sunny

convert weights to mnn model

3

感谢分享,想了解下weights是如何转换到mnn model，有参考的链接分享下嚒，是weights->onnx->mnn流程嚒?

question about the ImageDemo

5

hello： when i test the ImageDemo.py, i find that a picture of 600*640 pixes need 17s on cpu, and 10s on gpu; However, this is not the case in the...

some questions about DAN_Model

1

hi : 1. i train the first stage only and then the second stage only；but when i trained the first stage, the validation set was chosen at random from train...

issues about trainDNA.py

86

您好，我在进行trainDAN训练时，STAGE=2，执行sess.sun()；获取数据训练时，运行到models.py中的S2_InputImage = AffineTransformLayer(InputImage, S2_AffineParam)会报错； ## 错误如下： Caused by op 'Stage2/MatrixInverse', defined at: File "D:/softmares/Pycharm_workplace/Deep-Alignment-Network-tensorflow-master/DAN-TF/python_test1.py", line 73, in dan = DAN(initLandmarks) File "D:\softmares\Pycharm_workplace\Deep-Alignment-Network-tensorflow-master\DAN-TF\python_test2.py", line 102, in DAN S2_InputImage = AffineTransformLayer(InputImage, S2_AffineParam)...

hello: thanks for your sharing code, it's good. i find the code just implements CNN-6, CNN-7 in the paper, are you not implementing it? Looking forward to your replay. Thanks，best...

hello， when i predict one image，should provide a face detector？ can you provide the prediction time of one image. such as xx.fps？ Thanks，best wishes～

lower mAP

1

hello，I modified the config xxx.py file into a yaml file and used the hrnet or higherhrnet framework code for training. I found that the mAP on the coco validation dataset...

hello，thanks for your sharing working, how to use NAS to customize the backbone network？can you share the code about it? thanks.

the 3d loss

4

hello： Thanks for your sharing about the work. In the code(such as h36m.py and train3d.py), i don't understand the 'reg_ind' and 'reg_target', can you explain the parameters and why use...

分割交流

24

你好，目前好像遇到相似的问题，在unet-resnet等模型上效果都是不好，val_acc上身一点就不再变化，方便交流下有尝试其他网络效果不错的，除了fcn8