在训练完cnn模型后,我想可视化权重或打印出权重,我该怎么做呢? 甚至在训练后我也无法打印变量。 谢谢!
在训练完CNN模型后,您可以通过可视化来观察权重,或者通过打印输出来查看权重。但是,在训练后您可能无法直接打印变量。在训练完cnn模型后,我想可视化权重或打印出权重,我该怎么做呢? 甚至在训练后我也无法打印变量。 谢谢!
在训练完CNN模型后,您可以通过可视化来观察权重,或者通过打印输出来查看权重。但是,在训练后您可能无法直接打印变量。为了可视化权重,你可以使用tf.image_summary()
操作将卷积滤波器(或滤波器的一个切片)转换为摘要proto,使用tf.train.SummaryWriter
将它们写入日志,并使用TensorBoard可视化日志。
假设您有以下(简化版)程序:
filter = tf.Variable(tf.truncated_normal([8, 8, 3]))
images = tf.placeholder(tf.float32, shape=[None, 28, 28])
conv = tf.nn.conv2d(images, filter, strides=[1, 1, 1, 1], padding="SAME")
# More ops...
loss = ...
optimizer = tf.GradientDescentOptimizer(0.01)
train_op = optimizer.minimize(loss)
filter_summary = tf.image_summary(filter)
sess = tf.Session()
summary_writer = tf.train.SummaryWriter('/tmp/logs', sess.graph_def)
for i in range(10000):
sess.run(train_op)
if i % 10 == 0:
# Log a summary every 10 steps.
summary_writer.add_summary(filter_summary, i)
完成此操作后,您可以启动TensorBoard来可视化/tmp/logs
中的日志,并可以看到过滤器的可视化。
请注意,此技巧将深度为3的过滤器可视化为RGB图像(以匹配输入图像的通道)。如果您有更深的过滤器,或者它们没有意义解释为颜色通道,则可以使用tf.split()
操作在深度维上拆分过滤器,并为每个深度生成一个图像摘要。
tf.Variable
对象传递给 sess.run()
,它将返回一个包含权重的 numpy 数组。 - mrrytf.image_summary(tag, tensor, ...)
。 - Dima Lituievtf.image_summary
已经被弃用,取而代之的是tf.summary.image
。详情请参见https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/ops/logging_ops.py。 - P-Gn像@mrry所说,你可以使用tf.image_summary
。例如,在cifar10_train.py
中,你可以在def train()
下的某个地方放置这段代码。注意如何在scope 'conv1'下访问变量。
# Visualize conv1 features
with tf.variable_scope('conv1') as scope_conv:
weights = tf.get_variable('weights')
# scale weights to [0 255] and convert to uint8 (maybe change scaling?)
x_min = tf.reduce_min(weights)
x_max = tf.reduce_max(weights)
weights_0_to_1 = (weights - x_min) / (x_max - x_min)
weights_0_to_255_uint8 = tf.image.convert_image_dtype (weights_0_to_1, dtype=tf.uint8)
# to tf.image_summary format [batch_size, height, width, channels]
weights_transposed = tf.transpose (weights_0_to_255_uint8, [3, 0, 1, 2])
# this will display random 3 filters from the 64 in conv1
tf.image_summary('conv1/filters', weights_transposed, max_images=3)
如果您想将所有conv1
滤波器可视化为一个漂亮的网格,您需要自己将它们组织成一个网格。今天我做到了,所以现在我想分享一个用于将conv1可视化为网格的gist
with tf.variable_scope('conv1', reuse=True) as scope_conv:
W_conv1 = tf.get_variable('weights', shape=[5, 5, 1, 32])
weights = W_conv1.eval()
with open("conv1.weights.npz", "w") as outfile:
np.save(outfile, weights)
'conv1'
)和变量名(在我的情况下为'weights'
)。接下来就是对numpy数组进行可视化。一个展示numpy数组的例子如下:#!/usr/bin/env python
"""Visualize numpy arrays."""
import numpy as np
import scipy.misc
arr = np.load('conv1.weights.npb')
# Get each 5x5 filter from the 5x5x1x32 array
for filter_ in range(arr.shape[3]):
# Get the 5x5x1 filter:
extracted_filter = arr[:, :, :, filter_]
# Get rid of the last dimension (hence get 5x5):
extracted_filter = np.squeeze(extracted_filter)
# display the filter (might be very small - you can resize the window)
scipy.misc.imshow(extracted_filter)
with open("conv1.weights.npz", "wb") as outfile:
(注意b)与Python 3一起使用。 - mimoralea使用 tensorflow 2 API
,有几个选项:
使用 get_weights()
函数提取权重。
weights_n = model.layers[n].get_weights()[0]
使用 numpy()
转换函数提取偏差。
bias_n = model.layers[n].bias.numpy()