facenet

facenet copied to clipboard

Why use " labels.append(np.ones(dists.size(0)))" in training? and

3

dists = l2_dist.forward(embed_anchor, embed_pos) distances.append(dists.data.cpu().numpy()) labels.append(np.ones(dists.size(0))) dists = l2_dist.forward(embed_anchor, embed_neg) distances.append(dists.data.cpu().numpy()) labels.append(np.zeros(dists.size(0))) can you exlpain the code ? what's for?

liuzhongling

55renchen

please i need to understand the meaning of evaluation metrics calculate_roc calculate accuracy

ofathy1981

Is there pretrained weights available?

2

Michael-Jing

why accuracy of the model is less than 99%?

1

I wonder why the accuracy of the trained model does not reach 99% described in the paper. Is it because you chose offline instead of online when choosing hard triplet?

ghost

# DATA PARALLEL When I trained the ***FaceNet model*** using your repository, the default batch size of 128 was too much memory for just one GPU. Instead, I added the...

eplatero97

Pretrained Model on vggface2

1

Hello, I am looking to train this model on my own dataset for which I require a pretrained model on VGGFace2. Can you please make available the pretrained model on...

HarshPathakhp