将二进制_crossentropy（）的结果相加时出现TensorFlow加法错误 当一个非常意外的错误出现时，我正在训练我的GaN。我不知道如何修理它。这个错误不是马上就发生的，它发生在我训练的2-3分钟左右。这里是错误 Traceback (most recent call last): File "gan.py", line 103, in <module> train(X_train_dataset,200) File "gan.py", line 80, in train train_step(images) # takes images and improves both the generator and the discriminator File "gan.py", line 91, in train_step discriminator_loss = get_discriminator_loss(real_output,fake_output) File "gan.py", line 48, in get_discriminator_loss return fake_loss+real_loss File "/home/jake/.local/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py", line 1125, in binary_op_wrapper return func(x, y, name=name) File "/home/jake/.local/lib/python3.6/site-packages/tensorflow/python/util/dispatch.py", line 201, in wrapper return target(*args, **kwargs) File "/home/jake/.local/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py", line 1447, in _add_dispatch return gen_math_ops.add_v2(x, y, name=name) File "/home/jake/.local/lib/python3.6/site-packages/tensorflow/python/ops/gen_math_ops.py", line 486, in add_v2 _ops.raise_from_not_ok_status(e, name) File "/home/jake/.local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 6843, in raise_from_not_ok_status six.raise_from(core._status_to_exception(e.code, message), None) File "<string>", line 3, in raise_from tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [100] vs. [13] [Op:AddV2]

有人有什么想法吗？请记住，这是在成功运行约2-3分钟后。错误不会发生在前多次传递中

我已经找到了错误的根源，但我不知道为什么会发生

我在其中一个过程中的实际损失只有13个值，而不是正常的100

这怎么可能

这是我的全部代码

    import tensorflow as tf
import matplotlib.pyplot as plt
import numpy as np
import time
import pickle

pickle_in_X = open("X.pickle","rb")
pickle_in_y = open("y.pickle","rb")

X=pickle.load(pickle_in_X)
y = pickle.load(pickle_in_y)
y = np.array(y)


X_train = X[  int(len(X)*.3):  ]
y_train = y[  int(len(y)*.3 ):  ]

X_test = X[  :int(len(X)*.3)  ]
y_test = X[  :int(len(y)*.3)    ]

X_train = (X_train-127.5)/127.5

BATCH_SIZE = 100
X_train_dataset = tf.data.Dataset.from_tensor_slices(X_train).batch(BATCH_SIZE)

#creates a discriminator model.
#discriminator will ouput 0-1 which represents the probability that the image is real
def make_discriminator():
    model = tf.keras.Sequential()
    model.add(tf.keras.layers.Conv2D(7,(3,3),padding="same",input_shape=(40,40,1)))
    model.add(tf.keras.layers.Flatten())
    model.add(tf.keras.layers.LeakyReLU())
    model.add(tf.keras.layers.Dense(50,activation="relu"))
    model.add(tf.keras.layers.Dense(1))
    return model

model_discriminator = make_discriminator()
discriminator_optimizer = tf.optimizers.Adam(1e-3)

#real_loss is the amount of error when trying to guess that the real images are in fact real. i.e loss will be if our discriminator guesses that there is a 100% chance that this real image is real
#fake_loss is the amount of error when trying to guess that the fake images are in fact fake. i.e loss will be zero if our discriminator guesses there is a 0% chance that this fake image is fake
#returns the total of our loss
def get_discriminator_loss(real_predictions,fake_predictions):
    real_predictions = tf.sigmoid(real_predictions)
    fake_predictions = tf.sigmoid(fake_predictions)
    real_loss=tf.losses.binary_crossentropy(tf.ones_like(real_predictions),real_predictions)
    fake_loss=tf.losses.binary_crossentropy(tf.zeros_like(fake_predictions),fake_predictions)
    return fake_loss+real_loss

#take an input of a random string of numbers. and output either a dog or a cat
def make_generator():
    model = tf.keras.Sequential()
    model.add(tf.keras.layers.Dense(10*10*256,input_shape = (100,)))
    model.add(tf.keras.layers.BatchNormalization())
    model.add(tf.keras.layers.Reshape((10,10,256)))
    model.add(tf.keras.layers.Conv2DTranspose(128,(3,3),padding="same"))
    model.add(tf.keras.layers.BatchNormalization())
    model.add(tf.keras.layers.Conv2DTranspose(64,(3,3),strides=(2,2),padding="same"))
    model.add(tf.keras.layers.BatchNormalization())
    model.add(tf.keras.layers.Conv2DTranspose(1,(3,3),strides=(2,2),padding="same"))
    return model

model_generator = make_generator()

#generator gets rewarded when it fools the discriminator
def get_generator_loss(fake_predictions):
    fake_predictions = tf.sigmoid(fake_predictions)
    fake_loss=tf.losses.binary_crossentropy(tf.ones_like(fake_predictions),fake_predictions)
    return fake_loss

generator_optimizer = tf.optimizers.Adam(1e-3)


#training

def train(X_train_dataset,epochs):
    for _ in range(epochs):
        for images in X_train_dataset:
            images = tf.cast(images,tf.dtypes.float32)
            train_step(images) # takes images and improves both the generator and the discriminator


def train_step(images):
    fake_image_noise = np.random.randn(BATCH_SIZE,100)#produces 100 random numbers that wll be converted to images
    with tf.GradientTape() as generator_gradient, tf.GradientTape() as discriminator_gradient:
        generated_images = model_generator(fake_image_noise)
        real_output = model_discriminator(images)
        fake_output = model_discriminator(generated_images)

        generator_loss = get_generator_loss(fake_output)
        discriminator_loss = get_discriminator_loss(real_output,fake_output)

        gradients_of_generator = generator_gradient.gradient(generator_loss,model_generator.trainable_variables)#gradient of gen loss with respect to trainable variables
        gradients_of_discriminator = discriminator_gradient.gradient(discriminator_loss,model_discriminator.trainable_variables)
        
        discriminator_optimizer.apply_gradients(zip(gradients_of_discriminator,model_discriminator.trainable_variables))
        generator_optimizer.apply_gradients(zip(gradients_of_generator,model_generator.trainable_variables))

        print("generator loss: ", np.mean(generator_loss))
        print("discriminator loss: ",np.mean(discriminator_loss))


train(X_train_dataset,200)

model_generator.save('genModel')

model_discriminator.save('discModel')

---

如果数据集的大小不是批大小的倍数，则上一批的样本数将少于其他批。为了避免这种情况，您可以强制

tf.data.Dataset

删除小于批大小的最后一批。有关更多信息，请参阅

tf.data.Dataset.from_tensor_slices(X_train).batch(BATCH_SIZE, drop_remainder=True)

---

您可以尝试使用

tf.data.Dataset.from_tensor_切片（X_序列）.batch（batch_SIZE，drop_rements=True）

？这可能是因为新纪元结束时的批次比其他批次小。@jakub非常感谢。我一个人永远也想不到这一点。

tf.data.Dataset.from_tensor_slices(X_train).batch(BATCH_SIZE, drop_remainder=True)