MNIST はじまりました

やっとこさ始めることができました、MNIST。

まずはこれが理解できないと始まらないので・・・

これさえも動かない状態が続いていたので、やっと光が見えた感じです。

まずはinput_dataでerrorとなりつまずきました。

ここは修正することで何とか切り抜けて、以下のようにlogが取れるまでになりました。

あー長かったorz

直したところは↓ここ。

import input_data

これを

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)

これでエラー解消

ではやってみましょう。

:~$ python3 mn1.py
Extracting MNIST_data/train-images-idx3-ubyte.gz
Extracting MNIST_data/train-labels-idx1-ubyte.gz
Extracting MNIST_data/t10k-images-idx3-ubyte.gz
Extracting MNIST_data/t10k-labels-idx1-ubyte.gz
2017-06-18 07:33:39.264680: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2017-06-18 07:33:39.313121: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2017-06-18 07:33:39.313275: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
WARNING:tensorflow:From /home/tatsu/.pyenv/versions/3.5.2/lib/python3.5/site-packages/tensorflow/python/util/tf_should_use.py:170: initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02.
Instructions for updating:
Use `tf.global_variables_initializer` instead.
0.9144
WARNING:tensorflow:From /home/tatsu/.pyenv/versions/3.5.2/lib/python3.5/site-packages/tensorflow/python/util/tf_should_use.py:170: initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02.
Instructions for updating:
Use `tf.global_variables_initializer` instead.
step 0, training accuracy 0
step 100, training accuracy 0.78
step 200, training accuracy 0.94
step 300, training accuracy 0.94
step 400, training accuracy 0.92
step 500, training accuracy 0.98
step 600, training accuracy 0.94
step 700, training accuracy 1
step 800, training accuracy 0.96
step 900, training accuracy 0.94
step 1000, training accuracy 0.94
step 1100, training accuracy 0.88
step 1200, training accuracy 0.98
step 1300, training accuracy 1
step 1400, training accuracy 0.98
step 1500, training accuracy 1
step 1600, training accuracy 1
step 1700, training accuracy 0.96

本日はこれが終わるまでで終了。