Mino_Qin

hi Chen, Did u evaluate the usual problem in demosaic? such as false color and zipper effect. Thanks!

Dear michalfaber @michalfaber and All, training/generate_hdf5.py line-182: isValidationArray = [data[i]['isValidation'] for i in range(numSample)] val_total_write_count = isValidationArray.count(0.0) tr_total_write_count = len(data) - val_total_write_count isValidationArray==1 count the validation set during training val_total_write_count...

multi GPU support?

9

Dear All, I have problem when using multi-GPU to train the model. How to set multi-gpu to boost the training procedure. I tried following methods: 1. set GPUdeviceNumber=2 or GPUdeviceNumber=0,1...

how to evaluate the human segmentation?

2

HI, How to evaluate the human segmentation part as paper described? just using last channel of (K+1) keypoints heatmap? How to extract the segmentation from PRN network. Any post-processing op...

hi anjieZheng How ot re-implement your job by your repo? Thanks! BR

How to generate mocap.npz?

15

Hi, How to generage mocap.npz, which seems not easy to me. Can u give a clue how to generate mocap.npz from public mocap dataset? The train_mvae.py script assumes the mocap...

error @mlsl?

5

The error happens when using caffe@intel How to solve it . Thanks! PS: I used this repo for caffe evaluation. https://github.com/Jack-CV/PCN-FaceDetection-FaceAlignment [Thread debugging using libthread_db enabled] Using host libthread_db library...