用原始图像尺寸错误喂养张量流
feeding tensorflow with raw images dimension error
我对 tensorflow 很陌生，所以我尝试使用 tutorial 中的代码
用大小为 (944,944) 和 类 yes/no (1,0) 的图像提供一些层以查看它的性能，但我无法使其工作。我得到的最后一个错误是："Dimension size must be evenly divisible by 57032704 but is 3565440 for 'Reshape_1' with input shapes: [10,236,236,64], and with input tensors computed as partial shapes: input1 = [?,57032704]".
我不知道错误是来自任何重塑操作还是因为我不能像这样喂养神经元。代码如下：
import tensorflow as tf
import numpy as np
import os
# import cv2
from scipy import ndimage
import PIL
tf.logging.set_verbosity(tf.logging.INFO)
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.reshape(pool2, [-1,944*944*64])
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)
train_data, train_labels = load_images("C:\Users\Heads\Desktop\BDManchas_Semi")
eval_data = train_data.copy()
eval_labels = train_labels.copy()
# 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=10,
num_epochs=None,
shuffle=True)
classifier.train(
input_fn=train_input_fn,
steps=20000,
hooks=[logging_hook])
# Evaluate the model and print results
eval_input_fn = tf.estimator.inputs.numpy_input_fn(
x={"x": eval_data},
y=eval_labels,
num_epochs=1,
shuffle=False)
eval_results = classifier.evaluate(input_fn=eval_input_fn)
print(eval_results)
--------------------------------更多：------------ ----------------------
好的，现在我已经进行了重塑，我遇到了另一个错误，训练期间的损失是 NaN。我一直在研究这个（ 有一个很好的答案）但是对于我使用的每个新功能，都有不同的错误。我试图改变损失：
loss = tf.losses.sparse_softmax_cross_entropy(labels=labels, logits=logits)
至：
loss = tf.nn.sigmoid_cross_entropy_with_logits(labels=labels, logits=logits)
但是似乎reshape也有问题，错误说logits和labels必须有相同的shape ((10,10) vs (10,))，我试过reshape logits和labels但是我总是得到不同的错误（我想没有办法使两个数组相等）。
标签定义如下：
list_of_classes = []
# if ... class == 1
list_of_classes.append(1)
#else
list_of_classes.append(0)
labels = np.array(list_of_classes).astype("int32")
知道如何使用适当的损失吗？
初始问题
第二个池化层 (pool2) 的输出形状为 (1, 236, 236, 64)（卷积和池化减小了张量的大小），因此尝试将其重塑为 (-1, 944*944*64) (pool2_flat) 抛出错误。
为避免这种情况，您可以将 pool2_flat 定义为：
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)
关于您的修改
不知道你是如何定义你的标签的，很难说哪里做错了。 labels 的形状必须是 (None,)（批次中每个图像的 class 个 ID），而 logits 的形状必须是 (None, nb_classes)（每个图像的估计概率） class，对于批处理中的每个图像）。
以下代码对我有用：
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])
# ...
所以解决方案是更改行：
pool2_flat = tf.reshape(pool2, [-1,944*944*64])
对于行：
pool2_flat = tf.layers.flatten(pool2)
我还需要使用 512x512 调整大小的图像而不是 944x944，因为它不适合内存...
我对 tensorflow 很陌生，所以我尝试使用 tutorial 中的代码
用大小为 (944,944) 和 类 yes/no (1,0) 的图像提供一些层以查看它的性能，但我无法使其工作。我得到的最后一个错误是："Dimension size must be evenly divisible by 57032704 but is 3565440 for 'Reshape_1' with input shapes: [10,236,236,64],
我不知道错误是来自任何重塑操作还是因为我不能像这样喂养神经元。代码如下：
import tensorflow as tf
import numpy as np
import os
# import cv2
from scipy import ndimage
import PIL
tf.logging.set_verbosity(tf.logging.INFO)
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.reshape(pool2, [-1,944*944*64])
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)
train_data, train_labels = load_images("C:\Users\Heads\Desktop\BDManchas_Semi")
eval_data = train_data.copy()
eval_labels = train_labels.copy()
# 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=10,
num_epochs=None,
shuffle=True)
classifier.train(
input_fn=train_input_fn,
steps=20000,
hooks=[logging_hook])
# Evaluate the model and print results
eval_input_fn = tf.estimator.inputs.numpy_input_fn(
x={"x": eval_data},
y=eval_labels,
num_epochs=1,
shuffle=False)
eval_results = classifier.evaluate(input_fn=eval_input_fn)
print(eval_results)
--------------------------------更多：------------ ----------------------
好的，现在我已经进行了重塑，我遇到了另一个错误，训练期间的损失是 NaN。我一直在研究这个（
loss = tf.losses.sparse_softmax_cross_entropy(labels=labels, logits=logits)
至：
loss = tf.nn.sigmoid_cross_entropy_with_logits(labels=labels, logits=logits)
但是似乎reshape也有问题，错误说logits和labels必须有相同的shape ((10,10) vs (10,))，我试过reshape logits和labels但是我总是得到不同的错误（我想没有办法使两个数组相等）。
标签定义如下：
list_of_classes = []
# if ... class == 1
list_of_classes.append(1)
#else
list_of_classes.append(0)
labels = np.array(list_of_classes).astype("int32")
知道如何使用适当的损失吗？
初始问题
第二个池化层 (pool2) 的输出形状为 (1, 236, 236, 64)（卷积和池化减小了张量的大小），因此尝试将其重塑为 (-1, 944*944*64) (pool2_flat) 抛出错误。
为避免这种情况，您可以将 pool2_flat 定义为：
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)
关于您的修改
不知道你是如何定义你的标签的，很难说哪里做错了。 labels 的形状必须是 (None,)（批次中每个图像的 class 个 ID），而 logits 的形状必须是 (None, nb_classes)（每个图像的估计概率） class，对于批处理中的每个图像）。
以下代码对我有用：
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])
# ...
所以解决方案是更改行：
pool2_flat = tf.reshape(pool2, [-1,944*944*64])
对于行：
pool2_flat = tf.layers.flatten(pool2)
我还需要使用 512x512 调整大小的图像而不是 944x944，因为它不适合内存...