使用Keras封装好的RNN模型解决mnist数据集手写数字分类问题

众所周知 这是一篇Hello World

代码参考来自于
运行报错

TypeError: __init__() missing 1 required positional argument: 'units'

stackoverflow的解决方案

`用units替代output_dim属性`

model.add(SimpleRNN(
    # for batch_input_shape, if using tensorflow as the backend, we have to put None for the batch_size.
    # Otherwise, model.evaluate() will get error.
    batch_input_shape=(None, TIME_STEPS, INPUT_SIZE),  # Or: input_dim=INPUT_SIZE, input_length=TIME_STEPS,
    #output_dim=CELL_SIZE,
    units=CELL_SIZE,unroll=True
))

代码：

import numpy as np

np.random.seed(1337)  # for reproducibility 设置随机数种子 随机数种子一样产生的伪随机数序列相同 有利于复现结果

from keras.datasets import mnist
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import SimpleRNN, Activation, Dense
from keras.optimizers import Adam

TIME_STEPS = 28  # same as the height of the image
INPUT_SIZE = 28  # same as the width of the image
BATCH_SIZE = 50
BATCH_INDEX = 0
OUTPUT_SIZE = 10 #类标签总数
CELL_SIZE = 50 #隐藏层神经元个数
LR = 0.001