python - 如何将张量板可视化集成到 tf.Estimator?
问题描述
我有用于识别手写数字的经典 TensorFlow 代码https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/tutorials/mnist/mnist_with_summaries.py,使用 tf.Estimator。我的问题很复杂,由两个问题组成
我应该为代码中的目标变量编写 tf.summary() 以可视化 Tensoboard 中的数据,只需键入
tensorboard -- logdir=/tmp/mnist_convnet_model
或 tf.Estimator 自动收集*/tmp/mnist_convnet_model
目录中的所有摘要,我可以调用tensorboard -- logdir=/tmp/mnist_convnet_model
吗?如果我必须写
tf.summary()
你能回答我,我应该在代码tf summary merge_all()
中插入代码吗?在哪一段代码中?
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import numpy as np
import tensorflow as tf
tf.logging.set_verbosity(tf.logging.INFO)
def cnn_model_fn(features, labels, mode):
"""Model function for CNN."""
# Input Layer
input_layer = tf.reshape(features["x"], [-1, 28, 28, 1])
# Convolutional Layer #1
conv1 = tf.layers.conv2d(
inputs=input_layer,
filters=32,
kernel_size=[5, 5],
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
conv2 = tf.layers.conv2d(
inputs=pool1,
filters=64,
kernel_size=[5, 5],
padding="same",
activation=tf.nn.relu)
# Pooling Layer #2
pool2 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], strides=2)
# Flatten tensor into a batch of vectors
pool2_flat = tf.reshape(pool2, [-1, 7 * 7 * 64])
# Dense Layer
dense = tf.layers.dense(inputs=pool2_flat, units=1024, activation=tf.nn.relu)
# Add dropout operation; 0.6 probability that element will be kept
dropout = tf.layers.dropout(
inputs=dense, rate=0.4, training=mode == tf.estimator.ModeKeys.TRAIN)
# Logits layer
# Input Tensor Shape: [batch_size, 1024]
# Output Tensor Shape: [batch_size, 10]
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)
def main(unused_argv):
# 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)
eval_data = mnist.test.images # Returns np.array
eval_labels = np.asarray(mnist.test.labels, dtype=np.int32)
# Create the Estimator
mnist_classifier = tf.estimator.Estimator(
model_fn=cnn_model_fn, model_dir="/tmp/mnist_convnet_model")
# Set up logging for predictions
# Log the values in the "Softmax" tensor with label "probabilities"
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.compat.v1.estimator.inputs.numpy_input_fn(
x={"x": train_data},
y=train_labels,
batch_size=100,
num_epochs=None,
shuffle=True)
mnist_classifier.train(
input_fn=train_input_fn,
steps=20000,
hooks=[logging_hook])
# Evaluate the model and print results
eval_input_fn = tf.compat.v1.estimator.inputs.numpy_input_fn(
x={"x": eval_data}, y=eval_labels, num_epochs=1, shuffle=False)
eval_results = mnist_classifier.evaluate(input_fn=eval_input_fn)
print(eval_results)
if __name__ == "__main__":
tf.app.run()
解决方案
通常,您只需要指定tf.summary.scalar()
,tf.summary.histogram()
或tf.summary.image()
代码中的任何位置。您可以通过以下方式使用直方图摘要来捕获所有权重和偏差
for value in tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES):
tf.summary.histogram(value.name, value)
至于可更新的指标摘要,例如 f1 分数的准确性,您需要将其包装eval_metric_ops
并传递给tf.estimator.EstimatorSpec
accuracy = tf.metrics.accuracy(labels=labels, predictions=predictions)
eval_metric_ops = {'accuracy': accuracy}
- 您可以使用您在训练期间指定的相同目录调用 tensorboard。
- 你不需要使用
tf.summary.merge_all()
推荐阅读
- flutter - 从 Flutter 登录 google 时,帐户选择器后没有任何反应
- html - 响应性/左边距
- java - 如何根据其他线程的响应在主线程中执行某些任务?
- assembly - x86 实模式函数调用未执行
- c# - MVVM 数据绑定问题,源属性未更新
- plot - 在 GrADS 的图中添加条形图?
- python - 如何更改我选择的像素的颜色?
- python - 两个文件之间的烧瓶 url_for BuildError
- javascript - 重新发送 otp 的功能在 django 项目中不起作用
- python - 在anaconda python上导入scipy时出现FileNotFoundError