Modification of scorings scripts

egs/iemocap/local/scoring.py

 import torch
 from tqdm import tqdm
 import os
+import re
 import seaborn as sns
 import pandas as pd
 import numpy as np
@@ -163,12 +164,15 @@ if model_type == "custom":
     loss_epoch = [line for line in file if "Epoch" in line]
     #loss_epoch = loss_epoch[::2] # 2 because only 1 gpu used: if more gpus are used, you have to do 2*nb_gpus
     loss_epoch = [line for line in loss_epoch if "[1/" in line]
+elif model_type == "half_resnet34":
+    loss_epoch = [line for line in file if "Epoch" in line][1:]
 else:
     loss_epoch = [line for line in file if "Epoch" in line]
 
-reduce_lr = [line for line in file if "reducing" in line]  # Can be empty
+reduce_lr_list = [line for line in file if "reducing" in line]  # Can be empty
 
 vloss = []  # Validation losses
+vacc = [] # Validation accuracy
 tloss = []  # Training losses
 aepoch = []  # Number of epochs
 
@@ -176,13 +180,14 @@ for linev, linel in zip(valid_loss, loss_epoch):
     linel = linel.split(":")
     linev = linev.split("=")
     vloss.append(round(float(linev[3].replace("\n", "").replace(" ", "")), 2))
+    vacc.append(round(float(linev[1].split("%")[0].replace(" ","")),2))
     aepoch.append(linel[3].split(" ")[1])
     tloss.append(round(float(linel[4].split("\t")[0].replace(" ", "")), 2))
-assert len(aepoch) == len(tloss) == len(vloss)
+assert len(aepoch) == len(tloss) == len(vloss) == len(vacc)
 
-print("--------------")
-for e, t, v in zip(aepoch, tloss, vloss):
-    print("Epoch:", e, "\ttrain loss:", t, "\tvalid loss:", v)
+print("--------------\n")
+for e, t, v ,a in zip(aepoch, tloss, vloss, vacc):
+    print("Epoch:", e, "\ttrain loss:", t, "\tvalid loss:", v, "\tvalid acc.:", a)
 
 ### Plotting of confusion matrix and losses ###
 if model_type == "custom":
@@ -209,21 +214,37 @@ plt.clf()
 print("\nConfusion matrix done!")
 
 # Plot losses
-ticks = [nb for nb in range(0, 9)]
-eticks = [nb for nb in range(0, len(aepoch), 5)]
-plt.plot(aepoch, tloss, label="Training loss")
-plt.plot(aepoch, vloss, label="Validation loss")
-plt.yticks(ticks)
-plt.xticks(eticks)
-
-if len(reduce_lr) != 0:
-    colors = ["b", "g", "y", "c", "m", "r"]
+fig, ax = plt.subplots()
+twin = ax.twinx() # Add a 3rd axis on the right
+
+plot_tl, = ax.plot(tloss, label="Training loss")
+plot_vl, = ax.plot(vloss, label="Validation loss")
+plot_vac, = twin.plot(vacc, "g-.",  label="Validation accuracy")
+
+handles = [plot_tl, plot_vl, plot_vac]
+
+ax.set_xlabel("Epochs")
+ax.set_ylabel("CrossEntropyLoss()")
+twin.set_ylabel("Validation accuracy (%)")
+
+ax.tick_params(axis='x', length=len(aepoch), width=5)
+ax.tick_params(axis='y', length=8)
+twin.set_ylim(0, 100)
+
+if len(reduce_lr_list) != 0:
+    reduce_lr_list = [re.sub(r"\s+", " ", elmt) for elmt in reduce_lr_list]
+    reduce_lr_list = [elmt.split(" ") for elmt in reduce_lr_list]
+    reduce_lr_list = {elmt[1][:-1] : elmt[-1][:-1]for elmt in reduce_lr_list}
+
+    colors = ["b", "m", "y", "c", "g", "r"]
     i = 0
     for key, value in reduce_lr.items():
         label = "lr: " + str(value)
-        plt.axvline(x=key, color=colors[i], linestyle='--', label=label)
+        handles.append(plt.axvline(x=key, color=colors[i], linestyle='--', label=label))
         i += 1
-plt.legend()
+
+ax.legend(handles=handles)
+
 plt.title("Model: {}{}{}_{}emo_{}batch\nEpoch: {}  lr: {}  Data: Test-IEMOCAP {}".format(model_type, model_2nd, freeze, cates, nb_batch, aepoch[-1], lr, ses_nb))
 plt.savefig(os.path.join(path, "losses_{}{}{}_{}emo_{}batch_epoch-{}_lr-{}_Test-IEMOCAP{}.png".format(model_type, model_2nd, freeze, cates, nb_batch, aepoch[-1], lr, ses_nb)))
 plt.show()

egs/iemocap/local/scoring_cross_validation.py

@@ -39,7 +39,7 @@ else:
 
 # Path to save the confusion matrix for cross-validation
 if model_type == "custom":                                                                               
-    path = "model_{}/Sess_all_cross-valid/{}/{}emo_{}batch_lr-{}{}".format(model_type, ses_nb, model_2nd[1:] ,cates, nb_batch, lr, freeze)
+    path = "model_{}/Sess_all_cross-valid/{}/{}emo_{}batch_lr-{}{}".format(model_type, model_2nd[1:] ,cates, nb_batch, lr, freeze)
 
     if not os.path.isdir(path.rsplit("/", 2)[0]):
         os.mkdir(path.rsplit("/", 2)[0])
@@ -97,7 +97,10 @@ for i in range(1, 6):
     print("Session {} is processing...".format(i))
 
     # 1st is the model, 2nd is the weights and all
-    xtract, config = load_model("model_{}/Sess{}_test/{}emo_{}batch_lr-{}{}/best_{}{}_{}emo_{}batch_lr-{}_Test-IEMOCAP{}.pt".format(model_type, i, cates, nb_batch, lr, freeze, model_type, freeze, cates, nb_batch, lr, i), "cuda")
+    if model_type == "custom":
+        xtract, config = load_model("model_{}/Sess{}_test/{}/{}emo_{}batch_lr-{}{}/best_{}{}{}_{}emo_{}batch_lr-{}_Test-IEMOCAP{}.pt".format(model_type, i, model_2nd[1:], cates, nb_batch, lr, freeze, model_type, model_2nd, freeze, cates, nb_batch, lr, i), "cuda")
+    else:
+        xtract, config = load_model("model_{}/Sess{}_test/{}emo_{}batch_lr-{}{}/best_{}{}_{}emo_{}batch_lr-{}_Test-IEMOCAP{}.pt".format(model_type, i, cates, nb_batch, lr, freeze, model_type, freeze, cates, nb_batch, lr, i), "cuda")
 
     path_wav = "data/IEMOCAP/Session{}/sentences/wav".format(i)