tensorflow57 《TensorFlow技术解析与实战》07 Tensorflow的高级框架-tflearn

# -*- coding: utf-8 -*-

""" AlexNet.

Applying 'Alexnet' to Oxford's 17 Category Flower Dataset classification task.

References:
    - Alex Krizhevsky, Ilya Sutskever & Geoffrey E. Hinton. ImageNet
    Classification with Deep Convolutional Neural Networks. NIPS, 2012.
    - 17 Category Flower Dataset. Maria-Elena Nilsback and Andrew Zisserman.

Links:
    - [AlexNet Paper](http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf)
    - [Flower Dataset (17)](http://www.robots.ox.ac.uk/~vgg/data/flowers/17/)

"""
# 《TensorFlow技术解析与实战》07 Tensorflow的高级框架
# win10 Tensorflow1.2.0-RC0 python3.5.3
# CUDA v8.0 cudnn-8.0-windows10-x64-v5.1
# filename:nntf07.01.py TFLearn
# https://github.com/tflearn/tflearn/blob/master/examples/images/alexnet.py

from __future__ import division, print_function, absolute_import

import tflearn
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.normalization import local_response_normalization
from tflearn.layers.estimator import regression

import tflearn.datasets.oxflower17 as oxflower17
X, Y = oxflower17.load_data(one_hot=True, resize_pics=(227, 227))

# Building 'AlexNet'
network = input_data(shape=[None, 227, 227, 3])
network = conv_2d(network, 96, 11, strides=4, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = conv_2d(network, 256, 5, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = conv_2d(network, 384, 3, activation='relu')
network = conv_2d(network, 384, 3, activation='relu')
network = conv_2d(network, 256, 3, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = fully_connected(network, 4096, activation='tanh')
network = dropout(network, 0.5)
network = fully_connected(network, 4096, activation='tanh')
network = dropout(network, 0.5)
network = fully_connected(network, 17, activation='softmax')
network = regression(network, optimizer='momentum',
                     loss='categorical_crossentropy',
                     learning_rate=0.001)

# Training
model = tflearn.DNN(network, checkpoint_path='model_alexnet',
                    max_checkpoints=1, tensorboard_verbose=2)
model.fit(X, Y, n_epoch=1000, validation_set=0.1, shuffle=True,
          show_metric=True, batch_size=64, snapshot_step=200,
          snapshot_epoch=False, run_id='alexnet_oxflowers17')

'''
curses is not supported on this machine (please install/reinstall curses for an optimal experience)
Downloading Oxford 17 category Flower Dataset, Please wait...
100.0% 60252160 / 60270631100.0% 60260352 / 60270631100.0% 60268544 / 60270631100.0% 60276736 / 60270631
('Succesfully downloaded', '17flowers.tgz', 60270631, 'bytes.')
File Extracted
Starting to parse images...
Parsing Done!
---------------------------------
Run id: alexnet_oxflowers17
Log directory: /tmp/tflearn_logs/
---------------------------------
Training samples: 1224
Validation samples: 136
--
Training Step: 1  | time: 8.379s
| Momentum | epoch: 001 | loss: 0.00000 - acc: 0.0000 -- iter: 0064/1224
Training Step: 2  | total loss: 2.88168 | time: 12.973s
| Momentum | epoch: 001 | loss: 2.88168 - acc: 0.0422 -- iter: 0128/1224
...
| Momentum | epoch: 966 | loss: 0.31271 - acc: 0.9679 -- iter: 1216/1224
Training Step: 19320  | total loss: 0.31271 | time: 99.209s
| Momentum | epoch: 966 | loss: 0.31271 - acc: 0.9679 -- iter: 1224/1224
Training Step: 19321  | total loss: 0.28209 | time: 5.142s
| Momentum | epoch: 967 | loss: 0.28209 - acc: 0.9711 -- iter: 0064/1224
'''