justinttl / deep3d-tf Goto Github PK

Hi!

I have finished some training on the Deep3D_TF Network based on the VGG19.npy(https://mega.nz/#!xZ8glS6J!MAnE91ND_WyfZ_8mvkuSa2YcA7q-1ehfSm-Q1fxOvvs), but the result is always unsatisfying: the result image is misty especial the background...

So can you help to provide your trained npy file?

Thank you!

I ran the code based on vgg19 weights and got this error. Could you please help me on this ?

OutOfRangeError (see above for traceback): RandomShuffleQueue '_2_shuffle_batch/random_shuffle_queue' is closed and has insufficient elements (requested 30, current size 0)
[[Node: shuffle_batch = QueueDequeueManyV2[component_types=[DT_FLOAT, DT_FLOAT], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/device:CPU:0"](shuffle_batch/random_shuffle_queue, shuffle_batch/n)]]

ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[23040 ,4096] and type float - This is the error obtained on NVIDIA GeForce 10 series GPU. The immediate fix involves training in batches but it is already being done. What would you suggest would be the fix for the issue?
Also, could you please provide your utils file?

Thank you!