First, congratulations and thank you for your work, it's very exciting to see that's possible to make a light CNN without millions (or billions) of parameters and achieve state-of-art accuracy.

I intend to do two experiments (varying type of activations, cost functions, solver types, neurons, ...) using the model C architecture, one training a new CNN on my database and another with fine-tuning of model C on my database. I made the following solver.prototxt and train_value.prototxt:

• solver:

net: "LightenedCNN_New_train_val.prototxt"
test_iter: 1000
test_interval: 10000
iter_size: 60
base_lr: 0.001
lr_policy: "step"
gamma: 0.1
stepsize: 500000
display: 100
max_iter: 5000000
momentum: 0.9
weight_decay: 0.0005
snapshot: 10000
snapshot_prefix: "LightenedCNN_New_Net"
solver_mode: GPU

• train_val

layer {
  name: "data"
  type:"Data"
  top: "data"
  top: "label"
  data_param{
	  source: "my_csv_train_database.txt"
	  batch_size: 32
	}
  transform_param {
    scale: 0.00390625
    crop_size: 128
    mirror: true
  }
  include: { phase: TRAIN }
}

layer {
  name: "data"
  type: "Data"
  top: "data"
  top: "label"
  data_param{
	  source: "my_csv_validation_database.txt"
	  batch_size: 10
	}
  transform_param {
    scale: 0.00390625
    crop_size: 128
    mirror: false
  }
  include: { phase: TEST }
}
...
the same layers on deploy

Could you tell me if this solver and train_val are similar to those you used on the final training of model C? And for fine-tuning can I use the same solver used in train and just freeze the layers on the train_val or it's necessary another solver for fine-tuning?

Thanks

Hi,

I would like to know if you have a Matlab program to extract the features. I have written one but did not get the results properly. For a single image (i.e., batch size = 1), my program is as follows:

modelName = 'LightenedCNN_A_deploy.prototxt'; modelWeight = 'LightenedCNN_A.caffemodel'; caffe.set_device(1); caffe.set_mode_gpu();

% Define net net = caffe.Net(modelName, modelWeight, 'test');

% read image I = rgb2gray(imread('imgName.jpg'));

% get features J(:,:,1,1) = I; net.forward({J}); fts = net.blobs('eltwise6').get_data()';

I get features of 256 dimension. However, with these features I obtained very low accuracy. I have pre-processed the images with the normalization program written by you.

• Here I did not scale the value to 1 (by dividing pixel values with 256) as it gives even worse result on LFW.
• Besides, I would like to inform you that I was unable to load the caffemodel for your CNN-B.

Looking forward for your feedback.

Thank you.

I am trying to train with lightened_B model in CASIA. I followed the training methodology in paper, But it does not converge. At beginning, accuracy is 0, and loss is 87.3365. What's the problem? I am using caffe-windows-master of happynear(Feng Wang). Thanks.

Hi, I want to reproduce your results mentioned in your paper arXiv:1511.02683 "A Lightened CNN for Deep Face Representation". Although you claim that the fc1 layer dimension is 256 in your paper, it is actually 512 in your prototxt file. I used Dlib to detect and extract faces of LFW-closedset. Dlib in addition, rotates faces to align wrt the centers of eye locations horizontally. Then I resized the faces to 128x128 pixels. Then I used your LightenedCNN_A caffemodel release to extract features from fc1 layer, which has 512 dimensionality, using matcaffe latest release. One thing to note is, you did not release the mean binaryproto file of your training set. Don't you apply mean normalization before testing? I compared the probe features with gallery features using cosine similarity. I obtained very low Rank-1 accuracy (less than %10). What would be the reason of the difference with your results?

Hello, Mr Wu: I have study how to evaluate a model on MegaFace recently. But I confuse how to convert a vector into bin form. The default material said matio.py is a good tool. But I don't understand it without the comment. Could you tell me something about it ? Thank you so much.

吴老师，您好： 先感谢您分享的网络模型！ 当测试模型时遇到两个问题：

1. 按照网络A_deploy，提取fc1层的特征应该是512维（按这个正确率是93.8%），但看保存特征的mat里，特征维数是256维，想问一下，您提取的是那一层特征？ 2.在测试网络B_deploy时，出现 ： ...insert_splits.cpp:35] Unknown blob input label to layer 1 的错误，想问一下这个怎么解决？

十分感谢！

Pretrained model: LightenedCNN_B.caffemodel Net proto: LightenedCNN_B_ex.prototxt but change the input to (so that I can read the image_path in commend line): layers { name: "icub-camera" type: MEMORY_DATA top: "data" top: "label" memory_data_param { batch_size: 1 channels: 1 height: 144 width: 144 }
}

Report Cannot copy param 0 weights from layer 'fc1'; shape mismatch. Source param shape is 1 1 512 8192 (4194304); target param shape is 512 10368 (5308416).

What is wrong?

老师您好 首先我想请问下 文章中进行测试时是对于LFW的原始数据集进行的特征点定位还是说根据deep funneled的图片进行的特征点定位呢 其次 readme里面写的利用caffe_ftr.py进行特征提取 但是我们在运行文件的时候提示说 'Classifier' object has no attribute 'set_phase_test'

Hi!

Thank you for sharing your approaches.

When I use your python code for feature extraction, I get the error "ValueError: could not broadcast input array from shape (64,3,28,28) into shape (64,1,28,28)". I am a little confused about what should I change.

I'm using as inputs:

• your pretrained model (DeepFace_set003_net_iter.caffemodel)
• your network definition (DeepFace_set003.prototxt)
• an image list of some LFW grayscale images' path and labels

Thank you!!

Hi, why the features stored in the matlab matrix is 256 dimensions? but fc1-layer in the network's output number is 512. I cannot understand which layer's output treat as the terminal feature!

Hello, I want to train on the pre-trained Lightened CNN model. I would like know how should the labeling be done. Is it binary labeling stating 0 for similar images and 1 for non-similar? Or do we have to get a similarity between each image pair of the same subject? Thank you in advance.