search

ridvansalihkuzu / vein-biometrics

A State-of-the-art Solution for Finger-Vein, Palm-Vein, Dorsal-Vein Recognition by Using Deep Learning
46 stars 12 forks source link

Can you share the training parameters? I am using a dataset and cannot obtain good results #12

Open yangh-zzf-itcast opened 1 year ago

yangh-zzf-itcast commented 1 year ago

this is my parameters Namespace(batch_size=32, database_dir='/ssd_data/yanghang/palm_vein/POLYU/NIR_polyu_crop/', embedding_size=512, evaluate=False, learning_rate=0.01, logdir='./data_polyup/CSVFiles/cnn_logs.csv', margin=0.5, num_classes=450, num_epochs=300, num_workers=8, outdir='modeldir/00/05/', scale_rate=32.0, start_epoch=0, test_dir='/ssd_data/yanghang/palm_vein/POLYU/data_polyup_CSVFiles/output_list_test_pair.csv', train_dir='/ssd_data/yanghang/palm_vein/POLYU/data_polyup_CSVFiles/output_list_train.csv', type='aamp', valid_dir='/ssd_data/yanghang/palm_vein/POLYU/data_polyup_CSVFiles/output_list_val.csv', weight_decay=0.0001) I use polyu palm vein dataset，and use MNASNet_Modified model，The validation set loss keeps rising, obviously overfitting image

151210148 commented 7 months ago

hi , POLYU data can share? thanks

jieblue commented 4 months ago

Can u share POLYU palm vein datasets？ Thanks.

deeperlearner commented 2 months ago

@yangh-zzf-itcast I have the same problem. Validation prec stays at zero, but the test pair results seem good. I don't think the training process is responsible for the good test results. This is due to the pre-trained weights of ImageNet's MNASNet_Modified model. Do you have any findings? Thanks. image

deeperlearner commented 3 weeks ago

Reduce the batch size can improve the validation performance. python3 -m benchmark_verification.main_train_CNN --num_epochs 100 --batch-size 8 --type none image