Python mean pixel accuracy

7 Python code examples are found related to " mean pixel accuracy". You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example.
Example 1
Source File: metric.py    From FNA with Apache License 2.0 7 votes vote down vote up 
def mean_pixel_accuracy(pixel_correct, pixel_labeled):
    mean_pixel_accuracy = 1.0 * np.sum(pixel_correct) / (
            np.spacing(1) + np.sum(pixel_labeled))

    return mean_pixel_accuracy
Example 2
Source File: utils.py    From Semantic-Aware-Scene-Recognition with MIT License 5 votes vote down vote up 
def MeanPixelAccuracy(pred, label):
    """
    Function to compute the mean pixel accuracy for semantic segmentation between mini-batch tensors
    :param pred: Tensor of predictions
    :param label: Tensor of ground-truth
    :return: Mean pixel accuracy for all the mini-bath
    """
    # Convert tensors to numpy arrays
    imPred = np.asarray(torch.squeeze(pred))
    imLab = np.asarray(torch.squeeze(label))

    # Create empty numpy arrays
    pixel_accuracy = np.empty(imLab.shape[0])
    pixel_correct = np.empty(imLab.shape[0])
    pixel_labeled = np.empty(imLab.shape[0])

    # Compute pixel accuracy for each pair of images in the batch
    for i in range(imLab.shape[0]):
        pixel_accuracy[i], pixel_correct[i], pixel_labeled[i] = pixelAccuracy(imPred[i], imLab[i])

    # Compute the final accuracy for the batch
    acc = 100.0 * np.sum(pixel_correct) / (np.spacing(1) + np.sum(pixel_labeled))

    return acc
Example 3
Source File: eval.py    From Deeplab-v3plus with MIT License 5 votes vote down vote up 
def Mean_Pixel_Accuracy(self):
        MPA = np.diag(self.confusion_matrix) / self.confusion_matrix.sum(axis=1)
        MPA = np.nanmean(MPA)

        return MPA
Example 4
Source File: eval.py    From MaxSquareLoss with MIT License 5 votes vote down vote up 
def Mean_Pixel_Accuracy(self, out_16_13=False):
        MPA = np.diag(self.confusion_matrix) / self.confusion_matrix.sum(axis=1)
        if self.synthia:
            MPA_16 = np.nanmean(MPA[:self.ignore_index])
            MPA_13 = np.nanmean(MPA[synthia_set_16_to_13])
            return MPA_16, MPA_13
        if out_16_13:
            MPA_16 = np.nanmean(MPA[synthia_set_16])
            MPA_13 = np.nanmean(MPA[synthia_set_13])
            return MPA_16, MPA_13
        MPA = np.nanmean(MPA[:self.ignore_index])

        return MPA