|
- Run on time: 2022-05-11 20:21:48.038345
-
- Model name: hybrid_snn_conversion
- Model size: 1703.7 MB
- Model description: A convert-then-finetune snn model proposed in Rathi et al. ICLR 2020 (Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation)
-
- Make ImageNet TEST DataLoader finished! Time: 2022-05-11 20:21:49.539565
-
- Load model successfully!
-
- DataParallel(
- (module): VGG_SNN_STDB(
- (input_layer): PoissonGenerator()
- (features): Sequential(
- (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
- (1): ReLU(inplace=True)
- (2): Dropout(p=0.3, inplace=False)
- (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
- (4): ReLU(inplace=True)
- (5): AvgPool2d(kernel_size=2, stride=2, padding=0)
- (6): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
- (7): ReLU(inplace=True)
- (8): Dropout(p=0.3, inplace=False)
- (9): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
- (10): ReLU(inplace=True)
- (11): AvgPool2d(kernel_size=2, stride=2, padding=0)
- (12): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
- (13): ReLU(inplace=True)
- (14): Dropout(p=0.3, inplace=False)
- (15): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
- (16): ReLU(inplace=True)
- (17): Dropout(p=0.3, inplace=False)
- (18): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
- (19): ReLU(inplace=True)
- (20): AvgPool2d(kernel_size=2, stride=2, padding=0)
- (21): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
- (22): ReLU(inplace=True)
- (23): Dropout(p=0.3, inplace=False)
- (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
- (25): ReLU(inplace=True)
- (26): Dropout(p=0.3, inplace=False)
- (27): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
- (28): ReLU(inplace=True)
- (29): AvgPool2d(kernel_size=2, stride=2, padding=0)
- (30): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
- (31): ReLU(inplace=True)
- (32): Dropout(p=0.3, inplace=False)
- (33): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
- (34): ReLU(inplace=True)
- (35): Dropout(p=0.3, inplace=False)
- (36): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
- (37): ReLU(inplace=True)
- (38): Dropout(p=0.3, inplace=False)
- )
- (classifier): Sequential(
- (0): Linear(in_features=100352, out_features=4096, bias=False)
- (1): ReLU(inplace=True)
- (2): Dropout(p=0.5, inplace=False)
- (3): Linear(in_features=4096, out_features=4096, bias=False)
- (4): ReLU(inplace=True)
- (5): Dropout(p=0.5, inplace=False)
- (6): Linear(in_features=4096, out_features=1000, bias=False)
- )
- )
- )
-
- Batch 1, Batch acc@1: 9.3750, Avg acc@1: 9.3750, Batch acc@5: 28.1250, Avg acc@5: 28.1250,Time: 0:01:25
- Batch 2, Batch acc@1: 3.1250, Avg acc@1: 6.2500, Batch acc@5: 28.1250, Avg acc@5: 28.1250,Time: 0:02:51
-
- Testing average acc@1: 6.2500, time cost: 0:02:51
- Testing average acc@5: 28.1250, time cost: 0:02:51
|