中文字幕理论片,69视频免费在线观看,亚洲成人app,国产1级毛片,刘涛最大尺度戏视频,欧美亚洲美女视频,2021韩国美女仙女屋vip视频

import osimport numpy as npdef read_data():    # 數(shù)據(jù)目錄    data_dir = '/home/your_name/TensorFlow/DCGAN/data/mnist'        # 打開訓(xùn)練數(shù)據(jù)        fd = open(os.path.join(data_dir,'train-images-idx3-ubyte'))    # 轉(zhuǎn)化成 numpy 數(shù)組    loaded = np.fromfile(file=fd,dtype=np.uint8)    # 根據(jù) mnist 官網(wǎng)描述的數(shù)據(jù)格式，圖像像素從 16 字節(jié)開始    trX = loaded[16:].reshape((60000,28,28,1)).astype(np.float)    # 訓(xùn)練 label    fd = open(os.path.join(data_dir,'train-labels-idx1-ubyte'))    loaded = np.fromfile(file=fd,dtype=np.uint8)    trY = loaded[8:].reshape((60000)).astype(np.float)    # 測試數(shù)據(jù)    fd = open(os.path.join(data_dir,'t10k-images-idx3-ubyte'))    loaded = np.fromfile(file=fd,dtype=np.uint8)    teX = loaded[16:].reshape((10000,28,28,1)).astype(np.float)    # 測試 label    fd = open(os.path.join(data_dir,'t10k-labels-idx1-ubyte'))    loaded = np.fromfile(file=fd,dtype=np.uint8)    teY = loaded[8:].reshape((10000)).astype(np.float)    trY = np.asarray(trY)    teY = np.asarray(teY)        # 由于生成網(wǎng)絡(luò)由服從某一分布的噪聲生成圖片，不需要測試集，    # 所以把訓(xùn)練和測試兩部分?jǐn)?shù)據(jù)合并    X = np.concatenate((trX, teX), axis=0)    y = np.concatenate((trY, teY), axis=0)        # 打亂排序    seed = 547    np.random.seed(seed)    np.random.shuffle(X)    np.random.seed(seed)    np.random.shuffle(y)        # 這里，y_vec 表示對網(wǎng)絡(luò)所加的約束條件，這個條件是類別標(biāo)簽，    # 可以看到，y_vec 實(shí)際就是對 y 的獨(dú)熱編碼，關(guān)于什么是獨(dú)熱編碼，    # 請參考 http://www.cnblogs.com/Charles-Wan/p/6207039.html    y_vec = np.zeros((len(y), 10), dtype=np.float)    for i, label in enumerate(y):        y_vec[i,y[i]] = 1.0        return X/255., y_vec

import tensorflow as tffrom tensorflow.contrib.layers.python.layers import batch_norm as batch_norm# 常數(shù)偏置def bias(name, shape, bias_start = 0.0, trainable = True):        dtype = tf.float32    var = tf.get_variable(name, shape, tf.float32, trainable = trainable,                           initializer = tf.constant_initializer(                                                  bias_start, dtype = dtype))    return var# 隨機(jī)權(quán)重def weight(name, shape, stddev = 0.02, trainable = True):        dtype = tf.float32    var = tf.get_variable(name, shape, tf.float32, trainable = trainable,                           initializer = tf.random_normal_initializer(                                              stddev = stddev, dtype = dtype))    return var# 全連接層def fully_connected(value, output_shape, name = 'fully_connected', with_w = False):        shape = value.get_shape().as_list()        with tf.variable_scope(name):        weights = weight('weights', [shape[1], output_shape], 0.02)        biases = bias('biases', [output_shape], 0.0)            if with_w:        return tf.matmul(value, weights) + biases, weights, biases    else:        return tf.matmul(value, weights) + biases# Leaky-ReLu 層def lrelu(x, leak=0.2, name = 'lrelu'):        with tf.variable_scope(name):        return tf.maximum(x, leak*x, name = name)        # ReLu 層def relu(value, name = 'relu'):    with tf.variable_scope(name):        return tf.nn.relu(value)    # 解卷積層def deconv2d(value, output_shape, k_h = 5, k_w = 5, strides =[1, 2, 2, 1],              name = 'deconv2d', with_w = False):        with tf.variable_scope(name):        weights = weight('weights',                          [k_h, k_w, output_shape[-1], value.get_shape()[-1]])        deconv = tf.nn.conv2d_transpose(value, weights,                                         output_shape, strides = strides)        biases = bias('biases', [output_shape[-1]])        deconv = tf.reshape(tf.nn.bias_add(deconv, biases), deconv.get_shape())        if with_w:            return deconv, weights, biases        else:            return deconv            # 卷積層            def conv2d(value, output_dim, k_h = 5, k_w = 5,             strides =[1, 2, 2, 1], name = 'conv2d'):        with tf.variable_scope(name):        weights = weight('weights',                          [k_h, k_w, value.get_shape()[-1], output_dim])        conv = tf.nn.conv2d(value, weights, strides = strides, padding = 'SAME')        biases = bias('biases', [output_dim])        conv = tf.reshape(tf.nn.bias_add(conv, biases), conv.get_shape())                return conv# 把約束條件串聯(lián)到 feature mapdef conv_cond_concat(value, cond, name = 'concat'):        # 把張量的維度形狀轉(zhuǎn)化成 Python 的 list    value_shapes = value.get_shape().as_list()    cond_shapes = cond.get_shape().as_list()        # 在第三個維度上（feature map 維度上）把條件和輸入串聯(lián)起來，    # 條件會被預(yù)先設(shè)為四維張量的形式，假設(shè)輸入為 [64, 32, 32, 32] 維的張量，    # 條件為 [64, 32, 32, 10] 維的張量，那么輸出就是一個 [64, 32, 32, 42] 維張量    with tf.variable_scope(name):                return tf.concat(3, [value,                              cond * tf.ones(value_shapes[0:3] + cond_shapes[3:])])  # Batch Normalization 層        def batch_norm_layer(value, is_train = True, name = 'batch_norm'):        with tf.variable_scope(name) as scope:        if is_train:                    return batch_norm(value, decay = 0.9, epsilon = 1e-5, scale = True,                               is_training = is_train,                               updates_collections = None, scope = scope)        else:            return batch_norm(value, decay = 0.9, epsilon = 1e-5, scale = True,                               is_training = is_train, reuse = True,                               updates_collections = None, scope = scope)