-
Hello, I have a quetion didn't understand, is the final layer for face verification and identification is same,?which means the embedding size for contrastive is class nums of identity.
-
I want to use VGG-16 model to train CIFAR-10 dataset.
Since the VGG-16 model's input size is 224x224, I use `im2rec` to resize CIFAR-10 `png` pictures(32x32) to 224x224 as dataiter:
```
batch_size …
-
issue: crashes when loading pb file in C++ program:
> Session * session;
> GraphDef graph_def;
> SessionOptions opts;
> TF_CHECK_OK(ReadBinaryProto(Env::Default(), heartPrintPbPa…
-
@AlfredXiangWu 请问有没有测试过Joint Bayesian的提升作用？ 我尝试使用Joint Bayesian对CNN特征进一步训练，效果不仅没有提升，还有略微下降，感觉不太正常。 (使用LBP+JB效果还是很明显的，所以很困惑，deepID里面JB的作用还是很明显的)
-
I am tasked with transfering deepid using caffe to that using mxnet. All parameters come from a caffe prototxt. But how I train the network,the maximum Train-accuracy is only up to like 0.40,while ca…
-
您好，不介意我用中文吧。
看了您 关于 数据预处理的代码deepid/src/generate_training_samples.cpp ，对我帮助很大。
感谢！
但是我还有个疑问关于generate_training_samples.cpp：
`//三种尺度，patch的高，patch的宽，两眼距离占宽的比例
static const boost::tuple scales[] = {…
-
i run simple c++ code to pass image to my preTrained caffemodel bur when i want create network say unknown Input layer !:
Check failed: registry.count(type) == 1 (0 vs. 1) Unknown layer type: Input…
-
I use the same train and validation set with the same preparing parameters,but the Train-accuracy and Validation-accuracy has a so big separation. According to my thought, they should be the same. Doe…
-
I git clone this repo, but finding it seems lacking data? or something else configures I don't know?
Thanks!
-
how about face recognition with mxnet? anyone implements it!