VGGNet分类······Keras重建模型

感觉AI可能因为是个新兴的学科，所以特别迷；

keras, tensorflow, slim等各大模块乱七八糟，博客内容五花八门......

1）利用tensorflow的slim模块复现vggnet实现图像分类

import tensorflow as tf

import tensorflow.contrib.slim as slim

import tensorflow.contrib.slim.nets as nets

import sys

import numpy as np

sys.path.append('D:/models-master/research/slim')

from preprocessing import vgg_preprocessing

from nets import vgg

tf.reset_default_graph()

image_size = vgg.vgg_16.default_image_size

image=tf.read_file('1.jpeg')

jpeg = tf.image.decode_jpeg(image, channels=3)

processed_image = vgg_preprocessing.preprocess_image(jpeg,

                                                  image_size,

                                                  image_size,

                                                  is_training=False)

processed_images  = tf.expand_dims(processed_image, 0)

with slim.arg_scope(vgg.vgg_arg_scope()):

    logits, _ = vgg.vgg_16(processed_images,

                          num_classes=1000,

                          is_training=False)

probabilities = tf.nn.softmax(logits)

np_image = tf.placeholder(tf.float32, [None,224,224,3])

init_fn = slim.assign_from_checkpoint_fn('./vgg_16.ckpt',slim.get_model_variables('vgg_16'))

with tf.Session(config=tf.ConfigProto(device_count={'gpu':0})) as sess:

    init_fn(sess)

    np_image, network_input, probabilities = sess.run([jpeg, processed_images,probabilities])

    print(np.max(probabilities))

2）利用keras复现vggnet

from keras.preprocessing.image import load_img

from keras.preprocessing.image import img_to_array

from keras.applications.vgg16 import preprocess_input

from keras.applications.vgg16 import decode_predictions

from keras.applications.vgg16 import VGG16

# load the model

model = VGG16()

# load an image from file

image = load_img('mug.jpg', target_size=(224, 224))

# convert the image pixels to a numpy array

image = img_to_array(image)

# reshape data for the model

image = image.reshape((1, image.shape[0], image.shape[1], image.shape[2]))

# prepare the image for the VGG model

image = preprocess_input(image)

# predict the probability across all output classes

yhat = model.predict(image)

# convert the probabilities to class labels

label = decode_predictions(yhat)

# retrieve the most likely result, e.g. highest probability

label = label[0][0]

# print the classification

print('%s (%.2f%%)' % (label[1], label[2]*100))

感觉不懂tensorflow强行入门好难呀，继续钻研ing