機器學習中訓練和驗證指標曲線圖能告訴我們什么？

作者：deephub 2022-06-10 15:51:22

我們在訓練和驗證模型時都會將訓練指標保存成起來制作成圖表，這樣可以在結束后進行查看和分析，但是你真的了解這些指標的圖表的含義嗎？

在本文中將對訓練和驗證可能產生的情況進行總結并介紹這些圖表到底能為我們提供什么樣的信息。

讓我們從一些簡單的代碼開始以下代碼建立了一個基本的訓練流程框架。

from sklearn.model_selection import train_test_split
from sklearn.datasets import make_classification
import torch
from torch.utils.data import Dataset, DataLoader
import torch.optim as torch_optim
import torch.nn as nn
import torch.nn.functional as F
import numpy as np
import matplotlib.pyplot as pltclass MyCustomDataset(Dataset):
def __init__(self, X, Y, scale=False):
self.X = torch.from_numpy(X.astype(np.float32))
self.y = torch.from_numpy(Y.astype(np.int64))

def __len__(self):
return len(self.y)

def __getitem__(self, idx):
return self.X[idx], self.y[idx]def get_optimizer(model, lr=0.001, wd=0.0):
parameters = filter(lambda p: p.requires_grad, model.parameters())
optim = torch_optim.Adam(parameters, lr=lr, weight_decay=wd)
return optimdef train_model(model, optim, train_dl, loss_func):
# Ensure the model is in Training mode
model.train()
total = 0
sum_loss = 0
for x, y in train_dl:
batch = y.shape[0]
# Train the model for this batch worth of data
logits = model(x)
# Run the loss function. We will decide what this will be when we call our Training Loop
loss = loss_func(logits, y)
# The next 3 lines do all the PyTorch back propagation goodness
optim.zero_grad()
loss.backward()
optim.step()
# Keep a running check of our total number of samples in this epoch
total += batch
# And keep a running total of our loss
sum_loss += batch*(loss.item())
return sum_loss/total
def train_loop(model, train_dl, valid_dl, epochs, loss_func, lr=0.1, wd=0):
optim = get_optimizer(model, lr=lr, wd=wd)
train_loss_list = []
val_loss_list = []
acc_list = []
for i in range(epochs): 
loss = train_model(model, optim, train_dl, loss_func)
# After training this epoch, keep a list of progress of 
# the loss of each epoch 
train_loss_list.append(loss)
val, acc = val_loss(model, valid_dl, loss_func)
# Likewise for the validation loss and accuracy
val_loss_list.append(val)
acc_list.append(acc)
print("training loss: %.5f valid loss: %.5f accuracy: %.5f" % (loss, val, acc))

return train_loss_list, val_loss_list, acc_list
def val_loss(model, valid_dl, loss_func):
# Put the model into evaluation mode, not training mode
model.eval()
total = 0
sum_loss = 0
correct = 0
batch_count = 0
for x, y in valid_dl:
batch_count += 1
current_batch_size = y.shape[0]
logits = model(x)
loss = loss_func(logits, y)
sum_loss += current_batch_size*(loss.item())
total += current_batch_size
# All of the code above is the same, in essence, to
# Training, so see the comments there
# Find out which of the returned predictions is the loudest
# of them all, and that's our prediction(s)
preds = logits.sigmoid().argmax(1)
# See if our predictions are right
correct += (preds == y).float().mean().item()
return sum_loss/total, correct/batch_count
def view_results(train_loss_list, val_loss_list, acc_list):
plt.rcParams["figure.figsize"] = (15, 5)
plt.figure()
epochs = np.arange(0, len(train_loss_list)) plt.subplot(1, 2, 1)
plt.plot(epochs-0.5, train_loss_list)
plt.plot(epochs, val_loss_list)
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'val', 'acc'], loc = 'upper left')

plt.subplot(1, 2, 2)
plt.plot(acc_list)
plt.title('accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'val', 'acc'], loc = 'upper left')
plt.show()

def get_data_train_and_show(model, batch_size=128, n_samples=10000, n_classes=2, n_features=30, val_size=0.2, epochs=20, lr=0.1, wd=0, break_it=False):
# We'll make a fictitious dataset, assuming all relevant
# EDA / Feature Engineering has been done and this is our 
# resultant data
X, y = make_classification(n_samples=n_samples, n_classes=n_classes, n_features=n_features, n_informative=n_features, n_redundant=0, random_state=1972)

if break_it: # Specifically mess up the data
X = np.random.rand(n_samples,n_features)
X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=val_size, random_state=1972) train_ds = MyCustomDataset(X_train, y_train)
valid_ds = MyCustomDataset(X_val, y_val)
train_dl = DataLoader(train_ds, batch_size=batch_size, shuffle=True)
valid_dl = DataLoader(valid_ds, batch_size=batch_size, shuffle=True) train_loss_list, val_loss_list, acc_list = train_loop(model, train_dl, valid_dl, epochs=epochs, loss_func=F.cross_entropy, lr=lr, wd=wd)
view_results(train_loss_list, val_loss_list, acc_list)