-6dB的效果也不错

最新推荐文章于 2022-10-16 12:20:39 发布
最新推荐文章于 2022-10-16 12:20:39 发布
阅读量201 收藏
点赞数
分类专栏： python 脉冲神经网络
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/huatianxue/article/details/117406594
版权 
G:\python\python.exe "F:/my_code/spikingjelly-master-20201221/spikingjelly/clock_driven/ann2snn/examples/if_cnn_mnist_work - 副本.py"
All the temp files are saved to  ./log-cnn_mnist1622381673.6093786
ann2snn config:
	 {'simulation': {'reset_to_zero': False, 'encoder': {'possion': False}, 'avg_pool': {'has_neuron': True}, 'max_pool': {'if_spatial_avg': False, 'if_wta': False, 'momentum': None}}, 'parser': {'robust_norm': True}}
Device is cuda
Epoch 0 [1/782] ANN Training Loss:1.606 Accuracy:0.188
Epoch 0 [101/782] ANN Training Loss:0.706 Accuracy:0.739
Epoch 0 [201/782] ANN Training Loss:0.545 Accuracy:0.799
Epoch 0 [301/782] ANN Training Loss:0.480 Accuracy:0.798
Epoch 0 [401/782] ANN Training Loss:0.445 Accuracy:0.798
Epoch 0 [501/782] ANN Training Loss:0.423 Accuracy:0.798
Epoch 0 [601/782] ANN Training Loss:0.405 Accuracy:0.810
Epoch 0 [701/782] ANN Training Loss:0.395 Accuracy:0.796
Epoch 0 [157/157] ANN Validating Loss:0.328 Accuracy:0.800
Save model to: ./log-cnn_mnist1622381673.6093786\cnn_mnist.pkl
Epoch 1 [1/782] ANN Training Loss:0.305 Accuracy:0.812
Epoch 1 [101/782] ANN Training Loss:0.328 Accuracy:0.800
Epoch 1 [201/782] ANN Training Loss:0.325 Accuracy:0.802
Epoch 1 [301/782] ANN Training Loss:0.327 Accuracy:0.798
Epoch 1 [401/782] ANN Training Loss:0.329 Accuracy:0.794
Epoch 1 [501/782] ANN Training Loss:0.327 Accuracy:0.803
Epoch 1 [601/782] ANN Training Loss:0.326 Accuracy:0.803
Epoch 1 [701/782] ANN Training Loss:0.325 Accuracy:0.803
Epoch 1 [157/157] ANN Validating Loss:0.324 Accuracy:0.800
Save model to: ./log-cnn_mnist1622381673.6093786\cnn_mnist.pkl
Epoch 2 [1/782] ANN Training Loss:0.355 Accuracy:0.781
Epoch 2 [101/782] ANN Training Loss:0.314 Accuracy:0.807
Epoch 2 [201/782] ANN Training Loss:0.320 Accuracy:0.800
Epoch 2 [301/782] ANN Training Loss:0.318 Accuracy:0.806
Epoch 2 [401/782] ANN Training Loss:0.321 Accuracy:0.797
Epoch 2 [501/782] ANN Training Loss:0.313 Accuracy:0.857
Epoch 2 [601/782] ANN Training Loss:0.263 Accuracy:1.000
Epoch 2 [701/782] ANN Training Loss:0.226 Accuracy:1.000
Epoch 2 [157/157] ANN Validating Loss:0.004 Accuracy:1.000
Save model to: ./log-cnn_mnist1622381673.6093786\cnn_mnist.pkl
Epoch 3 [1/782] ANN Training Loss:0.001 Accuracy:1.000
Epoch 3 [101/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 3 [201/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 3 [301/782] ANN Training Loss:0.003 Accuracy:1.000
Epoch 3 [401/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 3 [501/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 3 [601/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 3 [701/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 3 [157/157] ANN Validating Loss:0.005 Accuracy:1.000
Save model to: ./log-cnn_mnist1622381673.6093786\cnn_mnist.pkl
Epoch 4 [1/782] ANN Training Loss:0.001 Accuracy:1.000
Epoch 4 [101/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 4 [201/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 4 [301/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 4 [401/782] ANN Training Loss:0.003 Accuracy:1.000
Epoch 4 [501/782] ANN Training Loss:0.003 Accuracy:1.000
Epoch 4 [601/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 4 [701/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 4 [157/157] ANN Validating Loss:0.003 Accuracy:1.000
Save model to: ./log-cnn_mnist1622381673.6093786\cnn_mnist.pkl
Epoch 5 [1/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 5 [101/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 5 [201/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 5 [301/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 5 [401/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 5 [501/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 5 [601/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 5 [701/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 5 [157/157] ANN Validating Loss:0.011 Accuracy:0.998
Save model to: ./log-cnn_mnist1622381673.6093786\cnn_mnist.pkl
Epoch 6 [1/782] ANN Training Loss:0.004 Accuracy:1.000
Epoch 6 [101/782] ANN Training Loss:0.003 Accuracy:1.000
Epoch 6 [201/782] ANN Training Loss:0.003 Accuracy:1.000
Epoch 6 [301/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 6 [401/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 6 [501/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 6 [601/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 6 [701/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 6 [157/157] ANN Validating Loss:0.002 Accuracy:1.000
Save model to: ./log-cnn_mnist1622381673.6093786\cnn_mnist.pkl
Epoch 7 [1/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 7 [101/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 7 [201/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 7 [301/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 7 [401/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 7 [501/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 7 [601/782] ANN Training Loss:0.003 Accuracy:1.000
Epoch 7 [701/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 7 [157/157] ANN Validating Loss:0.002 Accuracy:1.000
Save model to: ./log-cnn_mnist1622381673.6093786\cnn_mnist.pkl
Epoch 8 [1/782] ANN Training Loss:0.001 Accuracy:1.000
Epoch 8 [101/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 8 [201/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 8 [301/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 8 [401/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 8 [501/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 8 [601/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 8 [701/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 8 [157/157] ANN Validating Loss:0.002 Accuracy:1.000
Save model to: ./log-cnn_mnist1622381673.6093786\cnn_mnist.pkl
Epoch 9 [1/782] ANN Training Loss:0.001 Accuracy:1.000
Epoch 9 [101/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 9 [201/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 9 [301/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 9 [401/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 9 [501/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 9 [601/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 9 [701/782] ANN Training Loss:0.002 Accuracy:1.000
Epoch 9 [157/157] ANN Validating Loss:0.018 Accuracy:0.998
Save model to: ./log-cnn_mnist1622381673.6093786\cnn_mnist.pkl
Using 100 pictures as norm set
torchvision.datasets.folder.ImageFolder
torch.Size([100, 1, 28, 28])
Load best model for Model:cnn_mnist...
ANN Validating Accuracy:0.998
Save model to: ./log-cnn_mnist1622381673.6093786\parsed_cnn_mnist.pkl
Using robust normalization...
normalize with bias...
Print Parsed ANN model Structure:
Pytorch_Parser(
  (network): Sequential(
    (0): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1))
    (1): ReLU()
    (2): AvgPool2d(kernel_size=2, stride=2, padding=0)
    (3): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1))
    (4): ReLU()
    (5): AvgPool2d(kernel_size=2, stride=2, padding=0)
    (6): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1))
    (7): ReLU()
    (8): AvgPool2d(kernel_size=2, stride=2, padding=0)
    (9): Flatten(start_dim=1, end_dim=-1)
    (10): Linear(in_features=32, out_features=5, bias=True)
    (11): ReLU()
  )
)
Save model to: ./log-cnn_mnist1622381673.6093786\normalized_cnn_mnist.pkl
Print Simulated SNN model Structure:
PyTorch_Converter(
  (network): Sequential(
    (0): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1))
    (1): IFNode(
      v_threshold=1.0, v_reset=None, detach_reset=False
      (surrogate_function): Sigmoid(alpha=1.0, spiking=True)
    )
    (2): AvgPool2d(kernel_size=2, stride=2, padding=0)
    (3): IFNode(
      v_threshold=1.0, v_reset=None, detach_reset=False
      (surrogate_function): Sigmoid(alpha=1.0, spiking=True)
    )
    (4): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1))
    (5): IFNode(
      v_threshold=1.0, v_reset=None, detach_reset=False
      (surrogate_function): Sigmoid(alpha=1.0, spiking=True)
    )
    (6): AvgPool2d(kernel_size=2, stride=2, padding=0)
    (7): IFNode(
      v_threshold=1.0, v_reset=None, detach_reset=False
      (surrogate_function): Sigmoid(alpha=1.0, spiking=True)
    )
    (8): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1))
    (9): IFNode(
      v_threshold=1.0, v_reset=None, detach_reset=False
      (surrogate_function): Sigmoid(alpha=1.0, spiking=True)
    )
    (10): AvgPool2d(kernel_size=2, stride=2, padding=0)
    (11): IFNode(
      v_threshold=1.0, v_reset=None, detach_reset=False
      (surrogate_function): Sigmoid(alpha=1.0, spiking=True)
    )
    (12): Flatten(start_dim=1, end_dim=-1)
    (13): Linear(in_features=32, out_features=5, bias=True)
    (14): IFNode(
      v_threshold=1.0, v_reset=None, detach_reset=False
      (surrogate_function): Sigmoid(alpha=1.0, spiking=True)
    )
  )
)
100%|██████████| 100/100 [00:00<00:00, 514.42it/s]
[SNN Simulating... 0.64%] Acc:1.000
 54%|█████▍    | 54/100 [00:00<00:00, 533.31it/s][SNN Simulating... 1.28%] Acc:1.000
100%|██████████| 100/100 [00:00<00:00, 536.25it/s]
 56%|█████▌    | 56/100 [00:00<00:00, 558.51it/s][SNN Simulating... 1.92%] Acc:1.000
100%|██████████| 100/100 [00:00<00:00, 560.30it/s]
 57%|█████▋    | 57/100 [00:00<00:00, 568.64it/s][SNN Simulating... 2.56%] Acc:1.000
100%|██████████| 100/100 [00:00<00:00, 557.26it/s]
 55%|█████▌    | 55/100 [00:00<00:00, 543.26it/s][SNN Simulating... 3.20%] Acc:1.000
100%|██████████| 100/100 [00:00<00:00, 548.07it/s]
100%|██████████| 100/100 [00:00<00:00, 553.99it/s]
[SNN Simulating... 3.84%] Acc:0.997
 54%|█████▍    | 54/100 [00:00<00:00, 538.58it/s][SNN Simulating... 4.48%] Acc:0.998
100%|██████████| 100/100 [00:00<00:00, 536.22it/s]
100%|██████████| 100/100 [00:00<00:00, 536.19it/s]
[SNN Simulating... 5.12%] Acc:0.998
 54%|█████▍    | 54/100 [00:00<00:00, 538.42it/s][SNN Simulating... 5.76%] Acc:0.998
100%|██████████| 100/100 [00:00<00:00, 536.13it/s]
100%|██████████| 100/100 [00:00<00:00, 533.33it/s]
[SNN Simulating... 6.40%] Acc:0.998
 54%|█████▍    | 54/100 [00:00<00:00, 533.21it/s][SNN Simulating... 7.04%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.33it/s]
100%|██████████| 100/100 [00:00<00:00, 539.10it/s]
[SNN Simulating... 7.68%] Acc:0.999
 54%|█████▍    | 54/100 [00:00<00:00, 533.23it/s][SNN Simulating... 8.32%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 536.28it/s]
100%|██████████| 100/100 [00:00<00:00, 533.26it/s]
[SNN Simulating... 8.96%] Acc:0.999
 55%|█████▌    | 55/100 [00:00<00:00, 548.69it/s][SNN Simulating... 9.60%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 551.10it/s]
 55%|█████▌    | 55/100 [00:00<00:00, 548.40it/s][SNN Simulating... 10.24%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 544.92it/s]
 54%|█████▍    | 54/100 [00:00<00:00, 533.23it/s][SNN Simulating... 10.88%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
[SNN Simulating... 11.52%] Acc:0.999
 53%|█████▎    | 53/100 [00:00<00:00, 528.59it/s][SNN Simulating... 12.16%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 511.46it/s]
100%|██████████| 100/100 [00:00<00:00, 542.03it/s]
[SNN Simulating... 12.80%] Acc:0.999
 54%|█████▍    | 54/100 [00:00<00:00, 538.57it/s][SNN Simulating... 13.44%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 547.99it/s]
100%|██████████| 100/100 [00:00<00:00, 545.00it/s]
[SNN Simulating... 14.08%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 544.99it/s]
[SNN Simulating... 14.72%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
[SNN Simulating... 15.36%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 536.20it/s]
[SNN Simulating... 16.00%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 544.99it/s]
[SNN Simulating... 16.64%] Acc:0.999
 56%|█████▌    | 56/100 [00:00<00:00, 552.98it/s][SNN Simulating... 17.28%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 554.08it/s]
 54%|█████▍    | 54/100 [00:00<00:00, 533.38it/s][SNN Simulating... 17.92%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.42it/s]
 54%|█████▍    | 54/100 [00:00<00:00, 538.71it/s][SNN Simulating... 18.56%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 545.07it/s]
100%|██████████| 100/100 [00:00<00:00, 547.99it/s]
[SNN Simulating... 19.20%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 554.16it/s]
[SNN Simulating... 19.84%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 551.02it/s]
[SNN Simulating... 20.48%] Acc:0.999
 54%|█████▍    | 54/100 [00:00<00:00, 538.56it/s][SNN Simulating... 21.12%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 536.21it/s]
 55%|█████▌    | 55/100 [00:00<00:00, 548.54it/s][SNN Simulating... 21.76%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 542.03it/s]
 54%|█████▍    | 54/100 [00:00<00:00, 538.56it/s][SNN Simulating... 22.40%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.26it/s]
100%|██████████| 100/100 [00:00<00:00, 551.02it/s]
[SNN Simulating... 23.04%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 557.17it/s]
[SNN Simulating... 23.68%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 542.03it/s]
[SNN Simulating... 24.32%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 551.01it/s]
[SNN Simulating... 24.96%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 557.26it/s]
[SNN Simulating... 25.60%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 557.17it/s]
[SNN Simulating... 26.24%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 551.02it/s]
[SNN Simulating... 26.88%] Acc:0.999
 56%|█████▌    | 56/100 [00:00<00:00, 551.19it/s][SNN Simulating... 27.52%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 544.02it/s]
 54%|█████▍    | 54/100 [00:00<00:00, 533.23it/s][SNN Simulating... 28.16%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
 53%|█████▎    | 53/100 [00:00<00:00, 528.59it/s][SNN Simulating... 28.80%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
 53%|█████▎    | 53/100 [00:00<00:00, 528.59it/s][SNN Simulating... 29.44%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
100%|██████████| 100/100 [00:00<00:00, 554.16it/s]
[SNN Simulating... 30.08%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 557.26it/s]
[SNN Simulating... 30.72%] Acc:0.999
 57%|█████▋    | 57/100 [00:00<00:00, 568.49it/s][SNN Simulating... 31.36%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 563.47it/s]
100%|██████████| 100/100 [00:00<00:00, 563.56it/s]
[SNN Simulating... 32.00%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 560.30it/s]
[SNN Simulating... 32.64%] Acc:0.999
 56%|█████▌    | 56/100 [00:00<00:00, 558.66it/s][SNN Simulating... 33.28%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 560.39it/s]
100%|██████████| 100/100 [00:00<00:00, 554.08it/s]
[SNN Simulating... 33.92%] Acc:0.999
 57%|█████▋    | 57/100 [00:00<00:00, 563.01it/s][SNN Simulating... 34.56%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 563.56it/s]
100%|██████████| 100/100 [00:00<00:00, 563.56it/s]
[SNN Simulating... 35.20%] Acc:0.999
 56%|█████▌    | 56/100 [00:00<00:00, 558.66it/s][SNN Simulating... 35.84%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 560.39it/s]
 53%|█████▎    | 53/100 [00:00<00:00, 528.59it/s][SNN Simulating... 36.48%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 530.50it/s]
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
[SNN Simulating... 37.12%] Acc:0.999
 54%|█████▍    | 54/100 [00:00<00:00, 538.56it/s][SNN Simulating... 37.76%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 542.03it/s]
100%|██████████| 100/100 [00:00<00:00, 545.04it/s]
[SNN Simulating... 38.40%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
[SNN Simulating... 39.04%] Acc:0.999
 54%|█████▍    | 54/100 [00:00<00:00, 533.23it/s][SNN Simulating... 39.68%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
[SNN Simulating... 40.32%] Acc:0.999
 54%|█████▍    | 54/100 [00:00<00:00, 533.23it/s][SNN Simulating... 40.96%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 530.50it/s]
100%|██████████| 100/100 [00:00<00:00, 551.10it/s]
[SNN Simulating... 41.60%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 530.50it/s]
[SNN Simulating... 42.24%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 536.20it/s]
[SNN Simulating... 42.88%] Acc:0.999
 54%|█████▍    | 54/100 [00:00<00:00, 533.24it/s][SNN Simulating... 43.52%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
 54%|█████▍    | 54/100 [00:00<00:00, 533.23it/s][SNN Simulating... 44.16%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
100%|██████████| 100/100 [00:00<00:00, 554.08it/s]
[SNN Simulating... 44.80%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 560.31it/s]
[SNN Simulating... 45.44%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
[SNN Simulating... 46.08%] Acc:0.999
 55%|█████▌    | 55/100 [00:00<00:00, 548.54it/s][SNN Simulating... 46.72%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 557.17it/s]
100%|██████████| 100/100 [00:00<00:00, 545.00it/s]
[SNN Simulating... 47.36%] Acc:0.999
 54%|█████▍    | 54/100 [00:00<00:00, 533.23it/s][SNN Simulating... 48.00%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
 55%|█████▌    | 55/100 [00:00<00:00, 543.11it/s][SNN Simulating... 48.64%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 539.10it/s]
 54%|█████▍    | 54/100 [00:00<00:00, 533.23it/s][SNN Simulating... 49.28%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.33it/s]
 55%|█████▌    | 55/100 [00:00<00:00, 543.10it/s][SNN Simulating... 49.92%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 542.03it/s]
 54%|█████▍    | 54/100 [00:00<00:00, 538.57it/s][SNN Simulating... 50.56%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 536.20it/s]
 53%|█████▎    | 53/100 [00:00<00:00, 528.59it/s][SNN Simulating... 51.20%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 530.50it/s]
 54%|█████▍    | 54/100 [00:00<00:00, 533.23it/s][SNN Simulating... 51.84%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
[SNN Simulating... 52.48%] Acc:0.999
 54%|█████▍    | 54/100 [00:00<00:00, 533.23it/s][SNN Simulating... 53.12%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
 54%|█████▍    | 54/100 [00:00<00:00, 533.23it/s][SNN Simulating... 53.76%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
100%|██████████| 100/100 [00:00<00:00, 536.20it/s]
[SNN Simulating... 54.40%] Acc:0.999
 53%|█████▎    | 53/100 [00:00<00:00, 528.59it/s][SNN Simulating... 55.04%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 530.50it/s]
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
[SNN Simulating... 55.68%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
[SNN Simulating... 56.32%] Acc:0.999
 54%|█████▍    | 54/100 [00:00<00:00, 533.23it/s][SNN Simulating... 56.96%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
100%|██████████| 100/100 [00:00<00:00, 539.19it/s]
[SNN Simulating... 57.60%] Acc:0.999
 55%|█████▌    | 55/100 [00:00<00:00, 548.54it/s][SNN Simulating... 58.24%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 554.08it/s]
 55%|█████▌    | 55/100 [00:00<00:00, 543.25it/s][SNN Simulating... 58.88%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 542.11it/s]
 57%|█████▋    | 57/100 [00:00<00:00, 564.82it/s][SNN Simulating... 59.52%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 555.16it/s]
100%|██████████| 100/100 [00:00<00:00, 536.20it/s]
[SNN Simulating... 60.16%] Acc:0.999
 56%|█████▌    | 56/100 [00:00<00:00, 553.13it/s][SNN Simulating... 60.80%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 545.08it/s]
100%|██████████| 100/100 [00:00<00:00, 539.02it/s]
[SNN Simulating... 61.44%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 536.28it/s]
[SNN Simulating... 62.08%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 550.93it/s]
[SNN Simulating... 62.72%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.41it/s]
[SNN Simulating... 63.36%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.36it/s]
[SNN Simulating... 64.00%] Acc:0.999
 54%|█████▍    | 54/100 [00:00<00:00, 533.07it/s][SNN Simulating... 64.64%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 539.10it/s]
100%|██████████| 100/100 [00:00<00:00, 533.33it/s]
[SNN Simulating... 65.28%] Acc:0.999
 55%|█████▌    | 55/100 [00:00<00:00, 548.56it/s][SNN Simulating... 65.92%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 542.03it/s]
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
[SNN Simulating... 66.56%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.32it/s]
[SNN Simulating... 67.20%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 547.97it/s]
[SNN Simulating... 67.84%] Acc:0.999
 54%|█████▍    | 54/100 [00:00<00:00, 533.20it/s][SNN Simulating... 68.48%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.33it/s]
100%|██████████| 100/100 [00:00<00:00, 533.41it/s]
[SNN Simulating... 69.12%] Acc:0.999
 54%|█████▍    | 54/100 [00:00<00:00, 533.38it/s][SNN Simulating... 69.76%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 536.19it/s]
 55%|█████▌    | 55/100 [00:00<00:00, 543.10it/s][SNN Simulating... 70.40%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 545.08it/s]
 54%|█████▍    | 54/100 [00:00<00:00, 538.40it/s][SNN Simulating... 71.04%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 536.11it/s]
 54%|█████▍    | 54/100 [00:00<00:00, 533.23it/s][SNN Simulating... 71.68%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.33it/s]
100%|██████████| 100/100 [00:00<00:00, 557.14it/s]
[SNN Simulating... 72.32%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 536.20it/s]
[SNN Simulating... 72.96%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.35it/s]
[SNN Simulating... 73.60%] Acc:0.999
 54%|█████▍    | 54/100 [00:00<00:00, 533.40it/s][SNN Simulating... 74.24%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.35it/s]
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
[SNN Simulating... 74.88%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 542.02it/s]
[SNN Simulating... 75.52%] Acc:0.999
 54%|█████▍    | 54/100 [00:00<00:00, 533.24it/s][SNN Simulating... 76.16%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 542.11it/s]
100%|██████████| 100/100 [00:00<00:00, 554.08it/s]
[SNN Simulating... 76.80%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 557.07it/s]
[SNN Simulating... 77.44%] Acc:0.999
 56%|█████▌    | 56/100 [00:00<00:00, 558.37it/s][SNN Simulating... 78.08%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 553.99it/s]
100%|██████████| 100/100 [00:00<00:00, 551.01it/s]
[SNN Simulating... 78.72%] Acc:0.999
 55%|█████▌    | 55/100 [00:00<00:00, 548.69it/s][SNN Simulating... 79.36%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 547.95it/s]
 56%|█████▌    | 56/100 [00:00<00:00, 558.66it/s][SNN Simulating... 80.00%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 557.17it/s]
100%|██████████| 100/100 [00:00<00:00, 554.00it/s]
[SNN Simulating... 80.64%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 544.92it/s]
[SNN Simulating... 81.28%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 551.03it/s]
[SNN Simulating... 81.92%] Acc:0.999
 53%|█████▎    | 53/100 [00:00<00:00, 528.73it/s][SNN Simulating... 82.56%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
[SNN Simulating... 83.20%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 539.09it/s]
[SNN Simulating... 83.84%] Acc:0.999
 54%|█████▍    | 54/100 [00:00<00:00, 533.36it/s][SNN Simulating... 84.48%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 545.07it/s]
100%|██████████| 100/100 [00:00<00:00, 539.02it/s]
[SNN Simulating... 85.12%] Acc:0.999
 54%|█████▍    | 54/100 [00:00<00:00, 538.34it/s][SNN Simulating... 85.76%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 536.12it/s]
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
[SNN Simulating... 86.40%] Acc:0.999
 55%|█████▌    | 55/100 [00:00<00:00, 542.96it/s][SNN Simulating... 87.04%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 539.10it/s]
 54%|█████▍    | 54/100 [00:00<00:00, 538.55it/s][SNN Simulating... 87.68%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 536.28it/s]
100%|██████████| 100/100 [00:00<00:00, 536.21it/s]
[SNN Simulating... 88.32%] Acc:0.999
 54%|█████▍    | 54/100 [00:00<00:00, 538.39it/s][SNN Simulating... 88.96%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 536.09it/s]
 54%|█████▍    | 54/100 [00:00<00:00, 533.23it/s][SNN Simulating... 89.60%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
[SNN Simulating... 90.24%] Acc:0.999
 54%|█████▍    | 54/100 [00:00<00:00, 533.23it/s][SNN Simulating... 90.88%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 536.20it/s]
100%|██████████| 100/100 [00:00<00:00, 542.03it/s]
[SNN Simulating... 91.52%] Acc:0.999
 55%|█████▌    | 55/100 [00:00<00:00, 543.12it/s][SNN Simulating... 92.16%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 539.11it/s]
100%|██████████| 100/100 [00:00<00:00, 530.50it/s]
[SNN Simulating... 92.80%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 536.21it/s]
[SNN Simulating... 93.44%] Acc:0.999
 54%|█████▍    | 54/100 [00:00<00:00, 538.56it/s][SNN Simulating... 94.08%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 545.00it/s]
 56%|█████▌    | 56/100 [00:00<00:00, 558.69it/s][SNN Simulating... 94.72%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 560.40it/s]
 54%|█████▍    | 54/100 [00:00<00:00, 533.24it/s][SNN Simulating... 95.36%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 536.20it/s]
100%|██████████| 100/100 [00:00<00:00, 542.04it/s]
[SNN Simulating... 96.00%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 554.08it/s]
[SNN Simulating... 96.64%] Acc:0.999
 54%|█████▍    | 54/100 [00:00<00:00, 533.23it/s][SNN Simulating... 97.28%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
100%|██████████| 100/100 [00:00<00:00, 530.50it/s]
[SNN Simulating... 97.92%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 530.50it/s]
[SNN Simulating... 98.56%] Acc:0.999
 54%|█████▍    | 54/100 [00:00<00:00, 533.23it/s][SNN Simulating... 99.20%] Acc:0.999
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
100%|██████████| 100/100 [00:00<00:00, 533.34it/s]
[SNN Simulating... 99.84%] Acc:0.999
 82%|████████▏ | 82/100 [00:00<00:00, 809.94it/s][SNN Simulating... 100.00%] Acc:0.999
SNN Simulating Accuracy:0.999
Summary:	ANN Accuracy:99.7500%  	SNN Accuracy:99.9000% [Increased 0.1500%]
100%|██████████| 100/100 [00:00<00:00, 804.44it/s]

Process finished with exit code 0
华天雪 L.W
关注
  • 0
    点赞
  • 踩
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
专栏目录
超宽带（UWB）信号谱的中心频率及-10dB带宽的计算(MATLAB)
ROF
01-07 3532
对于超宽带（UWB）信号，相对带宽或带宽及中心频率是其中两个重要的参数。如果已经得到UWB信号谱，那么通过信号谱如何来计算带宽及中心频率呢？ 一般来说，UWB信号谱可以通过直接测量或者由OptiSystem得到，是离散谱。通过拟合的方法，可以求得其中心频率及带宽。以下是自定义的求中心频率和带宽的函数find_UWB %=================...
为什么天线的回波损耗以-10dB大小来衡量？
aichu9418的博客
02-24 9846
传送门：http://www.eeworld.com.cn/Test_and_measurement/2014/0610/article_9152.html i:对于2端口无损耗网络，可以根据S11的值求出S21的值，但实际上么有那么多无损耗网络，但至少 说明S11与S21是相关的 ii;当S11高达-10dB时，30%的信号被反射，S21的传输损耗为-0.5dB？原文有公式 i...
-3dB下的正确率是100%！！！
huatianxue的博客
05-30 371
太难以置信了 2021年5月30日21:33:09跑的ann2snn的程序，结果居然是100% G:\python\python.exe "F:/my_code/spikingjelly-master-20201221/spikingjelly/clock_driven/ann2snn/examples/if_cnn_mnist_work - 副本.py" All the temp files are saved to ./log-cnn_mnist1622380146.61931 ann2snn con
dB, -3dB, -6dB相关知识
panlan7的博客
10-16 1万+
关于通频带，3dB带宽，三阶截点和1dB压缩点，截止频率，频率范围，带宽，特征频率（中心频率），截止频率和增益（db)_吵吵超超的博客-CSDN博客_1db压缩点定义。在信号传输系统中，系统输出信号从最大值衰减3dB的信号频率，上、下截止频率之间的频带称为通频带，用BW表示，通频带越宽，表明放大电路对不同频率信号的适应能力越强。时，取对数再乘以20，刚好等于-3dB，即，当功率降为原来一半时，此时的电压值降为原来的0.707倍。, 那么这个电路的增益为-3dB，即衰减3dB，功率降为原来的一半。
什么是分贝dB？
Android系统攻城狮
01-16 6317
关于分贝dB，人们的第一感觉认为是声音的大小单位，如机械厂房中噪声为90分贝。dB真的是单位吗？其实分贝除了用于声学领域之外，在NVH测量领域，到处可见分贝。它似乎是一个测量值的单位，通常是纵轴，但实际上它不是一个单位，它是个无量纲。我们经常在声学、振动、电子学、电信、音频工程&设计等领域见到它。既然它是个无量纲，那我们为什么要用它呢，怎么正确使用它呢？ 分贝最初使用是在电信行业，是为了...
1k-6dB-5s-16k-16-mono.wav 单声道1KHZ -6db 16k 16bit音频素材
最新发布
06-22
1k_-6dB_5s_16k_16_mono.wav 单声道1KHZ -6db 16k 16bit音频素材
6ES7136-6DB00-0CA0_V200_GSD_
09-30
标题 "6ES7136-6DB00-0CA0_V200_GSD_" 暗示我们正在讨论一个与Siemens PLC（可编程逻辑控制器）相关的固件或配置文件。"GSD" 标签进一步指出，这可能涉及到GSD（Generic Station Description）文件，它是用于描述...
sdk-6db5720-monkeyrunner 源码
11-24
【标题】"sdk-6db5720-monkeyrunner 源码"涉及的是Android SDK中的MonkeyRunner工具的源代码。MonkeyRunner是一款强大的自动化测试工具，它允许开发者通过编写Python脚本来控制Android设备或模拟器，进行各种自动化...
cssmin-minified_miv6db_cssmin_
10-01
这个压缩包"cssmin-minified_miv6db_cssmin_"显然与CSS压缩有关，它包含了一个名为"cssmin-v3.0.1-minified.php"的PHP脚本，这可能是一个用于压缩和优化CSS代码的库。在网站开发过程中，为了提高网页加载速度和降低...
信号强度（RSSI）知识整理
时光
03-03 8020
为什么无线信号（RSSI）是负值 答：其实归根到底为什么接收的无线信号是负值，这样子是不是容易理解多了。因为无线信号多为mW级别，所以对它进行了极化，转化为dBm而已，不表示信号是负的。1mW就是0dBm，小于1mW就是负数的dBm数。 弄清信号强度的定义就行了： RSSI（接收信号强度）Received Signal Strength Indicator Rss=10logP, 只需将接受到的信号功率P代入就是接收信号强度（灵敏度）。 [例1] 如果发射功率P为1mw，折算为dBm后为0dBm。 [例
3. 天线设计理论 - 什么是带宽
我思故我在！
02-27 8478
-10dB:对于天线来说，90%能收到，就认就可以接收。 天线：-13dB阻抗带宽。取决于应用 对于接头来说，需要-20dB才可接收。 相对带宽：能工作的上频率 - 下频率，然后除以中心频率。 通常用相对带宽这个概念 频率作为一种资源是有限的，只能划分成若干个信道，所以信道的带宽也是有限制的，太窄传递信息有限，太宽又浪费频率资源。 信道与信道之间必须有一定频率范围的间隔，所以就有了相对带宽这么一个概念。它只能是百分之几，如果过度了，则会影响毗邻信道的信息传输。也就是说一个信道从低频到高频的范围中..
基于UWB的高精度定位
whaosoft143ai的博客
05-21 4253
基于UWB的室内高精度定位系统 UWB定位简介 超宽带（Ultra Wide-Band，UWB）是一种新型的无线通信技术，根据美国联邦通信委员会的规范，UWB的工作频带为3.1~10.6GHz，系统-10dB带宽与系统中心频率之比大于20%或系统带宽至少为500MHz。UWB信号的发生可通过发射时间极短（如2ns）的窄脉冲（如二次高斯脉冲）通过微分或混频等上变频方式调制到UWB工作频段实现。目前，包括美国，日本，加拿大等在内的国家都在研究这项技术，在无线室内定位领域具有良好的前景。 UWB 技术..
射频&天线设计-dB知多少
madmanazo的博客
08-11 1479
《射频&天线设计-dB知多少》 在调试射频输出功率时经常听到“相差多少dB”，刚入门的话听得一脸懵逼，当然这种通俗单位别人也懒得跟你解释。 分贝（dB）是一个对数单位（logarithmic unit），最初用在声音领域，表示两个相同单位的物理量（功率）的比值： 作为分母的那个量通常是一个参考基准值，dB描述的是作为分子的物理量相对于基准值的大小，是一个相对值。 根据对数函数的特性可以看出，dB允许我们用简短的数字表示一个非常大的物理量： X=1000000000→10lgX = 90dB 这样有
一起聊聊 dB、dB、dBm、dBi 吧！
一名热爱技术的工程师的博客。分享技术干货，记录美好生活。永远相信美好的事情即将发生。
11-17 1614
点击上方“小麦大叔”，选择“置顶/星标公众号”福利干货，第一时间送达dB应该是无线通信中最基本、最习以为常的一个概念了。我们常说“传播损耗是xx dB”、“发射功率是xx dBm”、“天线...
电磁波传播相位是否会变化_电磁波、射频通信基础知识科普，超通俗解释！
weixin_42153615的博客
12-30 3278
一、电磁波 电磁波是能量的一种，凡是高于绝对零度的物体，都会释出电磁波。电与磁可说是一体两面，电流会产生磁场，变动的磁场则会产生电流。变化的电场和变化的磁场构成了一个不可分离的统一的场。 在低频的电振荡中，磁电之间的相互变化比较缓慢，其能量几乎全部返回原电路而没有能量辐射出去；在高频率的电振荡中，磁电互变甚快，能量不可能全部返回原 振荡电路，于是电能、磁能随着电场...
经验法则：回波损耗多少才算多？//学习记录
flomingo1的专栏
11-13 7502
可以说，99%的工程师经常被S参数搞混，当S参数被用来定义一些规范时，常常定义者自己都不理解S参数，本文将用经验法则告诉大家，如何规范的计算回波损耗。 S参数矩阵中的每个参量，事实上都是正弦信号从互连系统中某一端口输出和另一端口输入之间的比较。反射系数S11定义为端口1反射的能量占端口1入射信号的比例，也就是输入回波损耗;传输系数S21定义为从端口2出来的正弦波和从端口1进入的正弦波的比值。 我们知道，正弦波的能量是振幅的平方，据此，对于损耗很小的网络，S11和S21之间有如下的关系： 如果知道S11
-3dB的理解
weixin_30828379的博客
01-15 2722
-3dB到底是什么？集成运放-3dB带宽又是什么？ 以无源高通电路为例，介绍-3dB的意义。 输出与输入只比： Au=Uo/Ui=R/(R+1/j*2*PI*f*C)=1/(1+1/j*2*PI*f*R*C)。式中j*j=-1。 令fL=1/2*PI*R*C Au=1/(1+fL/jf)=jf/(jf+fL)=(jf/fL)/(1+jf/fL)=(1-jf/fL)*(j...
（微信开发）PHP curl模拟登陆教务系统查询成绩查询课表实现微信查成绩差课表功能
热门推荐
xiaoxiaobai2015的专栏
02-07 78万+
最近微信开发特别火，刚学会helloword的我也去玩了一下。做了一个微信端查成绩、查课表、查考试安排，图书借阅情况，一键续借的微信公众账号。做了几天，从只会echo到这个公众账号完成，遇到了不少问题，也学到了不少东西。现在写出来算是总结吧。也给需要的同学一个参考的例子。下面以中南民族大学教务系统为例。      一.原理        模拟登陆的原理是这样的，当我们登陆教务系统的时候，我们把学号
用AudioSegment 音频设置为 +6db到-6db之间
04-25
您可以使用以下代码将音频文件的音量设置在6dB到-6dB之间： ``` from pydub import AudioSegment # load audio file audio = AudioSegment.from_file("path/to/audio.wav", format="wav") # set volume to a ...

“相关推荐”对你有帮助么？

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值