aiacademy: 深度學習 Recurrnet Neural Network

複習

神經網路概念複習

一層神經網路矩陣表示法

人工智慧解決問題的流程

RNN

• 可以看我的筆記
  • rnn1
  • rnn2

RNN 概念介紹

RNN Cell 運作方式

---

---

---

---

---

RNN 應用

RNN 應用之對話機器人

• 對話機器人
  • 每次輸入和輸出都不是固定長度!

對話機器人的變形應用

• 應用

  • 翻譯
  • Video Captioning 生成影片敘述
  • 生成一段文字
  • 畫一半的圖完成它

• Andrej Karpathy

  • 李飛飛學生
  • 自動生成數學教科書

情意分析和 slot filing

Slot filing

RNN 全壘打預測實例

---

---

---

---

---

RNN Cell 的運作方式

RNN的應用類型

Bidirectional RNN

• 看看我的耳藝術天分!

---

---

---

可愛作業? LoL

簡單 RNN 作業

Numpy 計算 RNN 作業

計算作業完整輸出

完成第一個 RNN

---

---

---

RNN 的學習法和問題

LSTM 的 Gates

LSTM的運作方式

GRU

實作

回顧複習 RNN

• 設定 RNN 要輸出的大小

  • 先初始化 weight, weight shape = (n, m + n) = (3, 9)
    • n 代表要轉換的維度，m代表原本的feature大小

RNN 實作 MNIST

1. 前置作業 import package

import numpy as np
from pprint import pprint
import matplotlib.pyplot as plt
from sklearn.utils import shuffle 
import tensorflow as tf

1. Set hyperparameters

learning_rate = 0.001
batch_size = 128
epochs = 10

1. Load data and preprocess

(X_train, y_train), (X_test, y_test) = tf.keras.datasets.mnist.load_data()

print('Data shape: ', X_train[0].shape)
print('Label: ', y_train[2])
plt.figure(figsize=(6, 6))
plt.imshow(X_train[2], cmap='binary')
plt.show()

X_train = X_train / 255.
X_test = X_test / 255.
y_train = np.eye(10)[y_train[:]]
y_test = np.eye(10)[y_test[:]]

def batch_gen(X, y, batch_size):
   X, y = shuffle(X, y)
   batch_index = 0

   while batch_index < len(X):
      batch_X = X[batch_index : batch_index + batch_size]
      batch_y = y[batch_index : batch_index + batch_size]
      batch_index += batch_size
      yield batch_X, batch_y

1. Build the graph

def Rnn_layer(inputs, units):
   BasicRNN_cell = tf.nn.rnn_cell.BasicLSTMCell(num_units=units)
   # init_stae = tf.zeros([tf.shape(inputs)[0], units])
   init_state = BasicRNN_cell.zero_state(tf.shape(inputs)[0], dtype=tf.float32) # shape = (batch, units)
   outputs, states = tf.nn.dynamic_rnn(BasicRNN_cell, inputs, initial_state=init_state)
   return outputs

tf.reset_default_graph()

with tf.name_scope("inputs"):
    input_data = tf.placeholder(dtype=tf.float32, shape=[None, 28, 28], name="input_data")
    y_label = tf.placeholder(dtype=tf.float32, shape=[None, 10], name='label')

with tf.variabel_scope("RNN_layer"):
    outputs = RNN_layer(input_data, 32)

with tf.variable_scope("output_layer"):
    RNN_last_outputs = outputs[:,-1,:]  # outputs shape = (batch, timestep, feature)
    prediction = tf.layers.dense(inputs=RNN_last_outputs, units=10)

with tf.name_scope("loss"):
    loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=prediction,labels=y_label))

with tf.name_scope("optimizer"):
    opt = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(loss)

with tf.name_scope("accuracy"):
    correct_prediction = tf.equal(tf.argmax(prediction, 1), tf.argmax(y_label, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))    

init = tf.global_variables_initializer()

# with tf.keras

tf.reset_default_graph()

with tf.name_scope("inputs"):
    input_data = tf.placeholder(dtype=tf.float32, shape=[None, 28, 28], name='input_data')
    y_label = tf.placeholder(dtype=tf.float32, shape=[None, 10], name='label')

with tf.variable_scope("RNN_layer"):
    rnn_out = tf.keras.layers.SimpleRNN(units=32)(input_data)

with tf.variable_scope("output_layer"):
    prediction = tf.layers.dense(inputs=rnn_out, units=10)

with tf.name_scope("loss"):
    loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=prediction,labels=y_label))

with tf.name_scope("optimizer"):
    opt = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(loss)

with tf.name_scope("accuracy"):
    correct_prediction = tf.equal(tf.argmax(prediction, 1), tf.argmax(y_label, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))    

init = tf.global_variables_initializer()

1. Tain the model

sess = tf.Session()
sess.run(init)

for epoch_index in range(epochs):
    loss_ls, acc_ls = [], []
    get_batch = batch_gen(X_train, y_train, batch_size)
    
    for batch_X, batch_y in get_batch:
        _,  batch_acc, batch_loss = sess.run([opt, accuracy, loss], feed_dict={input_data: batch_X, y_label:batch_y})
        loss_ls.append(batch_loss)
        acc_ls.append(batch_acc)

    print("Epoch ", epoch_index)
    print("Accuracy ", np.mean(acc_ls), "     Loss ", np.mean(loss_ls))
    print("__________________") 

sess.close()