How do I plot steps_per_epoch against loss using fit_generator in Keras?

Question

I have the following code and I would like to plot the graph of loss against steps_per_epoch

model = unet(pretrained=False)

model.compile(optimizer=Adam(0.005), loss="binary_crossentropy",
              metrics=["accuracy"])

history = model.fit_generator(train_gen, steps_per_epoch=500, epochs=5,
                              callbacks=[dynamic_lr, chkp])

where lr and chkp are my callbacks for the model:

def lr_scheduler(epoch, lr):
  if epoch <= 2:
    lr = 0.002
    return lr
  lr = 0.001  
  return lr   

chkp = keras.callbacks.ModelCheckpoint(
    filepath="mypath/model.hdf5",
    monitor="loss",
    verbose=1,
    save_best_only=True,
    mode="min",
)

dynamic_lr = LearningRateScheduler(lr_scheduler, verbose=1)  

I do not think the history dict holds the loss for each step in epoch, but is there any way?

Answer 1

you can get the values of training accuracy, training loss, validation accuracy and validation loss from the history object. See code below.

training_accuracy=history.history['accuracy']
training_loss=history.history['loss']
valid_accuracy=history.history['val_accuracy']
valid_loss=history.history['val_loss']