在Keras中使用tensorboard可视化acc等曲线

1.使用tensorboard可视化ACC，loss等曲线

 keras.callbacks.TensorBoard(log_dir='./Graph',
                     histogram_freq= 0 ,
                     write_graph=True,
                 write_images=True)
 tbCallBack = keras.callbacks.TensorBoard(log_dir='./Graph',
                                          histogram_freq= 0,
                                          write_graph=True,
                                          write_images=True)
 …
 …
 model.compile(optimizer=optim,
               loss=MultiboxLoss(NUM_CLASSES, neg_pos_ratio=2.0).compute_loss, metrics=['accuracy'])
 nb_epoch = 30
 history = model.fit_generator(gen.generate(True), gen.train_batches,
                               nb_epoch, verbose=1,
                              callbacks=[tbCallBack],
                              validation_data=gen.generate(False),
                               nb_val_samples=gen.val_batches,
                               nb_worker=1)

然后新开一个终端 
输入：

tensorboard --logdir path_to_current_dir/Graph 

之后打开终端给出的网址即可。

2.直接使用matplotlib画出训练LOSS与ACC曲线

第一步：

 # define the function
 def training_vis(hist):
     loss = hist.history['loss']
     val_loss = hist.history['val_loss']
     acc = hist.history['acc']
     val_acc = hist.history['val_acc']

     # make a figure
     fig = plt.figure(figsize=(8,4))
     # subplot loss
     ax1 = fig.add_subplot(121)
     ax1.plot(loss,label='train_loss')
     ax1.plot(val_loss,label='val_loss')
     ax1.set_xlabel('Epochs')
     ax1.set_ylabel('Loss')
     ax1.set_title('Loss on Training and Validation Data')
     ax1.legend()
     # subplot acc
     ax2 = fig.add_subplot(122)
     ax2.plot(acc,label='train_acc')
     ax2.plot(val_acc,label='val_acc')
     ax2.set_xlabel('Epochs')
     ax2.set_ylabel('Accuracy')
     ax2.set_title('Accuracy  on Training and Validation Data')
     ax2.legend()
     plt.tight_layout()

第二步：

 # train the model
 hist = model.fit(...)

第三步：

 # call the function
 training_vis(hist)