Operating environment
GeForce GTX 1070 (8GB)
ASRock Z170M Pro4S [Intel Z170chipset]
Ubuntu 14.04 LTS desktop amd64
TensorFlow v0.11
cuDNN v5.1 for Linux
CUDA v8.0
Python 2.7.6
A program using a deep learning framework called TensorFlow is being tried.
I tried the sample code to read the csv file. http://qiita.com/learn_tensorflow/items/3e46b2512a1bab73f5b2
We did the following:
I got the following error:
$ python 3e46b2512a1bab73f5b2.py
File "3e46b2512a1bab73f5b2.py", line 4
SyntaxError: Non-ASCII character '\xe3' in file 3e46b2512a1bab73f5b2.py on line 4, but no encoding declared; see http://www.python.org/peps/pep-0263.html for details
The following areas may be relevant. http://yono.cc/python/python_basics/japanese.html
Based on the link above, we did the following:
The following two lines have been added to the beginning of 3e46b2512a1bab73f5b2.py.
#!/usr/bin/env python
# -*- coding: utf-8 -*-
The error no longer appears in python 3e46b2512a1bab73f5b2.py.
I also confirmed that it works even if only the second line (line of utf-8) is added to the beginning.
However, this time it seems that another error will occur.
I forgot to create input.csv. When I created it, it worked normally.
$ python 3e46b2512a1bab73f5b2.py
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcublas.so locally
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcudnn.so locally
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcufft.so locally
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcuda.so.1 locally
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcurand.so locally
WARNING:tensorflow:sum_of_squares (from tensorflow.contrib.losses.python.losses.loss_ops) is deprecated and will be removed after 2016-10-01.
Instructions for updating:
Use mean_squared_error.
I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:925] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
I tensorflow/core/common_runtime/gpu/gpu_device.cc:951] Found device 0 with properties:
name: GeForce GTX 1070
major: 6 minor: 1 memoryClockRate (GHz) 1.7715
pciBusID 0000:01:00.0
Total memory: 7.91GiB
Free memory: 7.43GiB
I tensorflow/core/common_runtime/gpu/gpu_device.cc:972] DMA: 0
I tensorflow/core/common_runtime/gpu/gpu_device.cc:982] 0: Y
I tensorflow/core/common_runtime/gpu/gpu_device.cc:1041] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 1070, pci bus id: 0000:01:00.0)
step 100: loss=0.247862
step 200: loss=0.247688
step 300: loss=0.247384
step 400: loss=0.241975
step 500: loss=0.238029
step 600: loss=0.162714
step 700: loss=0.073538
step 800: loss=0.032851
step 900: loss=0.016584
step 1000: loss=0.008190
step 1100: loss=0.007613
step 1200: loss=0.005846
step 1300: loss=0.004516
step 1400: loss=0.003045
step 1500: loss=0.003138
step 1600: loss=0.002398
step 1700: loss=0.002074
step 1800: loss=0.001769
step 1900: loss=0.001600
step 2000: loss=0.001209
Recommended Posts