AdaBound | An optimizer that trains as fast as Adam and as good as SGD | Machine Learning library

model: resnet18
msc: False            # if you use temporal multi-scale input

class_weight: True    # if you use class weight to calculate cross entropy or not
writer_flag: True     # if you use tensorboardx or not

n_classes: 400
batch_size: 32
inp  

# learning can be either a scalar or a tensor

# use exclude_from_weight_decay feature, 
# if you wanna selectively disable updating weight-decayed weights

optimizer = AdaBoundOptimizer(
    learning_rate=1e-3,
    final_lr=1e-1,
    beta_1=0.9,
     

model=Net(num_classes=9).to('cuda')
#model=MobileNetV2(n_class=9).to('cuda')
#model=resnet50(num_class=9,pretrained=False).to('cuda')
print(model)
print("cuda:0")

model=Net(num_classes=9).to('cpu')
#model = MobileNetV2(n_class=9).to("cpu")
#model=re