我有一个包含300张图像的自定义数据集：
我已经在tensorflow中制作了一个图，但是当我尝试对其进行训练时，我得到了InvalidArgumentError: logits and labels must be broadcastable: logits_size=[720,3] labels_size=[20,3]。
我知道问题是我的logits [720,3]和标签[20,3]形状不同，面临的问题是我的logits为什么以及在何处获得[720，3]形状以及如何更改相应地。改变层数，损失函数和批量大小并不能解决问题。
感谢您的帮助，谢谢！
我有一个Train类，带有build_graph()和train()方法。
这是完整的代码：
class Train:
__x_ = []
__y_ = []
__logits = []
__loss = []
__train_step = []
__merged_summary_op = []
__saver = []
__session = []
__writer = []
__is_training = []
__loss_val = []
__train_summary = []
__val_summary = []
def __init__(self):
pass
def build_graph(self):
self.__x_ = tf.placeholder("float", shape=[None, 192, 192, 3], name='X')
self.__y_ = tf.placeholder("int32", shape=[None, 3], name='Y')
self.__is_training = tf.placeholder(tf.bool)
with tf.name_scope("model") as scope:
conv1 = tf.layers.conv2d(inputs=self.__x_, filters=64,
kernel_size=[5, 5],
padding="same", activation=tf.nn.relu)
pool1 = tf.layers.max_pooling2d(inputs=conv1, pool_size=[2, 2], strides=2)
conv2 = tf.layers.conv2d(inputs=pool1, filters=64, kernel_size=[5, 5], padding="same",
activation=tf.nn.relu)
pool2 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], strides=2)
conv3 = tf.layers.conv2d(inputs=pool2, filters=32, kernel_size=[5, 5], padding="same",
activation=tf.nn.relu)
pool3 = tf.layers.max_pooling2d(inputs=conv3, pool_size=[2, 2], strides=2)
pool3_flat = tf.reshape(pool3, [-1, 4 * 4 * 32])
# FC layers
FC1 = tf.layers.dense(inputs=pool3_flat, units=128, activation=tf.nn.relu)
FC2 = tf.layers.dense(inputs=FC1, units=64, activation=tf.nn.relu)
self.__logits = tf.layers.dense(inputs=FC2, units=3)
#Create variables to hold training loss __loss and validation loss
#__loss_val
with tf.name_scope("loss_func") as scope:
self.__loss = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(logits=self.__logits, labels=self.__y_))
self.__loss_val = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(logits=self.__logits, labels=self.__y_))
# Add loss to tensorboard
self.__train_summary = tf.summary.scalar("loss_train", self.__loss)
self.__val_summary = tf.summary.scalar("loss_val", self.__loss_val)
with tf.name_scope("optimizer") as scope:
global_step = tf.Variable(0, trainable=False)
starter_learning_rate = 1e-3
# decay every 10000 steps with a base of 0.96 function
learning_rate = tf.train.exponential_decay(starter_learning_rate, global_step, 1000, 0.9,
staircase=True)
self.__train_step = tf.train.AdamOptimizer(learning_rate).minimize(self.__loss, global_step=global_step)
tf.summary.scalar("learning_rate", learning_rate)
tf.summary.scalar("global_step", global_step)
# Merge op for tensorboard
self.__merged_summary_op = tf.summary.merge_all()
# Build graph
init = tf.global_variables_initializer()
# Saver for checkpoints
self.__saver = tf.train.Saver(max_to_keep=None)
# Configure summary to output at given directory
self.__session = tf.Session()
self.__writer = tf.summary.FileWriter("./logs/flight_path", self.__session.graph)
self.__session.run(init)
def train(self, save_dir='./save', batch_size=20):
#Load dataset and labels
x = np.asarray(di.load_images())
y = np.asarray(di.load_labels())
#Shuffle dataset
np.random.seed(0)
shuffled_indeces = np.arange(len(y))
np.random.shuffle(shuffled_indeces)
shuffled_x = x[shuffled_indeces].tolist()
shuffled_y = y[shuffled_indeces].tolist()
shuffled_y = tf.keras.utils.to_categorical(shuffled_y, 3)
dataset = (shuffled_x, shuffled_y)
dataset = tf.data.Dataset.from_tensor_slices(dataset)
#dataset = dataset.shuffle(buffer_size=300)
# Using Tensorflow data Api to handle batches
dataset_train = dataset.take(200)
dataset_train = dataset_train.repeat()
dataset_train = dataset_train.batch(batch_size)
dataset_test = dataset.skip(200)
dataset_test = dataset_test.repeat()
dataset_test = dataset_test.batch(batch_size)
# Create an iterator
iter_train = dataset_train.make_one_shot_iterator()
iter_train_op = iter_train.get_next()
iter_test = dataset_test.make_one_shot_iterator()
iter_test_op = iter_test.get_next()
# Build model graph
self.build_graph()
# Train Loop
for i in range(10000):
batch_train = self.__session.run([iter_train_op])
batch_x_train, batch_y_train = batch_train[0]
# Print loss from time to time
if i % 100 == 0:
batch_test = self.__session.run([iter_test_op])
batch_x_test, batch_y_test = batch_test[0]
loss_train, summary_1 = self.__session.run([self.__loss,
self.__merged_summary_op],
feed_dict={self.__x_:
batch_x_train,
self.__y_:
batch_y_train,
self.__is_training: True})
loss_val, summary_2 = self.__session.run([self.__loss_val,
self.__val_summary],
feed_dict={self.__x_: batch_x_test,
self.__y_: batch_y_test,
self.__is_training: False})
print("Loss Train: {0} Loss Val: {1}".format(loss_train,
loss_val))
# Write to tensorboard summary
self.__writer.add_summary(summary_1, i)
self.__writer.add_summary(summary_2, i)
# Execute train op
self.__train_step.run(session=self.__session, feed_dict={
self.__x_: batch_x_train,
self.__y_: batch_y_train,
self.__is_training: True})
# Save model
if not os.path.exists(save_dir):
os.makedirs(save_dir)
checkpoint_path = os.path.join(save_dir, "model")
filename = self.__saver.save(self.__session, checkpoint_path)
print("Model saved in file: %s" % filename)
if __name__ == '__main__':
cnn = Train()
cnn.train()