git clone https://github.com/ZLkanyo009/STBP-train-and-compression.git

conv = nn.Conv2d(...)
conv_s = tdLayer(conv)

spike = LIFSpike()

def forward(self, x):
    x = self.conv1_s(x)
    x = self.spike(x)
    x = self.pool1_s(x)
    x = self.spike(x)
    x = x.view(x.shape[0], -1, x.shape[4])
    x = self.fc1_s(x)
    x = self.spike(x)
    out = torch.sum(x, dim=2) / steps
    return out

bn = nn.BatchNorm2d(...)
bn = tdBatchNorm(...)
conv_s = tdLayer(conv, bn)

# Start training fp32 model with: 
# model_name can be ResNet18, CifarNet, ...
python main.py ResNet18 --dataset CIFAR10

# training with DDP:
python -m torch.distributed.launch main.py ResNet18 --local_rank 0 --dataset CIFAR10 --p DDP

# You can manually config the training with: 
python main.py ResNet18 --resume --lr 0.01

# Start training quantize model with: 
# model_name can be ResNet18, CifarNet, ...
python main.py ResNet18 --dataset CIFAR10 -q

# training with DDP:
python -m torch.distributed.launch main.py ResNet18 --local_rank 0 --dataset CIFAR10 -q --p DDP

# You can manually config the training with: 
python main.py ResNet18 -q --resume --bit 4 --lr 0.01