deepid-implementation

deepid-implementation copied to clipboard

Hello, I see your test experiment, but I find your test accuracy on LFW is low comparing the paper test. Why?

getengqing

[INFO] A better CNN pre-trained model

3

author: AlfredXiangWu reference: https://github.com/AlfredXiangWu/face_verification_experiment related: #5 - caffe framework - CASIA-WebFace dataset: contains 493456 face images of 10575 identities. - feature extraction code: https://github.com/AlfredXiangWu/python_misc/blob/master/caffe/caffe_ftr.py - accuracy: (The single convolution net...

joyhuang9473

reference: [delphifirst/FaceX](https://github.com/delphifirst/FaceX) > A high performance (real-time) open source face landmarks detector (face alignment), based on explicit shape regression algorithm. forked by [joyhuang-machine-learning/FaceX](https://github.com/joyhuang-machine-learning/FaceX)

joyhuang9473

In train_val.prototxt: ``` layer { name: "accuracy_top_5" type: "Accuracy" bottom: "fc8" bottom: "label" top: "accuracy_top_5" accuracy_param { top_k: 5 } include { phase: TEST } } ```

joyhuang9473

類似 ReLU 功用 It is from the author of mxnet, Bing Xu, Naiyan Wang et al. http://arxiv.org/abs/1505.00853

joyhuang9473

reference: https://zh.wikipedia.org/wiki/%E7%BB%B4%E5%A5%A5%E6%8B%89-%E7%90%BC%E6%96%AF%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E6%A1%86%E6%9E%B6 Viola–Jones object detection framework => 這個方法在OpenCV中被實現為cvHaarDetectObjects()。

joyhuang9473

reference: happynear/FaceVerification 剪去 mean 的 data 不是用 scale 1/255 ? Ans: happynear: > But i don't understand why you set 0.0078125 scale in CASIA_train_test.prototxt. Why is not 0.00390625.Should it normalized...

joyhuang9473

reference: happynear/FaceVerification > how much is the best threshold for face authentication. Three probably answers: 1. You can use a linear svm to calculate the threshold. 2. The threshold is...

joyhuang9473

[INFO] The process of Xiang Wu's model

1

reference: happynear/FaceVerification > OK, I can tell you something you should be attention to in order to use Xiang Wu's model. > 1. Wu's alignment method is different from mine....

joyhuang9473

reference: https://github.com/happynear/FaceVerification/issues/14 > happynear: > > Recently I am working on face alignment. As a friend of mine said, he successfully trained a DeepID2 model, by setting the loss_weight of...

joyhuang9473