超人 issues

Results 9 issues of


                                             超人

关于onnx2caffe这个工具

我想在onnx2caffe这个工具中添加对slice op的支持，请问要添加那些内容？

CMakeLists.txt问题

add_executable(main src/main.cpp src/UltraFace.cpp) target_link_libraries(main ncnn ${OpenCV_LIBS}) 请问target_link_libraries(main ncnn ${OpenCV_LIBS}) 中main 后面的ncnn是怎么确定的?

what's the problem when i test on MOT16 dataset?

2020-04-26 10:19:16 [INFO]: Evaluate seq: MOT16-05 IDF1 IDP IDR Rcll Prcn GT MT PT ML FP FN IDs FM MOTA MOTP IDt IDa IDm MOT16-05 0.0% 0.0% nan% nan% 0.0%...

I want to know how your code differs from the original version of the pytorch code.

As far as I know you replaced resnet with vgg. in addition, your Overall Loss： Loss = 0.8*loss_reconstruction + 0.005*loss_perceptual + 0.4*loss_warping + loss_smooth the original version of the pytorch...

Note out（注释掉） the line 57(predict_score = mxnet.symbol.slice_axis(predict_score, axis=1, begin=0, end=1)

把mxnet模型转onnx模型前需要Note out（注释掉） the line 57(predict_score = mxnet.symbol.slice_axis(predict_score, axis=1, begin=0, end=1)，现在我想用python+tensorrt推理onnx模型，如何得到注释the line 57之前的结果呢？

我测试了你的代码，发现一个问题

我设置slomo_rate = 3，即我在每两帧之间插了三帧图片。我仔细观察了这三张图片，发现这三张图片几乎一模一样，变化非常小，而第四帧图像与之前的插值图像变化很大！这就意味着，三张插值图像复制了初始帧图像。

How much psnr and ssim do you get?

Hi, I want to know how much psnr and ssim you can get on Adobe-240 dataset after training?

超人