self.variance = cfg['variance']

[pjg205]

Hi, I run this code with my custom dataset. I add this(from data.config import custom_voc as cfg) on the top of eval.py and detection.py. However, it didn't work. Is there any clue to solve this error?

VGG base: [Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)), ReLU(inplace=True), Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)), ReLU(inplace=True), MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False), Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)), ReLU(inplace=True), Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)), ReLU(inplace=True), MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False), Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)), ReLU(inplace=True), Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)), ReLU(inplace=True), Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)), ReLU(inplace=True), MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=True), Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)), ReLU(inplace=True), Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)), ReLU(inplace=True), Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)), ReLU(inplace=True), MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False), Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)), ReLU(inplace=True), Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)), ReLU(inplace=True), Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)), ReLU(inplace=True), MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False), Conv2d(512, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(6, 6), dilation=(6, 6)), ReLU(inplace=True), Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1)), ReLU(inplace=True)] input channels: 128 extras layers: [Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1)), Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1)), Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)), Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1)), Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1)), Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1)), Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1)), Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1)), Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1)), Conv2d(128, 256, kernel_size=(4, 4), stride=(1, 1), padding=(1, 1))] VGG16 output size: 35 extra layer size: 10 extra layer 0 : Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1)) extra layer 1 : Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1)) extra layer 2 : Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) extra layer 3 : Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1)) extra layer 4 : Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1)) extra layer 5 : Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1)) extra layer 6 : Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1)) extra layer 7 : Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1)) extra layer 8 : Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1)) extra layer 9 : Conv2d(128, 256, kernel_size=(4, 4), stride=(1, 1), padding=(1, 1)) Begin to build SSD-VGG...

Finished loading model! torch.Size([1, 417044]) 17 torch.Size([1, 24532, 17]) Traceback (most recent call last): File "eval.py", line 436, in test_net(args.save_folder, net, args.cuda, dataset, File "eval.py", line 385, in test_net detections = net(x).data File "/opt/conda/envs/prac/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, **kwargs) File "/data/SSD.Pytorch/ssd.py", line 105, in forward output = self.detect.apply(17, 0, 200, 0.01, 0.45, File "/data/SSD.Pytorch/layers/functions/detection.py", line 117, in forward self.variance = cfg['variance'] KeyError: 'variance'