收集一些训练可视化与结果可视化的代码。

利用plt调用history绘图

1
2
3
4
5
6
7
8
9
10
11
12
13
14
# ref: https://www.kaggle.com/uysimty/keras-cnn-dog-or-cat-classification/notebook
fig, (ax1, ax2) = plt.subplots(2, 1, figsize=(12, 12))
ax1.plot(history.history['loss'], color='b', label="Training loss")
ax1.plot(history.history['val_loss'], color='r', label="validation loss")
ax1.set_xticks(np.arange(1, epochs, 1))
ax1.set_yticks(np.arange(0, 1, 0.1))

ax2.plot(history.history['acc'], color='b', label="Training accuracy")
ax2.plot(history.history['val_acc'], color='r',label="Validation accuracy")
ax2.set_xticks(np.arange(1, epochs, 1))

legend = plt.legend(loc='best', shadow=True)
plt.tight_layout()
plt.show()

查看预测结果

1
2
3
4
5
6
7
8
9
10
11
12
13
14
# ref: https://www.kaggle.com/uysimty/keras-cnn-dog-or-cat-classification/notebook
sample_test = test_df.head(18)
sample_test.head()
plt.figure(figsize=(12, 24))
for index, row in sample_test.iterrows():
    filename = row['filename']
    category = row['category']
    probability = row['probability']
    img = load_img("../input/test1/test1/"+filename, target_size=IMAGE_SIZE)
    plt.subplot(6, 3, index+1)
    plt.imshow(img)
    plt.xlabel(filename + '(' + "{}".format(category) + ')' '(' + "{}".format(round(probability, 2)) + ')')
plt.tight_layout()
plt.show()

仿照该段代码对图片进行显示，运行成功。需要注意的是：

  • iterrows方法是用于pd.DataFrame上，因此需要对生成的数组进行格式转换。
  • 在循环体中，subplot指令运行一直出错，发现index是tuple，使用时需要将其内容取出使用。
1
2
3
4
5
6
7
8
9
10
11
img=test[0:16,:,:,0]
img.shape
b=pd.DataFrame(np.arange(16)+1)
print(b)
for index in b.iterrows():
    num=index[0]+1
    subimg=img[num-1]
    plt.subplot(4, 4, num)
    plt.imshow(subimg)
plt.tight_layout()
plt.show()

查看混淆矩阵

使用plt

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
# Look at confusion matrix 

def plot_confusion_matrix(cm, classes,
                          normalize=False,
                          title='Confusion matrix',
                          cmap=plt.cm.Blues):
    """
    This function prints and plots the confusion matrix.
    Normalization can be applied by setting `normalize=True`.
    """
    plt.imshow(cm, interpolation='nearest', cmap=cmap)
    plt.title(title)
    plt.colorbar()
    tick_marks = np.arange(len(classes))
    plt.xticks(tick_marks, classes, rotation=45)
    plt.yticks(tick_marks, classes)

    if normalize:
        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]

    thresh = cm.max() / 2.
    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
        plt.text(j, i, cm[i, j],
                 horizontalalignment="center",
                 color="white" if cm[i, j] > thresh else "black")

    plt.tight_layout()
    plt.ylabel('True label')
    plt.xlabel('Predicted label')

# Predict the values from the validation dataset
Y_pred = model.predict(X_val)
# Convert predictions classes to one hot vectors 
Y_pred_classes = np.argmax(Y_pred,axis = 1) 
# Convert validation observations to one hot vectors
Y_true = np.argmax(Y_val,axis = 1) 
# compute the confusion matrix 
confusion_mtx = confusion_matrix(Y_true, Y_pred_classes) # sklearn
# plot the confusion matrix
plot_confusion_matrix(confusion_mtx, classes = range(10))

查看错误预测样本

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
# Display some error results 

# Errors are difference between predicted labels and true labels
errors = (Y_pred_classes - Y_true != 0)

Y_pred_classes_errors = Y_pred_classes[errors]
Y_pred_errors = Y_pred[errors]
Y_true_errors = Y_true[errors]
X_val_errors = X_val[errors]

def display_errors(errors_index,img_errors,pred_errors, obs_errors):
    """ This function shows 6 images with their predicted and real labels"""
    n = 0
    nrows = 2
    ncols = 3
    fig, ax = plt.subplots(nrows,ncols,sharex=True,sharey=True)
    for row in range(nrows):
        for col in range(ncols):
            error = errors_index[n]
            ax[row,col].imshow((img_errors[error]).reshape((28,28)))
            ax[row,col].set_title("Predicted label :{}\nTrue label :{}".format(pred_errors[error],obs_errors[error]))
            n += 1

# Probabilities of the wrong predicted numbers
Y_pred_errors_prob = np.max(Y_pred_errors,axis = 1)

# Predicted probabilities of the true values in the error set
true_prob_errors = np.diagonal(np.take(Y_pred_errors, Y_true_errors, axis=1))

# Difference between the probability of the predicted label and the true label
delta_pred_true_errors = Y_pred_errors_prob - true_prob_errors

# Sorted list of the delta prob errors
sorted_dela_errors = np.argsort(delta_pred_true_errors)

# Top 6 errors 
most_important_errors = sorted_dela_errors[-6:]

# Show the top 6 errors
display_errors(most_important_errors, X_val_errors, Y_pred_classes_errors, Y_true_errors)