The CIFAR10 dataset has the classes: ‘airplane’, ‘automobile’, ‘bird’, ‘cat’, ‘deer’, ‘dog’, ‘frog’, ‘horse’, ‘ship’, ‘truck’. The images in CIFAR-10 are of size 3x32x32, i.e. 3-channel color images of 32x32 pixels in size.
I trained a simple CNN network on the CIFAR10 dataset. when the hyperparameter lr = 0.0008，here is the model's Performance
When I change the lr to 0.001,here is the model's Performance
When I change the lr to 0.002,here is the model's Performance
