I have been working on tweaking a model that I created, It was trained on about 1000 images of mountains, forests, hills, cityscapes, um, deserts, and beaches. I am still fine-tuning variables, but here are the results so far. This was run on an image of random noise.
''
Sum nurd stuff
deploy.prototxt
name: "R-CNN-ilsvrc13" input: "data" input_dim: 10 input_dim: 3 input_dim: 227 input_dim: 227 layer { name: "conv1" type: "Convolution" bottom: "data" top: "conv1" convol