我正在使用數(shù)據(jù)集 API 生成訓練數(shù)據(jù)并將其分類為 NN 的批次。這是我的代碼的最小工作示例：import tensorflow as tfimport numpy as npimport randomdef my_generator(): while True: x = np.random.rand(4, 20) y = random.randint(0, 11) label = tf.one_hot(y, depth=12) yield x.reshape(4, 20, 1), labeldef my_input_fn(): dataset = tf.data.Dataset.from_generator(lambda: my_generator(), output_types=(tf.float64, tf.int32)) dataset = dataset.batch(32) iterator = dataset.make_one_shot_iterator() batch_features, batch_labels = iterator.get_next() return batch_features, batch_labelsif __name__ == "__main__": tf.enable_eager_execution() model = tf.keras.Sequential([tf.keras.layers.Flatten(input_shape=(4, 20, 1)), tf.keras.layers.Dense(128, activation=tf.nn.relu), tf.keras.layers.Dense(12, activation=tf.nn.softmax)]) model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy']) data_generator = my_input_fn() model.fit(data_generator)但batch_size不是 的公認關(guān)鍵字fit_generator()。我對這些錯誤消息感到困惑，如果有人能對它們有所了解，或者指出我做錯了什么，我將不勝感激。
1 回答
FFIVE
TA貢獻1797條經(jīng)驗 獲得超6個贊
雖然錯誤的根源仍然模糊不清，但我已經(jīng)找到了使代碼工作的解決方案。我會把它貼在這里，以防它對處于類似情況的任何人有用。
基本上，我將其更改my_input_fn()為生成器并使用model.fit_generator()如下：
import tensorflow as tf
import numpy as np
import random
def my_generator(total_items):
i = 0
while i < total_items:
x = np.random.rand(4, 20)
y = random.randint(0, 11)
label = tf.one_hot(y, depth=12)
yield x.reshape(4, 20, 1), label
i += 1
def my_input_fn(total_items, epochs):
dataset = tf.data.Dataset.from_generator(lambda: my_generator(total_items),
output_types=(tf.float64, tf.int64))
dataset = dataset.repeat(epochs)
dataset = dataset.batch(32)
iterator = dataset.make_one_shot_iterator()
while True:
batch_features, batch_labels = iterator.get_next()
yield batch_features, batch_labels
if __name__ == "__main__":
tf.enable_eager_execution()
model = tf.keras.Sequential([tf.keras.layers.Flatten(input_shape=(4, 20, 1)),
tf.keras.layers.Dense(64, activation=tf.nn.relu),
tf.keras.layers.Dense(12, activation=tf.nn.softmax)])
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
total_items = 200
batch_size = 32
epochs = 10
num_batches = int(total_items/batch_size)
train_data_generator = my_input_fn(total_items, epochs)
model.fit_generator(generator=train_data_generator, steps_per_epoch=num_batches, epochs=epochs, verbose=1)
編輯
正如 giser_yugang 在評論中暗示的那樣，也可以將其my_input_fn()作為返回dataset而不是單個批次的函數(shù)來執(zhí)行。
def my_input_fn(total_items, epochs):
dataset = tf.data.Dataset.from_generator(lambda: my_generator(total_items),
output_types=(tf.float64, tf.int64))
dataset = dataset.repeat(epochs)
dataset = dataset.batch(32)
return dataset
if __name__ == "__main__":
tf.enable_eager_execution()
model = tf.keras.Sequential([tf.keras.layers.Flatten(input_shape=(4, 20, 1)),
tf.keras.layers.Dense(64, activation=tf.nn.relu),
tf.keras.layers.Dense(12, activation=tf.nn.softmax)])
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
total_items = 100
batch_size = 32
epochs = 10
num_batches = int(total_items/batch_size)
dataset = my_input_fn(total_items, epochs)
model.fit_generator(dataset, epochs=epochs, steps_per_epoch=num_batches)
這些方法之間似乎沒有任何平均性能差異。
添加回答
舉報
0/150
提交
取消