You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
hello i utilize your useful program for face recognition,my implemented network is inception resnet v2 and
batch_size=16,
2.lr=0.001
3.embeding_size=128
4.train_size=708
5.eval_size=396
6.margin=0.5
7."triplet_strategy": "batch_all"
loss = 0.5458313, step = 1
loss = 0.0, step = 101 (3229.453 sec)
without pretrained weights and only with your implementation two layers CNN ,loss for evaluation goes to about 0.35(batch_size=64,lr=1e-4)with data augmentation .i use embeddings vector from PREDICTION mode as input of my SVM and KNN classifier but accuracies of both are too low about 10%. what do think about this low accuracy for recognition?which part do you think have caused this low accuracy (triplet part or classification part)?
The text was updated successfully, but these errors were encountered:
If the batch size is too low (16) and you have a lot of different classes (ex: 100), you may have no valid triplet in your batch, which might give you a loss of zero.
Or maybe the model is not converging because the learning rate is too high.
hello i utilize your useful program for face recognition,my implemented network is inception resnet v2 and
batch_size=16,
2.lr=0.001
3.embeding_size=128
4.train_size=708
5.eval_size=396
6.margin=0.5
7."triplet_strategy": "batch_all"
loss = 0.5458313, step = 1
loss = 0.0, step = 101 (3229.453 sec)
without pretrained weights and only with your implementation two layers CNN ,loss for evaluation goes to about 0.35(batch_size=64,lr=1e-4)with data augmentation .i use embeddings vector from PREDICTION mode as input of my SVM and KNN classifier but accuracies of both are too low about 10%. what do think about this low accuracy for recognition?which part do you think have caused this low accuracy (triplet part or classification part)?
The text was updated successfully, but these errors were encountered: