv3X3.0.weight", whose dimensions in the model are torch.Size([32, 64, 3, 3]) and whose dimensions in the checkpoint are torch.Size([32, 64, 3, 3]).
        While copying the parameter named "ssh1.conv5X5_1.0.weight", whose dimensions in the model are torch.Size([16, 64, 3, 3]) and whose dimensions in the checkpoint are torch.Size([16, 64, 3, 3]).
        While copying the parameter named "ssh1.conv5X5_2.0.weight", whose dimensions in the model are torch.Size([16, 16, 3, 3]) and whose dimensions in the checkpoint are torch.Size([16, 16, 3, 3]).
        While copying the parameter named "ssh1.conv7X7_2.0.weight", whose dimensions in the model are torch.Size([16, 16, 3, 3]) and whose dimensions in the checkpoint are torch.Size([16, 16, 3, 3]).
        While copying the parameter named "ssh1.conv7x7_3.0.weight", whose dimensions in the model are torch.Size([16, 16, 3, 3]) and whose dimensions in the checkpoint are torch.Size([16, 16, 3, 3]).
        While copying the parameter named "ssh2.conv3X3.0.weight", whose dimensions in the model are torch.Size([32, 64, 3, 3]) and whose dimensions in the checkpoint are torch.Size([32, 64, 3, 3]).
        While copying the parameter named "ssh2.conv5X5_1.0.weight", whose dimensions in the model are torch.Size([16, 64, 3, 3]) and whose dimensions in the checkpoint are torch.Size([16, 64, 3, 3]).
        While copying the parameter named "ssh2.conv5X5_2.0.weight", whose dimensions in the model are torch.Size([16, 16, 3, 3]) and whose dimensions in the checkpoint are torch.Size([16, 16, 3, 3]).
        While copying the parameter named "ssh2.conv7X7_2.0.weight", whose dimensions in the model are torch.Size([16, 16, 3, 3]) and whose dimensions in the checkpoint are torch.Size([16, 16, 3, 3]).
        While copying the parameter named "ssh2.conv7x7_3.0.weight", whose dimensions in the model are torch.Size([16, 16, 3, 3]) and whose dimensions in the checkpoint are torch.Size([16, 16, 3, 3]).
        While copying the parameter named "ssh3.conv3X3.0.weight", whose dimensions in the model are torch.Size([32, 64, 3, 3]) and whose dimensions in the checkpoint are torch.Size([32, 64, 3, 3]).
        While copying the parameter named "ssh3.conv5X5_1.0.weight", whose dimensions in the model are torch.Size([16, 64, 3, 3]) and whose dimensions in the checkpoint are torch.Size([16, 64, 3, 3]).
        While copying the parameter named "ssh3.conv5X5_2.0.weight", whose dimensions in the model are torch.Size([16, 16, 3, 3]) and whose dimensions in the checkpoint are torch.Size([16, 16, 3, 3]).
        While copying the parameter named "ssh3.conv7X7_2.0.weight", whose dimensions in the model are torch.Size([16, 16, 3, 3]) and whose dimensions in the checkpoint are torch.Size([16, 16, 3, 3]).
        While copying the parameter named "ssh3.conv7x7_3.0.weight", whose dimensions in the model are torch.Size([16, 16, 3, 3]) and whose dimensions in the checkpoint are torch.Size([16, 16, 3, 3]).
        While copying the parameter named "ClassHead.0.conv1x1.weight", whose dimensions in the model are torch.Size([4, 64, 1, 1]) and whose dimensions in the checkpoint are torch.Size([4, 64, 1, 1]).
        While copying the parameter named "ClassHead.1.conv1x1.weight", whose dimensions in the model are torch.Size([4, 64, 1, 1]) and whose dimensions in the checkpoint are torch.Size([4, 64, 1, 1]).
        While copying the parameter named "ClassHead.2.conv1x1.weight", whose dimensions in the model are torch.Size([4, 64, 1, 1]) and whose dimensions in the checkpoint are torch.Size([4, 64, 1, 1]).
        While copying the parameter named "BboxHead.0.conv1x1.weight", whose dimensions in the model are torch.Size([8, 64, 1, 1]) and whose dimensions in the checkpoint are torch.Size([8, 64, 1, 1]).
        While copying the parameter named "BboxHead.1.conv1x1.weight", whose dimensions in the model are torch.Size([8, 64, 1, 1]) and whose dimensions in the checkpoint are torch.Size([8, 64, 1, 1]).
        While copying the parameter named "BboxHead.2.conv1x1.weight", whose dimensions in the model are torch.Size([8, 64, 1, 1]) and whose dimensions in the checkpoint are torch.Size([8, 64, 1, 1]).
        While copying the parameter named "LandmarkHead.0.conv1x1.weight", whose dimensions in the model are torch.Size([20, 64, 1, 1]) and whose dimensions in the checkpoint are torch.Size([20, 64, 1, 1]).
        While copying the parameter named "LandmarkHead.1.conv1x1.weight", whose dimensions in the model are torch.Size([20, 64, 1, 1]) and whose dimensions in the checkpoint are torch.Size([20, 64, 1, 1]).
        While copying the parameter named "LandmarkHead.2.conv1x1.weight", whose dimensions in the model are torch.Size([20, 64, 1, 1]) and whose dimensions in the checkpoint are torch.Size([20, 64, 1, 1]).