Dtype rate = GetLearningRate();
Dtype momentum = this->param_.momentum();
Dtype weight_decay = this->param_.weight_decay();
- LOG(ERROR) << "rate:" << rate << " momentum:" << momentum
- << " weight_decay:" << weight_decay;
+ // LOG(ERROR) << "rate:" << rate << " momentum:" << momentum
+ // << " weight_decay:" << weight_decay;
switch (Caffe::mode()) {
case Caffe::CPU:
for (int param_id = 0; param_id < net_params.size(); ++param_id) {
layer.SetUp(bottom, &top);
// LOG(ERROR) << "Exhaustive Mode.";
for (int i = 0; i < top.size(); ++i) {
- LOG(ERROR) << "Exhaustive: blob " << i << " size " << top[i]->count();
+ // LOG(ERROR) << "Exhaustive: blob " << i << " size " << top[i]->count();
for (int j = 0; j < top[i]->count(); ++j) {
// LOG(ERROR) << "Exhaustive: blob " << i << " data " << j;
CheckGradientSingle(layer, bottom, top, check_bottom, i, j);
EXPECT_EQ(caffe_net.layer_names().size(), 10);
EXPECT_EQ(caffe_net.blob_names().size(), 10);
+ /*
// Print a few statistics to see if things are correct
for (int i = 0; i < caffe_net.blobs().size(); ++i) {
LOG(ERROR) << "Blob: " << caffe_net.blob_names()[i];
<< caffe_net.blobs()[i]->height() << ", "
<< caffe_net.blobs()[i]->width();
}
+ */
Caffe::set_mode(Caffe::CPU);
// Run the network without training.
LOG(ERROR) << "Performing Forward";
caffe_net.Forward(bottom_vec);
LOG(ERROR) << "Performing Backward";
LOG(ERROR) << caffe_net.Backward();
-
+
Caffe::set_mode(Caffe::GPU);
// Run the network without training.
LOG(ERROR) << "Performing Forward";