What is the difference between Pytorch (same parameter with Mxnet) and Pytorch (original image scale) about pytorch_retinaface HOT 6 OPEN

same parameter with Mxnet: scale image to certain scope when testing.
original image scale : scale = 1 when testing.
If you want to train model, you can follow readme.md(training part) .

from pytorch_retinaface.

Thanks, I get it.
The official code in Mxnet just resize the model's min_max size to [1024, 1920] to get a much better result on wider face hard set.
Have you ever tried adding anchor_size=8 and other tricks or using another backbone to improve the result on scale=1?
I will have a test if you haven't.

from pytorch_retinaface.

If you only pay attention to the face of certain scale, you can try control sampling scale or image size when training. You can also try other backbone.

from pytorch_retinaface.

@biubug6 any reason why you don't normaize input data to [0,1] range?
There arebatch normalization layers in the models, I heard that training works better with bn when input is normalized?

from pytorch_retinaface.

If you only pay attention to the face of certain scale, you can try control sampling scale or image size when training. You can also try other backbone.

I will test it by setting sampling scale at [4,8,16].

from pytorch_retinaface.

原始文献（Mxnet）中的test_widerface.py使用了如下所示的多尺度的测试方式，这里所说的相同参数，是也使用了多尺度测试吗？请问一下在这个项目中如果也要用多尺度测试的话，代码该如何修改，或者您当时进行多尺度测试时的代码可否分享一下。非常感谢
#TEST_SCALES = [500, 800, 1200, 1600]
TEST_SCALES = [500, 800, 1100, 1400, 1700]
target_size = 800
max_size = 1200
im_shape = im.shape
im_size_min = np.min(im_shape[0:2])
im_size_max = np.max(im_shape[0:2])
im_scale = float(target_size) / float(im_size_min)
# prevent bigger axis from being more than max_size:
if np.round(im_scale * im_size_max) > max_size:
im_scale = float(max_size) / float(im_size_max)
scales = [float(scale)/target_size*im_scale for scale in TEST_SCALES]

from pytorch_retinaface.