KLH1472

Why flip dx1, dy1, dx2, dy2 in generateBoundingBox when y.shape[0]==1? Please help me~

1

``` def __generate_bounding_box(imap, reg, scale, t): # use heatmap to generate bounding boxes stride = 2 cellsize = 12 imap = np.transpose(imap) dx1 = np.transpose(reg[:, :, 0]) dy1 = np.transpose(reg[:,...

Help! why there is a "np.square()" in the test.py?

1

The following codes are from interpret_output() in test.py. boxes[:, :, :, 0] += offset boxes[:, :, :, 1] += np.transpose(offset, (1, 0, 2)) boxes[:, :, :, :2] = 1.0 *...

I want to match across all the cells, but I cannot...

2

I like the jupyter_highlight_selected_word so much! Thank you! @jcb91 There is a problem: I want to show all matches across all the cells, but only visible matches are shown. When...

当PNet检测到一个超过阈值的anchor时，为什么要做转置？

2

如题~