zhly0

time

2

@luoyetx thanks for your nice work!the code is really simplified for caffe inference. and there is a question: when I use the time count: clock_t start = clock(); clock_t end...

Hi，GeorgeSeif： Thanks for your transfer learning code，if I want to setting different learning rate in different layer?Is keras possible to do this ? Thanks!

Hi,first of all,thanks for your nice work,this is not a issue,rather a question for a new learner. the opus's pitch_search module,is it relate to the sample rate?If I just want...

关于tensorflow 1.x中双线性插值，中align_mode，及half_pixel_center同时为false的情况，转换是正确的吗

2

关于tensorflow 1.x中双线性插值，中align_mode，及half_pixel_center同时为false的情况，能够转换，并且转换是正确的吗，同理，在paddle通过设定upsample的参数，能够实现tensorflow 1.x中align_mode，以及half_pixel_center同时为false的情形吗

This is not a issue,but a question,sorry to put it here. I want to do human body segmentation on Android phones using the frontal camera,the picture from camera,its width/height is...

TCN不定长

1

你好,非常感谢提供教程,我是小白,TCN中有个部分不是特别明白 TCN输入不定长的问题,比如输入是10x20 x40,相当于10是batch size,20是序列长度,40是每个元素的长度,如果使用TCN,对于序列长度不一致,是直接按最大序列长度补0吗?

tensorflow version

2

Thanks for your nice work！ And I would like to know the corresponding tensorflow version you have add to the tiny dnn。And was the tiny dnn support all the operation...

准确率

7

你好， 看了你的对比，确实感觉速度比较快，但是你对比的两个模型，都没有给出在相应测试集上的准确率和召回率，这个有进行过对比吗？谢谢

Thanks for your code,which helps to test on megaface. This is not a issue,just a question:the run_experiment.py code on megaface official page,it is use euclidean distance,but what should I do...

pb file

4

Hi,Engineering-Course: I freeze your model to a pb file for inference,but the first node is a fifo,not a input type,Can the code change to make the first layer is a...