permosegaard / faceswap-aws Goto Github PK

AWS P2 instance might be the best way to go for training the model...

Can you post a link to the demo results (gif/mp4)? Some folks might want to see the quality of results before paying for AWS...

Example replacing nic cage as neo in the matrix.

I posted two of my results from running convert on my Nvidia TX1 (GPU).

Thanks.

python faceswap.py convert -i ~/faceswap/photo/trump/ -o ~/faceswap/output/ -m ~/faceswap/models/
Using TensorFlow backend.
Input Directory: /home/nvidia/faceswap/photo/trump
Output Directory: /home/nvidia/faceswap/output
Starting, this may take a while...
2018-02-01 00:19:08.897026: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:857] ARM64 does not support NUMA - returning NUMA node zero
2018-02-01 00:19:08.897206: I tensorflow/core/common_runtime/gpu/gpu_device.cc:955] Found device 0 with properties:
name: NVIDIA Tegra X1
major: 5 minor: 3 memoryClockRate (GHz) 0.9984
pciBusID 0000:00:00.0
Total memory: 3.89GiB
Free memory: 1010.12MiB
2018-02-01 00:19:08.897284: I tensorflow/core/common_runtime/gpu/gpu_device.cc:976] DMA: 0
2018-02-01 00:19:08.897339: I tensorflow/core/common_runtime/gpu/gpu_device.cc:986] 0: Y
2018-02-01 00:19:08.897401: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1045] Creating TensorFlow device (/gpu:0) -> (device: 0, name: NVIDIA Tegra X1, pci bus id: 0000:00:00.0)
2018-02-01 00:19:59.365563: W tensorflow/core/common_runtime/bfc_allocator.cc:217] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.14GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory is available.
2018-02-01 00:19:59.413316: W tensorflow/core/common_runtime/bfc_allocator.cc:217] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.13GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory is available.
2018-02-01 00:19:59.453769: W tensorflow/core/common_runtime/bfc_allocator.cc:217] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.07GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory is available.
2018-02-01 00:19:59.453875: W tensorflow/core/common_runtime/bfc_allocator.cc:217] Allocator (GPU_0_bfc) ran out of memory trying to allocate 547.21MiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory is available.
2018-02-01 00:19:59.475675: W tensorflow/core/common_runtime/bfc_allocator.cc:217] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.04GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory is available.

Images found: 376
Images processed: 376
Faces detected: 308

Done!