TensorBoard中的Tensorflow混淆矩阵
deep-learning
python
tensorboard
tensorflow
5
0

我想在张量板上看到混乱矩阵的图像。为此,我正在修改Tensorflow Slim的评估示例: https : //github.com/tensorflow/models/blob/master/slim/eval_image_classifier.py

在此示例代码中,已经提供了“准确性”,但是无法直接添加“混淆矩阵”指标,因为它没有流式传输。

流指标和非流指标有什么区别?

因此,我尝试像这样添加它:

c_matrix = slim.metrics.confusion_matrix(predictions, labels)

#These operations needed for image summary
c_matrix = tf.cast(c_matrix, uint8)
c_matrix = tf.expand_dims(c_matrix, 2)
c_matrix = tf.expand_dims(c_matrix, 0)

op = tf.image_summary("confusion matrix", c_matrix, collections=[])
tf.add_to_collection(tf.GraphKeys.SUMMARIES, op)

这会在张量板上创建图像,但可能存在格式问题。矩阵应在0-1之间归一化,以便产生有意义的图像。

如何产生有意义的混淆矩阵?如何处理多批次评估流程?

参考资料:
Stack Overflow
收藏
评论
共 3 个回答
高赞 时间 活跃

这是与tf.contrib.metrics.MetricSpec一起使用的功能(使用Estimator时)。它的灵感来自Jerod的答案和metric_op.py源文件。您将获得一个包含百分比的流式混淆矩阵:

from tensorflow.python.framework import ops,dtypes
from tensorflow.python.ops import array_ops,variables

def _createLocalVariable(name, shape, collections=None, 
validate_shape=True,
              dtype=dtypes.float32):
  """Creates a new local variable.
  """
  # Make sure local variables are added to 
  # tf.GraphKeys.LOCAL_VARIABLES
  collections = list(collections or [])
  collections += [ops.GraphKeys.LOCAL_VARIABLES]
  return variables.Variable(
  initial_value=array_ops.zeros(shape, dtype=dtype),
  name=name,
  trainable=False,
  collections=collections,
  validate_shape=validate_shape)

def streamingConfusionMatrix(label, prediction, 
weights=None,num_classes=None):
  """
  Compute a streaming confusion matrix
  :param label: True labels
  :param prediction: Predicted labels
  :param weights: (Optional) weights (unused)
  :param num_classes: Number of labels for the confusion matrix
  :return: (percentConfusionMatrix,updateOp)
  """
  # Compute a per-batch confusion

  batch_confusion = tf.confusion_matrix(label, prediction,
                                    num_classes=num_classes,
                                    name='batch_confusion')

  count = _createLocalVariable(None,(),dtype=tf.int32)
  confusion = _createLocalVariable('streamConfusion',[num_classes, 
  num_classes],dtype=tf.int32)

  # Create the update op for doing a "+=" accumulation on the batch
  countUpdate = count.assign(count + tf.reduce_sum(batch_confusion))
  confusionUpdate = confusion.assign(confusion + batch_confusion)

  updateOp = tf.group(confusionUpdate,countUpdate)

  percentConfusion = 100 * tf.truediv(confusion,count)

  return percentConfusion,updateOp

然后可以通过以下方式将其用作评估指标:

from tensorflow.contrib import learn,metrics
#[...]

evalMetrics = {'accuracy': 
learn.MetricSpec(metric_fn=metrics.streaming_accuracy),
               'confusionMatrix':learn.MetricSpec(metric_fn=
                                                  lambda 
label,prediction,weights=None:                         
streamingConfusionMatrix(                                                    
label,prediction,weights,num_classes=nLabels))}

我建议您使用numpy.set_printoptions(precision = 2,suppress = True)进行打印。

收藏
评论

这是我为测试代码生成和显示“流式”混淆矩阵的方式(返回的test_op将针对要测试的每个批次进行评估)。

def _get_streaming_metrics(prediction,label,num_classes):

    with tf.name_scope("test"):
        # the streaming accuracy (lookup and update tensors)
        accuracy,accuracy_update = tf.metrics.accuracy(label, prediction, 
                                               name='accuracy')
        # Compute a per-batch confusion
        batch_confusion = tf.confusion_matrix(label, prediction,
                                             num_classes=num_classes,
                                             name='batch_confusion')
        # Create an accumulator variable to hold the counts
        confusion = tf.Variable( tf.zeros([num_classes,num_classes], 
                                          dtype=tf.int32 ),
                                 name='confusion' )
        # Create the update op for doing a "+=" accumulation on the batch
        confusion_update = confusion.assign( confusion + batch_confusion )
        # Cast counts to float so tf.summary.image renormalizes to [0,255]
        confusion_image = tf.reshape( tf.cast( confusion, tf.float32),
                                  [1, num_classes, num_classes, 1])
        # Combine streaming accuracy and confusion matrix updates in one op
        test_op = tf.group(accuracy_update, confusion_update)

        tf.summary.image('confusion',confusion_image)
        tf.summary.scalar('accuracy',accuracy)

    return test_op,accuracy,confusion

通过运行test_op处理所有数据批处理test_op ,您可以根据需要简单地通过confusion.eval()sess.eval(confusion)查找最终的混淆矩阵(在会话内)。

收藏
评论

这是我整理的东西,效果很好。仍然需要调整一些信息,例如刻度位置等。

Tensorflow中的图像混淆矩阵

这是将为您做所有事情的功能。

from textwrap import wrap
import re
import itertools
import tfplot
import matplotlib
import numpy as np
from sklearn.metrics import confusion_matrix



def plot_confusion_matrix(correct_labels, predict_labels, labels, title='Confusion matrix', tensor_name = 'MyFigure/image', normalize=False):
''' 
Parameters:
    correct_labels                  : These are your true classification categories.
    predict_labels                  : These are you predicted classification categories
    labels                          : This is a lit of labels which will be used to display the axix labels
    title='Confusion matrix'        : Title for your matrix
    tensor_name = 'MyFigure/image'  : Name for the output summay tensor

Returns:
    summary: TensorFlow summary 

Other itema to note:
    - Depending on the number of category and the data , you may have to modify the figzie, font sizes etc. 
    - Currently, some of the ticks dont line up due to rotations.
'''
cm = confusion_matrix(correct_labels, predict_labels, labels=labels)
if normalize:
    cm = cm.astype('float')*10 / cm.sum(axis=1)[:, np.newaxis]
    cm = np.nan_to_num(cm, copy=True)
    cm = cm.astype('int')

np.set_printoptions(precision=2)
###fig, ax = matplotlib.figure.Figure()

fig = matplotlib.figure.Figure(figsize=(7, 7), dpi=320, facecolor='w', edgecolor='k')
ax = fig.add_subplot(1, 1, 1)
im = ax.imshow(cm, cmap='Oranges')

classes = [re.sub(r'([a-z](?=[A-Z])|[A-Z](?=[A-Z][a-z]))', r'\1 ', x) for x in labels]
classes = ['\n'.join(wrap(l, 40)) for l in classes]

tick_marks = np.arange(len(classes))

ax.set_xlabel('Predicted', fontsize=7)
ax.set_xticks(tick_marks)
c = ax.set_xticklabels(classes, fontsize=4, rotation=-90,  ha='center')
ax.xaxis.set_label_position('bottom')
ax.xaxis.tick_bottom()

ax.set_ylabel('True Label', fontsize=7)
ax.set_yticks(tick_marks)
ax.set_yticklabels(classes, fontsize=4, va ='center')
ax.yaxis.set_label_position('left')
ax.yaxis.tick_left()

for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
    ax.text(j, i, format(cm[i, j], 'd') if cm[i,j]!=0 else '.', horizontalalignment="center", fontsize=6, verticalalignment='center', color= "black")
fig.set_tight_layout(True)
summary = tfplot.figure.to_summary(fig, tag=tensor_name)
return summary
#

这是调用此函数所需的其余代码。

''' confusion matrix summaries '''
img_d_summary_dir = os.path.join(checkpoint_dir, "summaries", "img")
img_d_summary_writer = tf.summary.FileWriter(img_d_summary_dir, sess.graph)
img_d_summary = plot_confusion_matrix(correct_labels, predict_labels, labels, tensor_name='dev/cm')
img_d_summary_writer.add_summary(img_d_summary, current_step)

混淆了!!!

收藏
评论
新手导航
  • 社区规范
  • 提出问题
  • 进行投票
  • 个人资料
  • 优化问题
  • 回答问题

关于我们

常见问题

内容许可

联系我们

@2020 AskGo
京ICP备20001863号