Reuse data memory if not propagate down

[Cysu]

Make a dry-run of forward pass. If some layer does not propagate down (or during test phase), reuse its top blob's data memory.

Change the keys from blob address to blob_name + "_data" (or "_diff") in the slot array.

Add to NetParameter an option optimize_mem that controls the memory optimization strategy. It has three enum values:

• NO_OPTIM: no memory optimization
• TRAIN_ONLY: only optimize forward and backward blobs memory during training phase
• ALL_OPTIM: optimize for both the training and test phase

It is set to TRAIN_ONLY by default. Note that using the memory optimization may corrupt internal blobs data/diff. So you may wish to use NO_OPTIM for feature extraction.

[yjxiong]

Looks good to me! Please proceed.

[yjxiong]

Thanks a lot!