初始问题
第二个池层的输出(
pool2
)它的形状很好
(1, 236, 236, 64)
(卷积和池缩小了张量的大小),所以尝试将其重塑为
(-1, 944*944*64)
(
pool2_flat
)抛出一个错误。
为了避免这种情况,您可以定义
普尔二号公寓
作为:
pool2_shape = tf.shape(pool2)
pool2_flat = tf.reshape(pool2, [-1, pool2_shape[1] * pool2_shape[2] * pool2_shape[3]])
# or directly pool2_flat = tf.reshape(pool2, [-1, 236 * 236 * 64])
# if your dimensions are fixed...
# or more simply, as suggested by @xdurch0:
pool2_flat = tf.layers.flatten(pool2)
关于你的编辑
由于不知道自己是如何定义自己的标签的,很难判断哪里做错了。这个
labels
一定很健康
(None,)
(批处理中每个图像的类ID)
logits
一定很健康
(None, nb_classes)
(对于批次中的每个图像,每个类别的估计概率)。
以下代码适用于我:
def define_model(features, labels, mode):
"""Model function for CNN."""
# Input Layer
input_layer = tf.reshape(features["x"], [-1,944, 944, 1])
# Convolutional Layer #1
conv1 = tf.layers.conv2d(
inputs=input_layer,
filters=32,
kernel_size=[16, 16],
padding="same",
activation=tf.nn.relu)
# Pooling Layer #1
pool1 = tf.layers.max_pooling2d(inputs=conv1, pool_size=[2, 2], strides=2)
# Convolutional Layer #2 and Pooling Layer #2
conv2 = tf.layers.conv2d(
inputs=pool1,
filters=64,
kernel_size=[16, 16],
padding="same",
activation=tf.nn.relu)
pool2 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], strides=2)
# Dense Layer
pool2_flat = tf.layers.flatten(pool2)
dense = tf.layers.dense(inputs=pool2_flat, units=1024, activation=tf.nn.relu)
dropout = tf.layers.dropout(
inputs=dense, rate=0.4, training=mode == tf.estimator.ModeKeys.TRAIN)
# Logits Layer - raw predictions
logits = tf.layers.dense(inputs=dropout, units=10)
predictions = {
# Generate predictions (for PREDICT and EVAL mode)
"classes": tf.argmax(input=logits, axis=1),
# Add `softmax_tensor` to the graph. It is used for PREDICT and by the
# `logging_hook`.
"probabilities": tf.nn.softmax(logits, name="softmax_tensor")
}
if mode == tf.estimator.ModeKeys.PREDICT:
return tf.estimator.EstimatorSpec(mode=mode, predictions=predictions)
# Calculate Loss (for both TRAIN and EVAL modes)
loss = tf.losses.sparse_softmax_cross_entropy(labels=labels, logits=logits)
# Configure the Training Op (for TRAIN mode)
if mode == tf.estimator.ModeKeys.TRAIN:
optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.001)
train_op = optimizer.minimize(
loss=loss,
global_step=tf.train.get_global_step())
return tf.estimator.EstimatorSpec(mode=mode, loss=loss, train_op=train_op)
# Add evaluation metrics (for EVAL mode)
eval_metric_ops = {
"accuracy": tf.metrics.accuracy(
labels=labels, predictions=predictions["classes"])}
return tf.estimator.EstimatorSpec(
mode=mode, loss=loss, eval_metric_ops=eval_metric_ops)
if __name__ == '__main__':
# Load training and eval data
# mnist = tf.contrib.learn.datasets.load_dataset("mnist")
# train_data = mnist.train.images # Returns np.array
# train_labels = np.asarray(mnist.train.labels, dtype=np.int32)
def mock_load_images(path):
nb_classes = 10
dataset_size = 100
train_data = np.random.rand(dataset_size, 944, 944).astype(np.float32)
list_of_classes = [np.random.randint(nb_classes) for i in range(dataset_size)]
train_labels = np.array(list_of_classes, dtype=np.int32)
return train_data, train_labels
train_data, train_labels = mock_load_images("C:\\Users\\Heads\\Desktop\\BDManchas_Semi")
# Create the Estimator
classifier = tf.estimator.Estimator(
model_fn=define_model, model_dir="/tmp/convnet_model")
# Set up logging for predictions
tensors_to_log = {"probabilities": "softmax_tensor"}
logging_hook = tf.train.LoggingTensorHook(
tensors=tensors_to_log, every_n_iter=50)
# Train the model
train_input_fn = tf.estimator.inputs.numpy_input_fn(
x={"x": train_data},
y=train_labels,
batch_size=1,
num_epochs=None,
shuffle=True)
classifier.train(
input_fn=train_input_fn,
steps=20000,
hooks=[logging_hook])
# ...
