SUPER-MARIO

Actually, I wonder why we need such a function i.e. calcSimilarityTransform(), I don't know why we should get a relative delta_shapes for predicting target. Sorry for my silly question. I...

I also want to know how to test...

那么在程序中getsimilarTransform函数具体有啥作用呢，是否可以直接回归delta S 而不用先Transform再Transform回来呢？ 也就是说 getSimilarityTransform(params_.mean_shape_, ProjectShape(augmented_current_shapes[i], augmented_bboxes[i]), rotation, scale); cv::transpose(rotation, rotation); regression_targets[i] = scale \* regression_targets[i] \* rotation; getSimilarityTransform(ProjectShape(augmented_current_shapes[i], augmented_bboxes[i]), params_.mean_shape_, rotation, scale); rotations_[i] = rotation; scales_[i] = scale; 这几句话怎么理解？

@wywu Dear author, I think the 68-pt definition and 98-pt definition have many pts in common, so I don't think a model trained on the extracted 68-pt data would perform...

@mrgloom Some images contain more than one faces.

Those outputs only make sense when RPN is trained separately, but here the whole network is trained end to end..

@gaopeng-eugene Hi, I also encounter the same problem with you, but after I change the code as you provided, the testing process becomes very very slow....Extremely slow...And I still don't...

@realwecan I'm using CUDA-7.5 and cudnn 5.0, but I cannot use cudnn for convolution.... I don't know which version of cudnn should I use....

@instant-high Hi, can I get your script? I'm really interested in fullframe face/head/partswap.

Hi, I wonder which part of the code point out the train and test dataset, I just cannot find 'minival' anywhere in the code...Forgive me for I'm new to mxnet...