Is train model error?

[sukerlove]

use source: https://github.com/yusuketomoto/chainer-fast-neuralstyle

I get http://msvocds.blob.core.windows.net/coco2014/train2014.zip unzip train2014.zip then

suker@suker:~/chainer-fast-neuralstyle$ python train.py -s rio.jpg -d ./train2014 -g 0 /usr/local/lib/python2.7/dist-packages/pkg_resources/init.py:1298: UserWarning: /home/gtx1080/.python-eggs is writable by group/others and vulnerable to attack when used with get_resource_filename. Consider a more secure location (set with .set_extraction_path or the PYTHON_EGG_CACHE environment variable). warnings.warn(msg, UserWarning) num traning images: 82783 82783 iterations, 2 epochs /usr/local/lib/python2.7/dist-packages/chainer-1.14.0-py2.7-linux-x86_64.egg/chainer/cuda.py:87: UserWarning: cuDNN is not enabled. Please reinstall chainer after you install cudnn (see https://github.com/pfnet/chainer#installation). 'cuDNN is not enabled.\n' epoch 0 (epoch 0) batch 0/82783... training loss is...235437792.0 (epoch 0) batch 1/82783... training loss is...329452736.0 (epoch 0) batch 2/82783... training loss is...154218272.0 (epoch 0) batch 3/82783... training loss is...63537960.0 (epoch 0) batch 4/82783... training loss is...58619268.0 (epoch 0) batch 5/82783... training loss is...55183628.0 (epoch 0) batch 6/82783... training loss is...54082024.0

is operate OK?

after more then 5 hours, the train finish.

the output rio_0.model rio_0.state

rio_1.model rio_1.state

rio.model rio.state

I use rio.model, to gen picture, it seems not ok, is any step i'm wrong?

rio-train.zip

rio.jpg rio.model rio-dst.jpg

thanks

[6o6o]

Looks about right, but your reference style appears to be already a product of a style transfer operation in some other app on this image. Better choose original unaltered styles, train with --image_size 512 option and even then result may not always be plausible.

[sukerlove]

@6o6o thanks, i now try --image_size 512 I use command, but memory out

GPU gtx1080, memroy:32G

num traning images: 82783 82783 iterations, 2 epochs /usr/local/lib/python2.7/dist-packages/chainer/cuda.py:87: UserWarning: cuDNN is not enabled. Please reinstall chainer after you install cudnn (see https://github.com/pfnet/chainer#installation). 'cuDNN is not enabled.\n' epoch 0 (epoch 0) batch 0/82783... training loss is...255842176.0 Traceback (most recent call last): File "train.py", line 133, in feature_hat = vgg(y) File "/home/gtx1080/work/src/github.com/yusuketomoto/chainer-fast-neuralstyle-0829/net.py", line 97, in call h = F.max_pooling_2d(y1, 2, stride=2) File "/usr/local/lib/python2.7/dist-packages/chainer/functions/pooling/max_pooling_2d.py", line 173, in max_pooling_2d return MaxPooling2D(ksize, stride, pad, cover_all, use_cudnn)(x) File "/usr/local/lib/python2.7/dist-packages/chainer/function.py", line 130, in call outputs = self.forward(in_data) File "/usr/local/lib/python2.7/dist-packages/chainer/function.py", line 234, in forward return self.forward_gpu(inputs) File "/usr/local/lib/python2.7/dist-packages/chainer/functions/pooling/max_pooling_2d.py", line 39, in forward_gpu y = cuda.cupy.empty((n, c, y_h, y_w), dtype=x[0].dtype) File "/usr/local/lib/python2.7/dist-packages/cupy/creation/basic.py", line 20, in empty return cupy.ndarray(shape, dtype=dtype) File "cupy/core/core.pyx", line 85, in cupy.core.core.ndarray.init (cupy/core/core.cpp:5013) File "cupy/cuda/memory.pyx", line 275, in cupy.cuda.memory.alloc (cupy/cuda/memory.cpp:5515) File "cupy/cuda/memory.pyx", line 414, in cupy.cuda.memory.MemoryPool.malloc (cupy/cuda/memory.cpp:8076) File "cupy/cuda/memory.pyx", line 430, in cupy.cuda.memory.MemoryPool.malloc (cupy/cuda/memory.cpp:8002) File "cupy/cuda/memory.pyx", line 337, in cupy.cuda.memory.SingleDeviceMemoryPool.malloc (cupy/cuda/memory.cpp:6970) File "cupy/cuda/memory.pyx", line 357, in cupy.cuda.memory.SingleDeviceMemoryPool.malloc (cupy/cuda/memory.cpp:6797) File "cupy/cuda/memory.pyx", line 255, in cupy.cuda.memory._malloc (cupy/cuda/memory.cpp:5457) File "cupy/cuda/memory.pyx", line 256, in cupy.cuda.memory._malloc (cupy/cuda/memory.cpp:5378) File "cupy/cuda/memory.pyx", line 31, in cupy.cuda.memory.Memory.init (cupy/cuda/memory.cpp:1540) File "cupy/cuda/runtime.pyx", line 196, in cupy.cuda.runtime.malloc (cupy/cuda/runtime.cpp:3067) File "cupy/cuda/runtime.pyx", line 126, in cupy.cuda.runtime.check_status (cupy/cuda/runtime.cpp:1982) cupy.cuda.runtime.CUDARuntimeError: cudaErrorMemoryAllocation: out of memory

[6o6o]

You need to install cuDNN. It reduces memory usage significantly. After installing CUDA, download cuDNN here, place the necessary files to your CUDA installation dir and reinstall chainer.

[sukerlove]

@6o6o thanks

I had install cudnn before

ls -la /usr/local/cuda-8.0/lib64/ ...... -rw-r--r-- 1 root root 737516 8月 11 18:21 libcudart_static.a lrwxrwxrwx 1 root root 35 8月 20 13:38 libcudnn.so -> /usr/local/cuda/lib64/libcudnn.so.5 lrwxrwxrwx 1 root root 39 8月 16 14:28 libcudnn.so.4 -> /usr/local/cuda/lib64/libcudnn.so.4.0.7 -rwxr-xr-x 1 root root 61453024 8月 16 14:15 libcudnn.so.4.0.7 lrwxrwxrwx 1 root root 39 8月 16 10:38 libcudnn.so.5 -> /usr/local/cuda/lib64/libcudnn.so.5.1.5 -rwxr-xr-x 1 root root 79337624 8月 11 18:42 libcudnn.so.5.1.5 lrwxrwxrwx 1 root root 40 8月 16 11:08 libcudnn.so.7.0 -> /usr/local/cuda/lib64/libcudnn.so.7.0.64

......

and set path: declare -x CPATH="/usr/local/cuda-8.0/include:/home/gtx1080/:" declare -x LD_LIBRARY_PATH="/home/gtx1080/torch/install/lib:/usr/local/cuda-8.0/lib64:" declare -x LIBRARY_PATH="/home/gtx1080/torch/install/lib:/usr/local/cuda-8.0/lib64:"

[6o6o]

Here is the original style image used to create the picture you provided