def cal_for_eval(self, gathered_outputs, gathered_batchdata):
"""
:param gathered_outputs: list of tensor, [B,C,H,W]
:param gathered_batchdata: list of numpy, [B,C,H,W]
:return: eval result
"""
crop_border = self.eval_cfg.crop_border
gathered_outputs = gathered_outputs[0] # image
gathered_batchdata = gathered_batchdata[-1] # label
assert list(gathered_batchdata.shape) == list(
gathered_outputs.shape), "{} != {}".format(
list(gathered_batchdata.shape), list(gathered_outputs.shape))
res = []
sample_nums = gathered_outputs.shape[0]
for i in range(sample_nums):
output = tensor2img(gathered_outputs[i], min_max=(-0.5, 0.5))
output_y = bgr2ycbcr(output, y_only=True)
gt = tensor2img(gathered_batchdata[i], min_max=(-0.5, 0.5))
gt_y = bgr2ycbcr(gt, y_only=True)
eval_result = dict()
for metric in self.eval_cfg.metrics:
eval_result[metric + "_RGB"] = self.allowed_metrics[metric](
output, gt, crop_border)
eval_result[metric + "_Y"] = self.allowed_metrics[metric](
output_y, gt_y, crop_border)
res.append(eval_result)
return res
def niqe(img, crop_border, input_order='HWC', convert_to='y'):
"""Calculate NIQE (Natural Image Quality Evaluator) metric.
Ref: Making a "Completely Blind" Image Quality Analyzer.
This implementation could produce almost the same results as the official
MATLAB codes: http://live.ece.utexas.edu/research/quality/niqe_release.zip
We use the official params estimated from the pristine dataset.
We use the recommended block size (96, 96) without overlaps.
Args:
img (ndarray): Input image whose quality needs to be computed.
The input image must be in range [0, 255] with float/int type.
The input_order of image can be 'HW' or 'HWC' or 'CHW'. (BGR order)
If the input order is 'HWC' or 'CHW', it will be converted to gray
or Y (of YCbCr) image according to the ``convert_to`` argument.
crop_border (int): Cropped pixels in each edge of an image. These
pixels are not involved in the metric calculation.
input_order (str): Whether the input order is 'HW', 'HWC' or 'CHW'.
Default: 'HWC'.
convert_to (str): Whether coverted to 'y' (of MATLAB YCbCr) or 'gray'.
Default: 'y'.
Returns:
float: NIQE result.
"""
# we use the official params estimated from the pristine dataset.
niqe_pris_params = np.load('mmedit/core/evaluation/niqe_pris_params.npz')
mu_pris_param = niqe_pris_params['mu_pris_param']
cov_pris_param = niqe_pris_params['cov_pris_param']
gaussian_window = niqe_pris_params['gaussian_window']
img = img.astype(np.float32)
if input_order != 'HW':
img = reorder_image(img, input_order=input_order)
if convert_to == 'y':
img = bgr2ycbcr(img / 255., y_only=True) * 255.
elif convert_to == 'gray':
img = bgr2gray(img / 255., cv2.COLOR_BGR2GRAY) * 255.
img = np.squeeze(img)
if crop_border != 0:
img = img[crop_border:-crop_border, crop_border:-crop_border]
niqe_result = niqe_core(img, mu_pris_param, cov_pris_param,
gaussian_window)
return niqe_result