How to plot multiple models val and traing acc/loss curve from csv files?

Question

I trained multiple CNN models, after that, I saved models details (Like , training/Validation Acc/Loss ) by callbacks by using this codes :

tf.keras.callbacks.CSVLogger 

Now I have multiple models training-val acc-loss respective values in different csv files.
I want to plots those in one figure from my csv files. How can I do this?

Answer 1

Here are the steps I solve my problem:

• Save Statistical records (Training-Validation Accuraciers, Training-Validation Recall, Training-Validation Precisions, Training-Validation F1) from CSV files of this following code tf.keras.callbacks.CSVLogger after training each fold (I trained for the 3 Folds).

• And load those csv files in the list:
      import pandas as pd
    l = ["/Records_of_Fold_2.csv" , "/Records_of_Fold_3.csv"]
  

• After that, Plot using matplotlib :

  for (k,i) in enumerate(l):
  data = pd.read_csv(i)
  plt.figure(str(k))
  plt.xlabel("x"+str(k))
  plt.ylabel("y"+str(k))
  plt.plot(data["epoch"],data["f1_score"])
  plt.plot(data["epoch"],data["loss"])
  print(k)
  plt.show()