我成功地将早期停止功能应用到Keras模型中,但是我不确定如何查看最佳时期的损失。
es = EarlyStopping(monitor='val_out_soft_loss',
mode='min',
restore_best_weights=True,
verbose=2,
patience=10)
model.fit(tr_x,
tr_y,
batch_size=batch_size,
epochs=epochs,
verbose=1,
callbacks=[es],
validation_data=(val_x, val_y))
loss = model.history.history["val_out_soft_loss"][-1]
return model, loss
我定义的损失分数意味着返回的分数来自最终时期,而不是最佳时期。
例如:
from sklearn.model_selection import train_test_split, KFold
losses = []
models = []
for k in range(2):
kfold = KFold(5, random_state = 42 + k, shuffle = True)
for k_fold, (tr_inds, val_inds) in enumerate(kfold.split(train_y)):
print("-----------")
print("-----------")
model, loss = get_model(64, 100)
models.append(model)
print(k_fold, loss)
losses.append(loss)
print("-------")
print(losses)
print(np.mean(losses))
Epoch 23/100
18536/18536 [==============================] - 7s 362us/step - loss: 0.0116 - out_soft_loss: 0.0112 - out_reg_loss: 0.0393 - val_loss: 0.0131 - val_out_soft_loss: 0.0127 - val_out_reg_loss: 0.0381
Epoch 24/100
18536/18536 [==============================] - 7s 356us/step - loss: 0.0116 - out_soft_loss: 0.0112 - out_reg_loss: 0.0388 - val_loss: 0.0132 - val_out_soft_loss: 0.0127 - val_out_reg_loss: 0.0403
Restoring model weights from the end of the best epoch
Epoch 00024: early stopping
0 0.012735568918287754
因此,在这个例子中,我想看到Epoch 00014时的损失(为0.0124)。
我还有一个单独的问题:如何设置val_out_soft_loss分数的小数位数?
loss = model.history.history["val_out_soft_loss"][-1]
,删除[-1]
并调用np.min(loss)
。但我猜想这不是你想要的,因为这有点显而易见。 - Nicolas Gervais