嗨，我使用自己的数据集来训练模型，但我有错误，我在下面提到。我的数据集有 124 个类，标签是 0 到 123，大小是 60*60 gray，批次是 10，结果是：
labels.eval() --> [ 1 101 101 103 103 103 103 100 102 1] -- len(lables.eval())= 10
原始图片大小 --> (?, 60, 60, 1)
第一个卷积层 (?, 30, 30, 32)
第二个卷积层。(?, 15, 15, 64)
变平。(?, 14400)
密集 .1 (?, 2048)
密集 0.2 (?, 124)
错误
ensorflow.python.framework.errors_impl.InvalidArgumentError: logits and
labels must have the same first dimension, got logits shape [40,124] and
labels shape [10]
代码
def model_fn(features, labels, mode, params):
# Reference to the tensor named "image" in the input-function.
x = features["image"]
# The convolutional layers expect 4-rank tensors
# but x is a 2-rank tensor, so reshape it.
net = tf.reshape(x, [-1, img_size, img_size, num_channels])
# First convolutional layer.
net = tf.layers.conv2d(inputs=net, name='layer_conv1',
filters=32, kernel_size=3,
padding='same', activation=tf.nn.relu)
net = tf.layers.max_pooling2d(inputs=net, pool_size=2, strides=2)
# Second convolutional layer.
net = tf.layers.conv2d(inputs=net, name='layer_conv2',
filters=64, kernel_size=3,
padding='same', activation=tf.nn.relu)
net = tf.layers.max_pooling2d(inputs=net, pool_size=2, strides=2)
# Flatten to a 2-rank tensor.
net = tf.contrib.layers.flatten(net)
# Eventually this should be replaced with:
# net = tf.layers.flatten(net)
# First fully-connected / dense layer.
# This uses the ReLU activation function.
net = tf.layers.dense(inputs=net, name='layer_fc1',
units=2048, activation=tf.nn.relu)
# Second fully-connected / dense layer.
# This is the last layer so it does not use an activation function.
net = tf.layers.dense(inputs=net, name='layer_fc_2',
units=num_classes)
# Logits output of the neural network.
logits = net
y_pred = tf.nn.softmax(logits=logits)
y_pred_cls = tf.argmax(y_pred, axis=1)
if mode == tf.estimator.ModeKeys.PREDICT:
spec = tf.estimator.EstimatorSpec(mode=mode,
predictions=y_pred_cls)
else:
cross_entropy =
tf.nn.sparse_softmax_cross_entropy_with_logits(labels=labels,
logits=logits)
loss = tf.reduce_mean(cross_entropy)
optimizer =
tf.train.AdamOptimizer(learning_rate=params["learning_rate"])
train_op = optimizer.minimize(
loss=loss, global_step=tf.train.get_global_step())
metrics = \
{
"accuracy": tf.metrics.accuracy(labels, y_pred_cls)
}
spec = tf.estimator.EstimatorSpec(
mode=mode,
loss=loss,
train_op=train_op,
eval_metric_ops=metrics)
return spec`
这个标签通过 tfrecords 来自这里：
def input_fn(filenames, train, batch_size=10, buffer_size=2048):
# Args:
# filenames: Filenames for the TFRecords files.
# train: Boolean whether training (True) or testing (False).
# batch_size: Return batches of this size.
# buffer_size: Read buffers of this size. The random shuffling
# is done on the buffer, so it must be big enough.
# Create a TensorFlow Dataset-object which has functionality
# for reading and shuffling data from TFRecords files.
dataset = tf.data.TFRecordDataset(filenames=filenames)
# Parse the serialized data in the TFRecords files.
# This returns TensorFlow tensors for the image and labels.
dataset = dataset.map(parse)
if train:
# If training then read a buffer of the given size and
# randomly shuffle it.
dataset = dataset.shuffle(buffer_size=buffer_size)
# Allow infinite reading of the data.
num_repeat = None
else:
# If testing then don't shuffle the data.
# Only go through the data once.
num_repeat = 1
# Repeat the dataset the given number of times.
dataset = dataset.repeat(num_repeat)
# Get a batch of data with the given size.
dataset = dataset.batch(batch_size)
# Create an iterator for the dataset and the above modifications.
iterator = dataset.make_one_shot_iterator()
# Get the next batch of images and labels.
images_batch, labels_batch = iterator.get_next()
# The input-function must return a dict wrapping the images.
x = {'image': images_batch}
y = labels_batch
print(x, ' - ', y.get_shape())
return x, y
我通过此代码生成标签，例如 image name=math-1 , lable = 1
def get_lable_and_image(path):
lbl = []
img = []
for filename in glob.glob(os.path.join(path, '*.png')):
img.append(filename)
lable = filename[41:].split()[0].split('-')[1]
lbl.append(int(lable))
lables = np.array(lbl)
images = np.array(img)
# print(images[1], lables[1])
return images, lables
我推送图像和标签来创建 tfrecords
def convert(image_paths, labels, out_path):
# Args:
# image_paths List of file-paths for the images.
# labels Class-labels for the images.
# out_path File-path for the TFRecords output file.
print("Converting: " + out_path)
# Number of images. Used when printing the progress.
num_images = len(image_paths)
# Open a TFRecordWriter for the output-file.
with tf.python_io.TFRecordWriter(out_path) as writer:
# Iterate over all the image-paths and class-labels.
for i, (path, label) in enumerate(zip(image_paths, labels)):
# Print the percentage-progress.
print_progress(count=i, total=num_images-1)
# Load the image-file using matplotlib's imread function.
img = imread(path)
# Convert the image to raw bytes.
img_bytes = img.tostring()
# Create a dict with the data we want to save in the
# TFRecords file. You can add more relevant data here.
data = \
{
'image': wrap_bytes(img_bytes),
'label': wrap_int64(label)
}
# Wrap the data as TensorFlow Features.
feature = tf.train.Features(feature=data)
# Wrap again as a TensorFlow Example.
example = tf.train.Example(features=feature)
# Serialize the data.
serialized = example.SerializeToString()
# Write the serialized data to the TFRecords file.
writer.write(serialized)