when i modify the data/cnn_model/Zeiler_spm_scale224_test_conv5.prototxt according to the caffe.proto file in your SPP_net branch in the caffe fork,it can not copy model from the file Zeiler_conv5 model file ,and i get the following error ,
net.cpp:710] Ignoring source layer ImageNet
net.cpp:713] Copying source layer conv1
net.cpp:716] Check failed: target_blobs.size() == source_layer.blobs_size() (2 vs. 0) Incompatible number of blobs for layer conv1
the modified prototxt is like this:
layers {
name: "conv1"
type: CONVOLUTION
convolution_param{
num_output: 96
kernel_size: 7
pad: 1
stride: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
blobs_lr: 1.0
blobs_lr: 2.0
bottom: "data"
top: "conv1"
}
the model file does not match the prototxt file ?
Thanks!
when i modify the data/cnn_model/Zeiler_spm_scale224_test_conv5.prototxt according to the caffe.proto file in your SPP_net branch in the caffe fork,it can not copy model from the file Zeiler_conv5 model file ,and i get the following error , net.cpp:710] Ignoring source layer ImageNet net.cpp:713] Copying source layer conv1 net.cpp:716] Check failed: target_blobs.size() == source_layer.blobs_size() (2 vs. 0) Incompatible number of blobs for layer conv1
the modified prototxt is like this:
layers { name: "conv1" type: CONVOLUTION convolution_param{ num_output: 96 kernel_size: 7 pad: 1 stride: 2 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0 } } blobs_lr: 1.0 blobs_lr: 2.0 bottom: "data" top: "conv1" } the model file does not match the prototxt file ? Thanks!