my_callbacks = [
tf.keras.callbacks.EarlyStopping(patience=2),
tf.keras.callbacks.ModelCheckpoint(filepath='model.{epoch:02d}-{val_loss:.2f}.h5'),
tf.keras.callbacks.TensorBoard(log_dir='./logs'),
]
model.fit(dataset, epochs=10, callbacks=my_callbacks)
start_epoch = -1
if RESUME:
path_checkpoint = "./models/checkpoint/ckpt_best_1.pth" # 断点路径
checkpoint = torch.load(path_checkpoint) # 加载断点
model.load_state_dict(checkpoint['net']) # 加载模型可学习参数
optimizer.load_state_dict(checkpoint['optimizer']) # 加载优化器参数
start_epoch = checkpoint['epoch'] # 设置开始的epoch
for epoch in range(start_epoch + 1 ,EPOCH):
# print('EPOCH:',epoch)
for step, (b_img,b_label) in enumerate(train_loader):
train_output = model(b_img)
loss = loss_func(train_output,b_label)
# losses.append(loss)
optimizer.zero_grad()
loss.backward()
optimizer.step()if RESUME:
path_checkpoint = "./models/checkpoint/ckpt_best_1.pth" # 断点路径
checkpoint = torch.load(path_checkpoint) # 加载断点
model.load_state_dict(checkpoint['net']) # 加载模型可学习参数
optimizer.load_state_dict(checkpoint['optimizer']) # 加载优化器参数
start_epoch = checkpoint['epoch'] # 设置开始的epoch#加载恢复
if RESUME:
path_checkpoint = "./model_parameter/test/ckpt_best_50.pth" # 断点路径
checkpoint = torch.load(path_checkpoint) # 加载断点
model.load_state_dict(checkpoint['net']) # 加载模型可学习参数
optimizer.load_state_dict(checkpoint['optimizer']) # 加载优化器参数
start_epoch = checkpoint['epoch'] # 设置开始的epoch
lr_schedule.load_state_dict(checkpoint['lr_schedule'])#加载lr_scheduler
#保存
for epoch in range(start_epoch+1,80):
optimizer.zero_grad()
optimizer.step()
lr_schedule.step()
if epoch %10 ==0:
print('epoch:',epoch)
print('learning rate:',optimizer.state_dict()['param_groups'][0]['lr'])
checkpoint = {
"net": model.state_dict(),
'optimizer': optimizer.state_dict(),
"epoch": epoch,
'lr_schedule': lr_schedule.state_dict()
}
if not os.path.isdir("./model_parameter/test"):
os.mkdir("./model_parameter/test")
torch.save(checkpoint, './model_parameter/test/ckpt_best_%s.pth' % (str(epoch)))