spenhouet/automated-deep-photo-style-transfer

TensorFlow implementation for the paper "Automated Deep Photo Style Transfer"

Hi My name is Sebastian Penhouet

Head of R&D at AIRAmed GmbH

My current main focus is on machine learning in the area of medical image segmentation. On the side I'm also a web dev and experimenting with web3 technologies.

• 🌍  I'm based in Tübingen, Germany
• 🚀  I'm currently working on quantification of MR images at AIRAmed for the treatment of neurodegenerative disease
• 🧠  I'm learning Svelte, d3 visualization, web3 communication
• 🌍  Find my personal webpage here: spenhouet.com

Skills

Socials

automated-deep-photo-style-transfer's Issues

why I can't replicate your result?

This is what I get from the bear picture.

Specify python version

For the time I was running your project in python 3.5 but throws an error in sematch library as follows.
from sematch.semantic.similarity import WordNetSimilarity
Traceback (most recent call last):
File "", line 1, in
File "C:\Users\Siyas\AppData\Local\Continuum\anaconda3\lib\site-packages\sematch\semantic\similarity.py", line 25, in
from sematch.semantic.sparql import EntityFeatures, StatSPARQL
File "C:\Users\Siyas\AppData\Local\Continuum\anaconda3\lib\site-packages\sematch\semantic\sparql.py", line 36
print query
^
SyntaxError: Missing parentheses in call to 'print'. Did you mean print(print query)?

The fix was to give a parenthesis to that file specified. But thats not the fix. Please tell me how did it work for you.

Document for parameters?

Is there any example of how to use style_transfer? Perhaps an explanation on the parameters as well. Thanks!

How to start the program?

I have followed the instructions in the Read Me section (steps 1 - 4). However, I'm not quite sure how to start the program. In Google Colab I have:

from PIL import Image
base_image = Image.open('/content/drive/My Drive/base.jpg')
style_image = Image.open('/content/drive/My Drive/style.jpg')

# pass arguments to script
!python style_transfer.py --base_image --style_image

It currently returns an unexpected argument error. Any thoughts on how I should proceed?

Licence

Under what conditions can I obtain a license for commercial use?

Some images run well. However some images could not run,why?

Using TensorFlow backend.
Create segmentation.
Compute segmentation started
2019-04-30 14:23:14.863543: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2019-04-30 14:23:15.033646: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:998] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2019-04-30 14:23:15.034140: I tensorflow/compiler/xla/service/service.cc:150] XLA service 0x56271ea411e0 executing computations on platform CUDA. Devices:
2019-04-30 14:23:15.034171: I tensorflow/compiler/xla/service/service.cc:158] StreamExecutor device (0): Tesla T4, Compute Capability 7.5
2019-04-30 14:23:15.035899: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2300000000 Hz
2019-04-30 14:23:15.036179: I tensorflow/compiler/xla/service/service.cc:150] XLA service 0x56271ea41080 executing computations on platform Host. Devices:
2019-04-30 14:23:15.036208: I tensorflow/compiler/xla/service/service.cc:158] StreamExecutor device (0): ,
2019-04-30 14:23:15.036524: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1433] Found device 0 with properties:
name: Tesla T4 major: 7 minor: 5 memoryClockRate(GHz): 1.59
pciBusID: 0000:00:04.0
totalMemory: 14.73GiB freeMemory: 14.60GiB
2019-04-30 14:23:15.036551: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1512] Adding visible gpu devices: 0
2019-04-30 14:23:15.037080: I tensorflow/core/common_runtime/gpu/gpu_device.cc:984] Device interconnect StreamExecutor with strength 1 edge matrix:
2019-04-30 14:23:15.037100: I tensorflow/core/common_runtime/gpu/gpu_device.cc:990] 0
2019-04-30 14:23:15.037110: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1003] 0: N
2019-04-30 14:23:15.037329: W tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:42] Overriding allow_growth setting because the TF_FORCE_GPU_ALLOW_GROWTH environment variable is set. Original config value was 0.
2019-04-30 14:23:15.037366: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 14202 MB memory) -> physical GPU (device: 0, name: Tesla T4, pci bus id: 0000:00:04.0, compute capability: 7.5)
WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
WARNING:tensorflow:From /content/automated-deep-photo-style-transfer/components/PSPNet/network.py:263: batch_normalization (from tensorflow.python.layers.normalization) is deprecated and will be removed in a future version.
Instructions for updating:
Use keras.layers.batch_normalization instead.
WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/tensorflow/python/util/dispatch.py:180: calling expand_dims (from tensorflow.python.ops.array_ops) with dim is deprecated and will be removed in a future version.
Instructions for updating:
Use the axis argument instead
WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py:1266: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file APIs to check for files with this prefix.
Restored model parameters from /content/automated-deep-photo-style-transfer/weights/PSPNet/checkpoint/model.ckpt-0
2019-04-30 14:23:19.381974: I tensorflow/stream_executor/dso_loader.cc:152] successfully opened CUDA library libcublas.so.10.0 locally
Semantic merge of segments started
Semantic merge of different segments started
Semantic merge of different segments started
Traceback (most recent call last):
File "/content/automated-deep-photo-style-transfer/style_transfer.py", line 322, in
args.semantic_thresh)
File "/content/automated-deep-photo-style-transfer/components/semantic_merge.py", line 93, in merge_segments
assert style_colors == content_colors
AssertionError

miss import

model.py file miss import numpy as np and import tensorflow as tf