Hi, everyone, I have a problem of net.children:
I have got a pretrained model but it has only one child as following:
BNInception (
(conv1_7x7_s2): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3))
(conv1_7x7_s2_bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
(conv1_relu_7x7): ReLU (inplace)
(pool1_3x3_s2): MaxPool2d (size=(3, 3), stride=(2, 2), dilation=(1, 1))
(conv2_3x3_reduce): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1))
(conv2_3x3_reduce_bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
(conv2_relu_3x3_reduce): ReLU (inplace)
(conv2_3x3): Conv2d(64, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2_3x3_bn): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True)
(conv2_relu_3x3): ReLU (inplace)
(pool2_3x3_s2): MaxPool2d (size=(3, 3), stride=(2, 2), dilation=(1, 1))
(inception_3a_1x1): Conv2d(192, 64, kernel_size=(1, 1), stride=(1, 1))
(inception_3a_1x1_bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
(inception_3a_relu_1x1): ReLU (inplace)
…
))
Then, how can I get output of immediate layer in this situation?
please help me, thank you!