Simple Image Classification With TensorFlow

A Neural Network Image Classifier With is what we learn in this video. We use the Fashion MNIST data set. If you are getting into Machine Learning this is a awesome tutorial for you because this is one of the simplest tutorials and it is very visual with is great for beginners.
I hope you guys like it! Please like, subscribe and turn on notifications. and make sure to check out my other videos!

[codingwithbobby]

This is all the code I just copied into the video:

7:23
plt.figure(figsize=(10, 10))
for i in range(25):
plt.subplot(5, 5, i+1)
plt.xticks([])
plt.yticks([])
plt.grid(False)
plt.imshow(train_images[i], cmap=plt.cm.binary)

plt.show()




21:33
def plot_image(i, predictions_array, true_label, img):
predictions_array, true_label, img = predictions_array, true_label[i], img[i]
plt.grid(False)
plt.xticks([])
plt.yticks([])

plt.imshow(img, cmap=plt.cm.binary)

predicted_label = np.argmax(predictions_array)
if predicted_label == true_label:
color = 'blue'
else:
color = 'red'

plt.xlabel("{} {:2.0f}% ({})".format(class_names[predicted_label],




def plot_value_array(i, predictions_array, true_label):
predictions_array, true_label = predictions_array, true_label[i]
plt.grid(False)
plt.xticks(range(10))
plt.yticks([])
thisplot = plt.bar(range(10), predictions_array,
plt.ylim([0, 1])
predicted_label = np.argmax(predictions_array)





22:00
i = 0 #we set the variable i to zero
plt.figure(figsize=(6, 3)) #create a figure object
plt.subplot(1, 2, 1) #subbplot is used to plot two or plots in one figure
plot_image(i, predictions[i], test_labels, test_images) #plotting the 0th index image, showsing our prediciton, test_labels, and test_images
plt.subplot(1, 2, 2)
plot_value_array(i, predictions[i], test_labels)
plt.show()



24:51

num_rows = 5
num_cols = 3
num_images = num_rows*num_cols
plt.figure(figsize=(2*2*num_cols, 2*num_rows))
for i in range(num_images):
plt.subplot(num_rows, 2*num_cols, 2*i+1)
plot_image(i, predictions[i], test_labels, test_images)
plt.subplot(num_rows, 2*num_cols, 2*i+2)
plot_value_array(i, predictions[i], test_labels)
plt.tight_layout()
plt.show()