Support batches for CPPN image representation

[shaibagon]

When representing the optimized image using CPPN network, current implementation allows for optimizing for a single image per run. This limitation prevents using, e.g., "diversity" objectives during optimization. This PR adds support for batching for cppn image representation by creating a batch of networks.

here's an example of generating a diverse batch=2 images for objective "mixed4d_3x3_bottleneck_pre_relu_conv:139" of inception network.