将现有项目转换为 TensorFlow

Question

我有一个基于以下代码的现有项目：https ://gist.github.com/karpathy/d4dee566867f8291f086 。作为学习 TensorFlow 的一个练习，我试图将此代码转换为使用 TF，但是，许多 API 文档似乎都期望我要移植的代码中不存在各种术语的先验知识。我假设我会使用 SimpleRNN 或 RNN 的某个子类。

这段代码的基本 TensorFlow 版本会是什么样子？

Answer 1

在获得了一些空闲时间和大量的摆弄之后，我想出了类似的东西：import numpy as npimport tensorflow as tffrom tensorflow.keras import layers, initializersfrom tensorflow.keras.optimizers import AdagradSCALE = 100.0def makeXVector(ix):    x = np.zeros((vocab_size, ))    x[ix] = 1.0    return xwith open('input.txt', 'r') as f:    print('Reading and tokenising input.txt')    data = f.read()print('Collecting chars')chars = list(set(data))data_size, vocab_size = len(data), len(chars)char_to_ix = { tok:i for i,tok in enumerate(chars) }ix_to_char = { i:tok for i,tok in enumerate(chars) }# hyperparametershidden_size = 300 # size of hidden layer of neuronsseq_length = 25 # number of steps to unroll the RNN forlearning_rate = 1e-1model = tf.keras.Sequential()model.add(    layers.SimpleRNN(      hidden_size,      activation='tanh',      use_bias=True,      stateful=True,      bias_initializer=initializers.Zeros(),      # (batch_size, timesteps, input_dim)      batch_input_shape=np.array((1, 1, vocab_size))    ))model.add(    layers.Dense(      vocab_size,      activation='softmax',      use_bias=True,      bias_initializer=initializers.Zeros(),    ))model.compile(    optimizer=Adagrad(learning_rate=learning_rate),    loss='categorical_crossentropy')n, p = 0, 0smooth_loss = -np.log(1.0/vocab_size)*seq_length # loss at iteration 0def sample(model, seed_ix, n):    x = makeXVector(seed_ix)    ixes = []    for t in range(n):      p = np.array(model.predict(np.array([[x.ravel()]]))).ravel()      # Select a random character based on the probability      ix = np.random.choice(list(range(vocab_size)), p=p)      x = makeXVector(ix)      ixes.append(ix)    return ixesprint('data has {:d} characters, {:d} unique.'.format(data_size, vocab_size))try:    while True:      # prepare inputs (we're sweeping from left to right in steps seq_length long)      if p+seq_length+1 >= len(data) or n == 0:         p = 0 # go from start of data      inputs = [char_to_ix[tok] for tok in data[p:p+seq_length]]      targets = [char_to_ix[tok] for tok in data[p+1:p+seq_length+1]]      # sample from the model now and then      if n % 100 == 0:        sample_ix = sample(model, inputs[0], 200)        txt = ' '.join((ix_to_char[ix][0] for ix in sample_ix))        print('----\n{}\n----'.format(txt))      hist = model.fit(        np.array([[inp] for inp in map(makeXVector, inputs)]),        np.array([targ for targ in map(makeXVector, targets)]),        verbose=0      )      loss = hist.history['loss'][-1]      smooth_loss = smooth_loss * 0.999 + loss * 0.001      if n % 100 == 0: print('iter {:d}, loss: {:f}'.format(n, smooth_loss)) # print progress      p += seq_length # move data pointer      n += 1 # iteration counter except KeyboardInterrupt:    pass