-
I've been doing some experiments with your batch hard triplet loss function and different architectures/datasets. On MARS I manage to reproduce the results from your paper (network seems to converge),…
-
I had downloaded lfw dataset from the web i trained with the below commands
The following the commands i used marjorly
step 1)
python train_softmax.py --models_base_dir /home//Desktop/facenet…
-
Dear author:
I have some questions about the set to set verification experiment.
I'm doing the set to set verification experiment, as the following picture shows. I'm doing the ex…
-
Hi !
The README lacks some documentation to know how to add (re-train) with some new faces ; can you please add something ?
I think there's 2 points here :
- how to upgrade training with new fa…
-
When run the casia.py, the error:
File "casia.py", line 35, in
auth_img = io.imread(glob(os.path.join(auth_Dir, auth_name))[0])
IndexError: list index out of range
znshi updated
4 years ago
-
i want get the Available dataset~ please~
-
Hello Sir,
Thank you for the models and codes you have provided. We are planning to train a face verification model on the CASIA-WebFace dataset from scratch using the "mnist_siamese_train_test.proto…
-
您好，我在看您的代码的train.py中有以下这段
` dir_img = './data/data_{}/train/tam/'.format(dataset)
dir_mask = './data/data_{}/train/mask/'.format(dataset)
dir_logs = './result/logs/{}/{}/'.format(dataset, m…
-
Thank you for providing some code, could you upload the training code?
-
Hi, I found that for the same checkpoints of IML-ViT, the inference results on CASIA v1 inferenced through this IMDB-IML-ViT framework is much lower (~12%) that computed within of the original code ba…