search

fangwei123456 / Spike-Element-Wise-ResNet

Deep Residual Learning in Spiking Neural Networks
Mozilla Public License 2.0
140 stars 21 forks source link

The testing_acc1 of dvsgesture is only 80. #11

Closed KoiLiu closed 1 year ago

KoiLiu commented 2 years ago

Hello, I trained the smodel in dvsgesture. But the testing_acc1 is around 80%, which is much lower than the accuracy in your paper. I used the Adam with lr=0.001 and the others are the default. python train.py --tb --amp --output-dir ./logs --model SEWResNet --connect_f ADD --device cuda:0 --lr-step-size 64 --epoch 192 --T_train 12 --T 16 --data-path ./dataset --lr 0.001 --adam The training loss and other results are as followed: AC75A908-D3FA-47AF-AA11-290D0EE2BC67 D0966B9A-A913-4F0B-8E96-4534BC86C87C 43026CF9-CC4D-4527-84E0-CFFF8062C0EC

fangwei123456 commented 2 years ago

Refer to this: https://github.com/fangwei123456/Spike-Element-Wise-ResNet/issues/7#issuecomment-1065849077

KoiLiu commented 2 years ago

Thank for your reply. I will try it again.

KoiLiu commented 2 years ago

I git the latest version of SJ and retrained the train.py in the gesture. Maybe I didn't express my problem clearly before. I trained the model on the DVS128Gesture dataset, not the Imagenet. And this time the acc of test is only 81.94%, which is still much lower than 97.92 acc in your work. I don't know the reson for it. More details are as followed: Namespace(T=16, T_train=12, adam=True, amp=True, batch_size=16, connect_f='ADD', data_path='./dataset', device='cuda:0', dist_url='env://', distributed=False, epochs=192, lr=0.001, lr_gamma=0.1, lr_step_size=64, model='SEWResNet', momentum=0.9, output_dir='./logs', print_freq=64, resume='', start_epoch=0, sync_bn=False, tb=True, test_only=False, weight_decay=0, workers=4, world_size=1)... Training time 0:50:47 max_test_acc1 81.94444444444444 test_acc5_at_max_test_acc1 100.0 I trained the DVS128Gesture dataset in the afternoon with the simple PythonNet and the acc was around 94%, but I don't know the reason the lower acc of SEWResNet. So I really want your help and advice. Thank you a lot!

fangwei123456 commented 2 years ago

adam=False