Python Deep Learning Projects

Testing the model

With the model trained, evaluate the model on test data, as in the following:

loss,acc = model.evaluate(test_data, test_label)print('Loss :', loss)print('Accuracy :', acc)

This should be the output:

97/97 [==============================] - 7s 71ms/step
Loss : 0.5390811630131043
Accuracy : 0.7633129960482883

We see that the SegNet model we built has a loss of 0.539 and accuracy of 76.33 on test images.

Let's plot the test images and their corresponding generated segmentations to understand model learning:

for i in range(3):    plt.figure(figsize = (10,3))    plt.subplot(1,2,1)    plt.imshow(img_lst[1900+i])    plt.title('Input')    plt.subplot(1,2,2)    plt.imshow(model.predict_classes(test_data[i:(i+1)*1]).reshape(360,480)) plt.title('Segmentation') ...