weiaicunzai

for x, y in zip(*[iter(line1)] * 2):

#line1(x0,y0,x1,y1)
#line1 -> (x0, y0), (x1, y1)

#. zip(*[iter(line1)] * 2)
#->zip(<tuple_iterator object at 0x10dafdb00>, <tuple_iterator object at 0x10dafdb00>)

weiaicunzai

def bb_intersection_over_union(boxA, boxB):
	# determine the (x, y)-coordinates of the intersection rectangle
	xA = max(boxA[0], boxB[0])
	yA = max(boxA[1], boxB[1])
	xB = min(boxA[2], boxB[2])
	yB = min(boxA[3], boxB[3])
 
	# compute the area of intersection rectangle
	interArea = max(0, xB - xA + 1) * max(0, yB - yA + 1)
 

weiaicunzai

import cProfile
cProfile.runctx("yolo_data[13]", globals(), None)

weiaicunzai

    import cProfile, pstats
    from pstats import SortKey

    sortby = SortKey.CUMULATIVE
    with cProfile.Profile() as pr:


        # your code here

        ps = pstats.Stats(pr).sort_stats(sortby)

weiaicunzai

 def _make_blocks(self, block_nums, layer_num, stride=2, block=RiRBlock):
        
        layers = nn.Sequential()
        in_channel = self.base
        for block in range(block_nums):
            layers.add_module("RiR_Block{}".format(block), RiRBlock(in_channel, self.base, layer_num, stride))
            in_channel = self.base
            self.base *= 2
        
        return layers

weiaicunzai

def compute_mean_std(cifar100_dataset):
    """compute the mean and std of cifar100 dataset

    Args:
        cifar100_training_dataset or cifar100_test_dataset
        witch derived from class torch.utils.data
    
    Returns:
        a tuple contains mean, std value of entire dataset
    """

weiaicunzai

from __future__ import print_function, absolute_import

__all__ = ['accuracy']

def accuracy(output, target, topk=(1,)):
    """Computes the precision@k for the specified values of k"""
    maxk = max(topk)
    batch_size = target.size(0)

    _, pred = output.topk(maxk, 1, True, True)