cm.py

# class_labels should contain names of both the classes
def plot_confusion_matrix(y_true,y_pred,class_labels):
    cm = np.zeros((2,2))
    cm[0,0] = np.sum((y_true==1) & (y_pred>0.5)) #TP
    cm[0,1] = np.sum((y_true==0) & (y_pred>0.5)) #FP
    cm[1,0] = np.sum((y_true==1) & (y_pred<0.5)) #FN
    cm[1,1] = np.sum((y_true==0) & (y_pred<0.5)) #TN
    cm_sum = np.sum(cm, axis=1, keepdims=True)
    cm_perc = cm / cm_sum.astype(float) * 100
    annot = np.empty_like(cm).astype(str)
    nrows, ncols = cm.shape
    for i in range(nrows):
        for j in range(ncols):
            c = cm[i, j]
            p = cm_perc[i, j]
            if i == j:
                s = cm_sum[i]
                annot[i, j] = '%.1f%%\n%d/%d' % (p, c, s)
            elif c == 0:
                annot[i, j] = ''
            else:
                annot[i, j] = '%.1f%%\n%d' % (p, c)
    
    if class_labels==None:
        class_labels = ['1','0']
    cm = pd.DataFrame(cm, index=class_labels, columns=class_labels)
    cm.index.name = 'Actual'
    cm.columns.name = 'Predicted'
    fig, ax = plt.subplots(figsize=(6,6))
    sns.set(font_scale=3.0) # Adjust to fit
    sns.heatmap(cm, cmap= "YlGnBu", annot=annot, fmt='', ax=ax)
    ax.tick_params(axis='both', which='major', labelsize=10)  # Adjust to fit
    ax.xaxis.set_ticklabels(class_labels)
    ax.yaxis.set_ticklabels(class_labels)
    fig.savefig('Confusion_Matrix.png')
    plt.show()

cmcall.py

#Given y as one-hot vector and pred as logits
plot_confusion_matrix(np.where(y==1)[1],np.argmax(pred,axis=1),class_labels)