Tensorflow：每个班级的借据答案

【问题标题】：Tensorflow : IOU per classTensorflow：每个班级的借据
【发布时间】：2019-07-17 03:56:46
【问题描述】：

我正在尝试使用 deeplab 进行语义分割。我想计算每个班级的 IOU（仅限个人的 IOU）而不是平均 IOU。

在 L142 的 https://github.com/tensorflow/models/blob/master/research/deeplab/eval.py, 我试图通过

得到混淆矩阵而不是平均IOU

miou, cmat = tf.metrics.mean_iou(...)
metric_map['cmat'] = cmat

但它不起作用。如果有人建议我如何出行，我将不胜感激。

【问题讨论】：

标签： tensorflow

【解决方案1】：

您可以使用tensorflow.python.ops.metrics_impl 中的_streaming_confusion_matrix 来获取混淆矩阵。本质上，它的工作方式与其他运行指标（如 mean_iou）相同。这意味着，在调用此指标时，您会得到两个操作，一个是总的混淆矩阵操作，另一个是累积更新混淆矩阵的更新操作。

有了混淆矩阵，现在你应该能够计算类明智的 iou

【讨论】：

【解决方案2】：

为此，我基于 MeanIoU 类实现了一个特定于类的 IoU 指标。

class ClassIoU(tf.keras.metrics.MeanIoU):
"""Computes the class-specific Intersection-Over-Union metric.

IOU is defined as follows:
  IOU = true_positive / (true_positive + false_positive + false_negative).
The predictions are accumulated in a confusion matrix, weighted by
`sample_weight` and the metric is then calculated from it.

If `sample_weight` is `None`, weights default to 1.
Use `sample_weight` of 0 to mask values.

Args:
  class_idx: The index of the the class of interest
  one_hot: Indicates if the input is a one_hot vector as in CategoricalCrossentropy or if the class indices
    are used as in SparseCategoricalCrossentropy or MeanIoU
  num_classes: The possible number of labels the prediction task can have.
    This value must be provided, since a confusion matrix of dimension =
    [num_classes, num_classes] will be allocated.
  name: (Optional) string name of the metric instance.
  dtype: (Optional) data type of the metric result.
"""
def __init__(self, class_idx, one_hot, num_classes, name=None, dtype=None):
    super().__init__(num_classes, name, dtype)
    self.one_hot = one_hot
    self.class_idx = class_idx

def result(self):
    sum_over_row = tf.cast(
        tf.reduce_sum(self.total_cm, axis=0), dtype=self._dtype)
    sum_over_col = tf.cast(
        tf.reduce_sum(self.total_cm, axis=1), dtype=self._dtype)
    true_positives = tf.cast(
        tf.linalg.diag_part(self.total_cm), dtype=self._dtype)

    # sum_over_row + sum_over_col =
    #     2 * true_positives + false_positives + false_negatives.
    denominator = sum_over_row[self.class_idx] + sum_over_col[self.class_idx] \
        - true_positives[self.class_idx]

    # The mean is only computed over classes that appear in the
    # label or prediction tensor. If the denominator is 0, we need to
    # ignore the class.
    num_valid_entries = tf.reduce_sum(
        tf.cast(tf.not_equal(denominator, 0), dtype=self._dtype))

    iou = tf.math.divide_no_nan(true_positives[self.class_idx], denominator)

    return tf.math.divide_no_nan(
        tf.reduce_sum(iou, name='mean_iou'), num_valid_entries)

def update_state(self, y_true, y_pred, sample_weight=None):
    if self.one_hot:
        return super().update_state(tf.argmax(y_true, axis=-1), tf.argmax(y_pred, axis=-1), sample_weight)
    else:
        return super().update_state(y_true, y_pred, sample_weight)

【讨论】：