Donald May

Yes I have. The real secret is for the end parameter you need to specify the layer name from the blob list that you want to use. The "higher" layers...

Here is a sample json that works with the googlenet_places205 dataset: { "model_path": "/home/vagrant/caffe/models/googlenet_places205/", "prototxt": "deploy_places205.protxt", "caffemodel": "googlelet_places205_train_iter_2400000.caffemodel", "image_mean": [104.0, 116.0, 122.0], "end": "inception_4d/output" }

Hello Tildebyte, The error you are seeing is not expected. I do not see that error on my end, so I find it quite odd. Creating a repo is not...

I opted to use JSON because I could represent the image mean list could be directly represented in the JSON instead of having to parse it out. Also I think...

Are you using ConfigParser or SafeConfigParser? Also I think the concept of mean needs to be looked at, because there are mean files potentially in the models themselves that are...