search

seominseok0429 / Real-world-Anomaly-Detection-in-Surveillance-Videos-pytorch

Real-world Anomaly Detection in Surveillance Videos- pytorch Re-implementation
102 stars 24 forks source link

Run code via cpu or withour nvidia driver #5

Closed Chuttyboy closed 2 years ago

Chuttyboy commented 2 years ago

Hello

def MIL(y_pred, batch_size, is_transformer=0):
    loss = torch.tensor(0.).cpu()
    loss_intra = torch.tensor(0.).cpu()
    sparsity = torch.tensor(0.).cpu()
    smooth = torch.tensor(0.).cpu()
    if is_transformer==0:
        y_pred = y_pred.view(batch_size, -1)
    else:
        y_pred = torch.sigmoid(y_pred)

    for i in range(batch_size):
        anomaly_index = torch.randperm(30).cpu()
        normal_index = torch.randperm(30).cpu()

Just change cuda to cpu it's working without Nvidia driver

Thank you