liuhengli
liuhengli
Excuse me, about gradient I have some not understand, why the gradient shapes same as activation output shape. And the gradient is not weight gradient? it shape is [i ,...
this function require pred_labels must have rank 2, but your program the pred_labels shape is (?, 7308, 81)
I want to know why this formula is used “target_w = (1 - hp.scale_lr) * target_w + hp.scale_lr * scaled_target_w[new_scale_id] ”
In "mobilenetdet.py" this file, the "set_anchors(img_shape, fea_shape)" function have bug.
I want to know Where can I download it
could you give a test example? And I can't find you trained model
我想请问一下這個更新尺度的公式有什麼依据“target_w = (1 - hp.scale_lr) * target_w + hp.scale_lr * scaled_target_w[new_scale_id] ”
错误 95 error MSB3721: 命令“"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v7.5\bin\nvcc.exe" -gencode=arch=compute_20,code=\"sm_20,compute_20\" --use-local-env --cl-version 2013 -ccbin "E:\Program Files (x86)\Microsoft Visual Studio 12.0\VC\bin\x86_amd64" -I......\3rdparty\include -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v7.5\include" -I"C:\Program Files\NVIDIA GPU Computing...
I want to know how to test in camera or video