Q：怎么看loss和acc的变化（loss几回合就不变了怎么办？）
（转自http://blog.csdn.net/SMF0504/article/details/71698354）
- train loss 不断下降，test loss不断下降，说明网络仍在学习;
- train loss 不断下降，test loss趋于不变，说明网络过拟合;
- train loss 趋于不变，test loss不断下降，说明数据集100%有问题;
- train loss 趋于不变，test loss趋于不变，说明学习遇到瓶颈，需要减小学习率或批量数目;
- train loss 不断上升，test loss不断上升，说明网络结构设计不当，训练超参数设置不当，数据集经过清洗等问题。
Q：训练过程中loss数值为负数？
【原因】输入的训练数据没有归一化造成
【解决方法】把输入数值通过下面的函数过滤一遍，进行归一化
def data_in_one(inputdata):
inputdata = (inputdata-inputdata.min())/(inputdata.max()-inputdata.min())
return inputdata
Q：如何让训练过程可视化
import keras
from keras.utils import np_utils
import matplotlib.pyplot as plt
%matplotlib inline
#写一个LossHistory类，保存loss和acc
class LossHistory(keras.callbacks.Callback):
def on_train_begin(self, logs={}):
self.losses = {'batch':[], 'epoch':[]}
self.accuracy = {'batch':[], 'epoch':[]}
self.val_loss = {'batch':[], 'epoch':[]}
self.val_acc = {'batch':[], 'epoch':[]}
def on_batch_end(self, batch, logs={}):
self.losses['batch'].append(logs.get('loss'))
self.accuracy['batch'].append(logs.get('acc'))
self.val_loss['batch'].append(logs.get('val_loss'))
self.val_acc['batch'].append(logs.get('val_acc'))
def on_epoch_end(self, batch, logs={}):
self.losses['epoch'].append(logs.get('loss'))
self.accuracy['epoch'].append(logs.get('acc'))
self.val_loss['epoch'].append(logs.get('val_loss'))
self.val_acc['epoch'].append(logs.get('val_acc'))
def loss_plot(self, loss_type):
iters = range(len(self.losses[loss_type]))
plt.figure()
# acc
plt.plot(iters, self.accuracy[loss_type], 'r', label='train acc')
# loss
plt.plot(iters, self.losses[loss_type], 'g', label='train loss')
if loss_type == 'epoch':
# val_acc
plt.plot(iters, self.val_acc[loss_type], 'b', label='val acc')
# val_loss
plt.plot(iters, self.val_loss[loss_type], 'k', label='val loss')
plt.grid(True)
plt.xlabel(loss_type)
plt.ylabel('acc-loss')
plt.legend(loc="upper right")
plt.show()
在模型中，model语句前加上:
history = LossHistory()
然后在model.fit里加上callbacks = {history}，以及下面调用history
model.fit(x, y, batch_size=32, nb_epoch=20,validation_data = (xt,yt),validation_steps=None,callbacks=[history])
history.loss_plot('epoch')
结果如下：
image.png
