python - 如何使用经过训练的模型
问题描述
我已经训练了我的网络并保存了模型。至此,我认为一切都是正确的。当我尝试使用此模型来预测独立程序中的数据值时,问题就开始了。我不想训练模型,我只想用它来预测值。我应该如何恢复它?我只发布了部分代码,在那里可以看到一个整体
def main(_):
train_data_node = tf.placeholder(
data_type(),
shape=(BATCH_SIZE, IMAGE_SIZE, IMAGE_SIZE, NUM_CHANNELS))
train_labels_node = tf.placeholder(tf.int64, shape=(BATCH_SIZE,))
eval_data = tf.placeholder(
data_type(),
shape=(EVAL_BATCH_SIZE, IMAGE_SIZE, IMAGE_SIZE, NUM_CHANNELS))
# The variables below hold all the trainable weights. They are passed an
# initial value which will be assigned when we call:
# {tf.global_variables_initializer().run()}
conv1_weights = tf.Variable(
tf.truncated_normal([5, 5, NUM_CHANNELS, 32], # 5x5 filter, depth 32.
stddev=0.1,
seed=SEED, dtype=data_type()))
conv1_biases = tf.Variable(tf.zeros([32], dtype=data_type()))
conv2_weights = tf.Variable(tf.truncated_normal(
[5, 5, 32, 64], stddev=0.1,
seed=SEED, dtype=data_type()))
conv2_biases = tf.Variable(tf.constant(0.1, shape=[64], dtype=data_type()))
fc1_weights = tf.Variable( # fully connected, depth 512.
tf.truncated_normal([IMAGE_SIZE // 4 * IMAGE_SIZE // 4 * 64, 512],
stddev=0.1,
seed=SEED,
dtype=data_type()))
fc1_biases = tf.Variable(tf.constant(0.1, shape=[512], dtype=data_type()))
fc2_weights = tf.Variable(tf.truncated_normal([512, NUM_LABELS],
stddev=0.1,
seed=SEED,
dtype=data_type()))
fc2_biases = tf.Variable(tf.constant(
0.1, shape=[NUM_LABELS], dtype=data_type()))
# We will replicate the model structure for the training subgraph, as well
# as the evaluation subgraphs, while sharing the trainable parameters.
def model(data, train=False):
"""The Model definition."""
# 2D convolution, with 'SAME' padding (i.e. the output feature map has
# the same size as the input). Note that {strides} is a 4D array whose
# shape matches the data layout: [image index, y, x, depth].
conv = tf.nn.conv2d(data,
conv1_weights,
strides=[1, 1, 1, 1],
padding='SAME')
# Bias and rectified linear non-linearity.
relu = tf.nn.relu(tf.nn.bias_add(conv, conv1_biases))
# Max pooling. The kernel size spec {ksize} also follows the layout of
# the data. Here we have a pooling window of 2, and a stride of 2.
pool = tf.nn.max_pool(relu,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
padding='SAME')
conv = tf.nn.conv2d(pool,
conv2_weights,
strides=[1, 1, 1, 1],
padding='SAME')
relu = tf.nn.relu(tf.nn.bias_add(conv, conv2_biases))
pool = tf.nn.max_pool(relu,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
padding='SAME')
# Reshape the feature map cuboid into a 2D matrix to feed it to the
# fully connected layers.
pool_shape = pool.get_shape().as_list()
reshape = tf.reshape(
pool,
[pool_shape[0], pool_shape[1] * pool_shape[2] * pool_shape[3]])
# Fully connected layer. Note that the '+' operation automatically
# broadcasts the biases.
hidden = tf.nn.relu(tf.matmul(reshape, fc1_weights) + fc1_biases)
# Add a 50% dropout during training only. Dropout also scales
# activations such that no rescaling is needed at evaluation time.
if train:
hidden = tf.nn.dropout(hidden, 0.5, seed=SEED)
return tf.matmul(hidden, fc2_weights) + fc2_biases
# Training computation: logits + cross-entropy loss.
logits = model(train_data_node, True)
loss = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(
labels=train_labels_node, logits=logits))
# L2 regularization for the fully connected parameters.
regularizers = (tf.nn.l2_loss(fc1_weights) + tf.nn.l2_loss(fc1_biases) +
tf.nn.l2_loss(fc2_weights) + tf.nn.l2_loss(fc2_biases))
# Add the regularization term to the loss.
loss += 5e-4 * regularizers
# Optimizer: set up a variable that's incremented once per batch and
# controls the learning rate decay.
batch = tf.Variable(0, dtype=data_type())
# Decay once per epoch, using an exponential schedule starting at 0.01.
learning_rate = tf.train.exponential_decay(
0.005, # Base learning rate.
batch * BATCH_SIZE, # Current index into the dataset.
train_size, # Decay step.
0.95, # Decay rate.
staircase=True)
# Use simple momentum for the optimization.
optimizer = tf.train.MomentumOptimizer(learning_rate,
0.9).minimize(loss,
global_step=batch)
# Predictions for the current training minibatch.
train_prediction = tf.nn.softmax(logits)
# Predictions for the test and validation, which we'll compute less often.
eval_prediction = tf.nn.softmax(model(eval_data))
# Small utility function to evaluate a dataset by feeding batches of data to
# {eval_data} and pulling the results from {eval_predictions}.
# Saves memory and enables this to run on smaller GPUs.
def eval_in_batches(data, sess):
"""Get all predictions for a dataset by running it in small batches."""
size = data.shape[0]
if size < EVAL_BATCH_SIZE:
raise ValueError("batch size for evals larger than dataset: %d" % size)
predictions = numpy.ndarray(shape=(size, NUM_LABELS), dtype=numpy.float32)
for begin in xrange(0, size, EVAL_BATCH_SIZE):
end = begin + EVAL_BATCH_SIZE
if end <= size:
predictions[begin:end, :] = sess.run(
eval_prediction,
feed_dict={eval_data: data[begin:end, ...]})
else:
batch_predictions = sess.run(
eval_prediction,
feed_dict={eval_data: data[-EVAL_BATCH_SIZE:, ...]})
predictions[begin:, :] = batch_predictions[begin - size:, :]
return predictions
# Create a local session to run the training.
start_time = time.time()
saver = tf.train.Saver()
with tf.Session() as sess:
# Run all the initializers to prepare the trainable parameters.
tf.global_variables_initializer().run()
print('Initialized!')
# Loop through training steps.
for step in xrange(int(num_epochs * train_size*4) // BATCH_SIZE):
# Compute the offset of the current minibatch in the data.
# Note that we could use better randomization across epochs.
offset = (step * BATCH_SIZE) % (train_size - BATCH_SIZE)
batch_data = train_data[offset:(offset + BATCH_SIZE), ...]
batch_labels = train_labels[offset:(offset + BATCH_SIZE)]
# This dictionary maps the batch data (as a numpy array) to the
# node in the graph it should be fed to.
feed_dict = {train_data_node: batch_data,
train_labels_node: batch_labels}
# Run the optimizer to update weights.
sess.run(optimizer, feed_dict=feed_dict)
# print some extra information once reach the evaluation frequency
if step % EVAL_FREQUENCY == 0:
# fetch some extra nodes' data
l, lr, predictions = sess.run([loss, learning_rate, train_prediction],
feed_dict=feed_dict)
elapsed_time = time.time() - start_time
start_time = time.time()
print('Step %d (epoch %.2f), %.1f ms' %
(step, float(step) * BATCH_SIZE / train_size,
1000 * elapsed_time / EVAL_FREQUENCY))
print('Minibatch loss: %.3f, learning rate: %.6f' % (l, lr))
print('Minibatch error: %.1f%%' % error_rate(predictions, batch_labels))
sys.stdout.flush()
# Finally print the result!
test_error = error_rate(eval_in_batches(test_data, sess), test_labels)
print('Test error: %.1f%%' % test_error)
#saver.save(sess, '/my-model')
save_path = saver.save(sess, "kupa/model_path")
if FLAGS.self_test:
print('test_error', test_error)
assert test_error == 0.0, 'expected 0.0 test_error, got %.2f' % (
test_error,)
if __name__ == '__main__':
tf.app.run()
解决方案
推荐阅读
- c# - 将 Windows 10 更新到版本 1803 后 C# UWP SpeechRecognizer() 不会初始化
- java - 在 Java 中求和时出现 NaN 错误
- reactive-programming - 将多个响应式请求连接到一个 Mono
- python - 将列表值传递给 loadworkbook || Python
- java - 两个 Jackson ObjectMapper 生成不同的序列化
- logging - 日志文件处理:缩短长十六进制字符串
- node.js - 在单存储库中对多个微服务进行 Dockerizing
- powershell - PFX 导入失败...?
- matlab - 正确理解和应用树图功能
- javascript - 如何循环一个 Web Worker?