zalando-tutorial.ipynb 23.1 KB
Newer Older
Nane Kratzke's avatar
Nane Kratzke committed
1
2
3
4
5
6
7
8
9
10
11
12
13
{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "4d709f6a-b9a1-4824-8fb8-cd64e8956c0a",
   "metadata": {},
   "source": [
    "# Basic classification using the Zalando Dataset: Classify images of clothing\n",
    "\n",
    "This guide trains a neural network model to classify images of clothing, like sneakers and shirts. It's okay if you don't understand all the details; this is a fast-paced overview of a complete TensorFlow program with the details explained as you go.\n",
    "\n",
    "This guide uses [tf.keras](https://www.tensorflow.org/guide/keras), a high-level API to build and train models in TensorFlow.\n",
    "\n",
Nane Kratzke's avatar
Nane Kratzke committed
14
    "**To follow this tutorial simply step interactively through the notebook cells using the ► button**. "
Nane Kratzke's avatar
Nane Kratzke committed
15
16
17
18
   ]
  },
  {
   "cell_type": "code",
Nane Kratzke's avatar
Nane Kratzke committed
19
   "execution_count": null,
Nane Kratzke's avatar
Nane Kratzke committed
20
21
   "id": "e66f6149-1a05-447a-9098-526ee537344c",
   "metadata": {},
Nane Kratzke's avatar
Nane Kratzke committed
22
   "outputs": [],
Nane Kratzke's avatar
Nane Kratzke committed
23
   "source": [
Nane Kratzke's avatar
Nane Kratzke committed
24
25
26
27
28
29
30
31
32
33
34
35
36
    "# Preliminary checks to import Tensorflow\n",
    "import os, sys\n",
    "if 'tensorflow' not in os.environ.get('JUPYTER_IMAGE').lower():\n",
    "    print(\"Error: You need a tensorflow image to run this notebook!\", file=sys.stderr)\n",
    "else:    \n",
    "    # TensorFlow and tf.keras\n",
    "    import tensorflow as tf\n",
    "\n",
    "    # Helper libraries\n",
    "    import numpy as np\n",
    "    import matplotlib.pyplot as plt\n",
    "\n",
    "    print(f\"Great, your Tensorflow Version is {tf.__version__}\")"
Nane Kratzke's avatar
Nane Kratzke committed
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
   ]
  },
  {
   "cell_type": "markdown",
   "id": "240e43d6-5e5b-451f-9f8f-e9383270479c",
   "metadata": {},
   "source": [
    "## Import the Fashion MNIST dataset\n",
    "\n",
    "This guide uses the Fashion [MNIST dataset](https://github.com/zalandoresearch/fashion-mnist) which contains 70,000 grayscale images in 10 categories. The images show individual articles of clothing at low resolution (28 by 28 pixels), as seen here:\n",
    "\n",
    "![Fashion Dataset](https://tensorflow.org/images/fashion-mnist-sprite.png)\n",
    "\n",
    "Fashion MNIST is intended as a drop-in replacement for the classic [MNIST](http://yann.lecun.com/exdb/mnist/) dataset—often used as the \"Hello, World\" of machine learning programs for computer vision. The MNIST dataset contains images of handwritten digits (0, 1, 2, etc.) in a format identical to that of the articles of clothing you'll use here.\n",
    "\n",
    "This guide uses Fashion MNIST for variety, and because it's a slightly more challenging problem than regular MNIST. Both datasets are relatively small and are used to verify that an algorithm works as expected. They're good starting points to test and debug code.\n",
    "\n",
    "Here, 60,000 images are used to train the network and 10,000 images to evaluate how accurately the network learned to classify images. You can access the Fashion MNIST directly from TensorFlow. **Import and load the Fashion MNIST data directly from TensorFlow:**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0c8dd540-4689-4626-8611-ba85fdfb0af4",
   "metadata": {},
   "outputs": [],
   "source": [
    "fashion_mnist = tf.keras.datasets.fashion_mnist\n",
    "\n",
    "(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "816889a8-c680-48d6-800d-08d349d3f7b6",
   "metadata": {},
   "source": [
    "Loading the dataset returns four NumPy arrays:\n",
    "\n",
    "- The `train_images` and `train_labels` arrays are the training set—the data the model uses to learn.\n",
    "- The model is tested against the test set, the `test_images`, and `test_labels` arrays.\n",
    "- The images are 28x28 NumPy arrays, with pixel values ranging from 0 to 255. The labels are an array of integers, ranging from 0 to 9.\n",
    "\n",
    "These correspond to the class of clothing the image represents:\n",
    "\n",
    "| Label | Class |\n",
    "| ----- | ----- |\n",
    "| 0 | T-shirt/top |\n",
    "| 1 | Trouser |\n",
    "| 2 | Pullover |\n",
    "| 3 | Dress |\n",
    "| 4 | Coat |\n",
    "| 5 | Sandal |\n",
    "| 6 | Shirt |\n",
    "| 7 | Sneaker |\n",
    "| 8 | Bag |\n",
    "| 9 | Ankle boot |\n",
    "\n",
    "Each image is mapped to a single label. Since the class names are not included with the dataset, store them here to use later when plotting the images:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "00a6ed38-ea17-4d3d-a745-7e1fa1507ea6",
   "metadata": {},
   "outputs": [],
   "source": [
    "class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat', 'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "867fb3cd-5e7f-4200-8a51-2488865af797",
   "metadata": {},
   "source": [
    "## Explore the data\n",
    "\n",
    "Let's explore the format of the dataset before training the model. The following shows there are 60,000 images in the training set, with each image represented as 28 x 28 pixels:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "de6edb3a-88f6-4e1a-907e-d794cefea2f8",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_images.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b628c5e0-f81c-41fa-811c-a5d7e827d8f4",
   "metadata": {},
   "source": [
    "Likewise, there are 60,000 labels in the training set:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0edbb781-102d-4431-9f17-c450f4666a45",
   "metadata": {},
   "outputs": [],
   "source": [
    "len(train_labels)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e6e60a8e-814d-41f8-a643-e032aacf413a",
   "metadata": {},
   "source": [
    "Each label is an integer between 0 and 9:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "883d6001-7848-4a0f-a29c-a564bebb7a79",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_labels"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dd47595b-f4d3-406b-9f7c-de4f01c4d5cc",
   "metadata": {},
   "source": [
    "And the test set contains 10,000 images labels:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a1eeb5ac-208e-4998-a986-8f23dc9521e1",
   "metadata": {},
   "outputs": [],
   "source": [
    "len(test_labels)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "eb9d279b-92d2-4e5c-b624-79ece636828a",
   "metadata": {},
   "source": [
    "## Preprocess the data\n",
    "\n",
    "The data must be preprocessed before training the network. If you inspect the first image in the training set, you will see that the pixel values fall in the range of 0 to 255:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "76f43538-99de-4677-81a5-730c0cf6b52c",
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.figure()\n",
    "plt.imshow(train_images[0])\n",
    "plt.colorbar()\n",
    "plt.grid(False)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "31c47da5-f74a-4316-a567-dbd95573f382",
   "metadata": {},
   "source": [
    "Scale these values to a range of 0 to 1 before feeding them to the neural network model. To do so, divide the values by 255. It's important that the training set and the testing set be preprocessed in the same way:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0aa57ac1-5651-4212-bc1a-c1c489ccdfd9",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_images = train_images / 255.0\n",
    "test_images = test_images / 255.0"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f081f6ef-908f-4877-89f6-7513fc0ec2a9",
   "metadata": {},
   "source": [
    "To verify that the data is in the correct format and that you're ready to build and train the network, let's display the first 25 images from the training set and display the class name below each image."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3b9370ea-bbd6-4534-8157-4b865a39c3b0",
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.figure(figsize=(10,10))\n",
    "for i in range(25):\n",
    "    plt.subplot(5,5,i+1)\n",
    "    plt.xticks([])\n",
    "    plt.yticks([])\n",
    "    plt.grid(False)\n",
    "    plt.imshow(train_images[i], cmap=plt.cm.binary)\n",
    "    plt.xlabel(class_names[train_labels[i]])\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3be87ee6-a76c-478f-b1b6-b112fe6516d0",
   "metadata": {},
   "source": [
    "## Build the model\n",
    "\n",
    "Building the neural network requires configuring the layers of the model, then compiling the model.\n",
    "\n",
    "### Set up the layers\n",
    "\n",
    "The basic building block of a neural network is the [layer](https://www.tensorflow.org/api_docs/python/tf/keras/layers). Layers extract representations from the data fed into them. Hopefully, these representations are meaningful for the problem at hand.\n",
    "\n",
    "Most of deep learning consists of chaining together simple layers. Most layers, such as [tf.keras.layers.Dense](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Dense), have parameters that are learned during training."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "209b0486-3c73-429d-a827-027c243e4157",
   "metadata": {},
   "outputs": [],
   "source": [
    "model = tf.keras.Sequential([\n",
    "    tf.keras.layers.Flatten(input_shape=(28, 28)),\n",
    "    tf.keras.layers.Dense(128, activation='relu'),\n",
    "    tf.keras.layers.Dense(10)\n",
    "])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0cecd604-5b53-4702-87d1-2b26dedae19c",
   "metadata": {},
   "source": [
    "The first layer in this network, [tf.keras.layers.Flatten](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Flatten), transforms the format of the images from a two-dimensional array (of 28 by 28 pixels) to a one-dimensional array (of 28 * 28 = 784 pixels). Think of this layer as unstacking rows of pixels in the image and lining them up. This layer has no parameters to learn; it only reformats the data.\n",
    "\n",
    "After the pixels are flattened, the network consists of a sequence of [two tf.keras.layers.Dense](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Dense) layers. These are densely connected, or fully connected, neural layers. The first Dense layer has 128 nodes (or neurons). The second (and last) layer returns a logits array with length of 10. Each node contains a score that indicates the current image belongs to one of the 10 classes.\n",
    "\n",
    "### Compile the model\n",
    "\n",
    "Before the model is ready for training, it needs a few more settings. These are added during the model's compile step:\n",
    "\n",
    "- [Loss function](https://www.tensorflow.org/api_docs/python/tf/keras/losses) — This measures how accurate the model is during training. You want to minimize this function to \"steer\" the model in the right direction.\n",
    "- [Optimizer](https://www.tensorflow.org/api_docs/python/tf/keras/optimizers) — This is how the model is updated based on the data it sees and its loss function.\n",
    "- [Metrics](https://www.tensorflow.org/api_docs/python/tf/keras/metrics) — Used to monitor the training and testing steps. The following example uses accuracy, the fraction of the images that are correctly classified."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3736e82e-1de8-477b-8c44-4c4bf9100a7b",
   "metadata": {},
   "outputs": [],
   "source": [
    "model.compile(optimizer='adam',\n",
    "    loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n",
    "    metrics=['accuracy']\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fca063a0-325c-4857-a988-ba48fc7128c7",
   "metadata": {},
   "source": [
    "## Train the model\n",
    "\n",
    "Training the neural network model requires the following steps:\n",
    "\n",
    "1. Feed the training data to the model. In this example, the training data is in the `train_images` and `train_labels` arrays.\n",
    "2. The model learns to associate images and labels.\n",
    "3. You ask the model to make predictions about a test set—in this example, the `test_images` array.\n",
    "4. Verify that the predictions match the labels from the `test_labels` array.\n",
    "\n",
    "### Feed the model\n",
    "\n",
    "To start training, call the [model.fit](https://www.tensorflow.org/api_docs/python/tf/keras/Model#fit) method—so called because it \"fits\" the model to the training data:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d3c6f740-c1ea-43de-912a-bed799cd58a0",
   "metadata": {},
   "outputs": [],
   "source": [
    "model.fit(train_images, train_labels, epochs=10)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ccead956-9389-4efd-900e-0f736597c8f1",
   "metadata": {},
   "source": [
    "As the model trains, the loss and accuracy metrics are displayed. This model reaches an accuracy of about 0.91 (or 91%) on the training data.\n",
    "\n",
    "### Evaluate accuracy\n",
    "\n",
    "Next, compare how the model performs on the test dataset:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "889c817e-3690-4fba-b155-1575146b0ab9",
   "metadata": {},
   "outputs": [],
   "source": [
    "test_loss, test_acc = model.evaluate(test_images,  test_labels, verbose=2)\n",
    "\n",
    "print('\\nTest accuracy:', test_acc)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b8fc59c9-c04f-4a32-be26-327fafa7eec5",
   "metadata": {},
   "source": [
    "It turns out that the accuracy on the test dataset is a little less than the accuracy on the training dataset. This gap between training accuracy and test accuracy represents overfitting. Overfitting happens when a machine learning model performs worse on new, previously unseen inputs than it does on the training data. An overfitted model \"memorizes\" the noise and details in the training dataset to a point where it negatively impacts the performance of the model on the new data. For more information, see the following:\n",
    "\n",
    "- [Demonstrate overfitting](https://www.tensorflow.org/tutorials/keras/overfit_and_underfit#demonstrate_overfitting)\n",
    "- [Strategies to prevent overfitting](https://www.tensorflow.org/tutorials/keras/overfit_and_underfit#strategies_to_prevent_overfitting)\n",
    "\n",
    "### Make predictions\n",
    "\n",
    "With the model trained, you can use it to make predictions about some images. The model's linear outputs, [logits](https://developers.google.com/machine-learning/glossary#logits). Attach a softmax layer to convert the logits to probabilities, which are easier to interpret."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6ea82cf4-a25e-4a0c-a634-471bc2816982",
   "metadata": {},
   "outputs": [],
   "source": [
    "probability_model = tf.keras.Sequential([model, tf.keras.layers.Softmax()])\n",
    "predictions = probability_model.predict(test_images)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cddb5534-9075-4aff-9f5f-1257e69d6a6d",
   "metadata": {},
   "source": [
    "Here, the model has predicted the label for each image in the testing set. Let's take a look at the first prediction:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "133f56fb-d423-4177-8a68-d2c0c31ed798",
   "metadata": {},
   "outputs": [],
   "source": [
    "predictions[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f269ae56-58ff-4238-8b3b-e314b61bc163",
   "metadata": {},
   "source": [
    "A prediction is an array of 10 numbers. They represent the model's \"confidence\" that the image corresponds to each of the 10 different articles of clothing. You can see which label has the highest confidence value:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "36082941-693e-4f61-9112-c51019dcbee8",
   "metadata": {},
   "outputs": [],
   "source": [
    "np.argmax(predictions[0])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d8bd872e-b82c-474e-b397-3d78e6621acc",
   "metadata": {},
   "source": [
    "So, the model is most confident that this image is an ankle boot, or `class_names[9]`. Examining the test label shows that this classification is correct:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "07e27687-b06b-42fe-ab0b-d9430f6d79af",
   "metadata": {},
   "outputs": [],
   "source": [
    "test_labels[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e2ba5393-69c1-4970-93a9-9cebd7052a97",
   "metadata": {},
   "source": [
    "Graph this to look at the full set of 10 class predictions."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "00b20016-d87b-4e63-884b-dcc8c2d3176f",
   "metadata": {},
   "outputs": [],
   "source": [
    "def plot_image(i, predictions_array, true_label, img):\n",
    "  true_label, img = true_label[i], img[i]\n",
    "  plt.grid(False)\n",
    "  plt.xticks([])\n",
    "  plt.yticks([])\n",
    "\n",
    "  plt.imshow(img, cmap=plt.cm.binary)\n",
    "\n",
    "  predicted_label = np.argmax(predictions_array)\n",
    "  if predicted_label == true_label:\n",
    "    color = 'blue'\n",
    "  else:\n",
    "    color = 'red'\n",
    "\n",
    "  plt.xlabel(\"{} {:2.0f}% ({})\".format(class_names[predicted_label],\n",
    "                                100*np.max(predictions_array),\n",
    "                                class_names[true_label]),\n",
    "                                color=color)\n",
    "\n",
    "def plot_value_array(i, predictions_array, true_label):\n",
    "  true_label = true_label[i]\n",
    "  plt.grid(False)\n",
    "  plt.xticks(range(10))\n",
    "  plt.yticks([])\n",
    "  thisplot = plt.bar(range(10), predictions_array, color=\"#777777\")\n",
    "  plt.ylim([0, 1])\n",
    "  predicted_label = np.argmax(predictions_array)\n",
    "\n",
    "  thisplot[predicted_label].set_color('red')\n",
    "  thisplot[true_label].set_color('blue')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3b4a3504-1298-4ff0-9a91-763dc4997bb0",
   "metadata": {},
   "source": [
    "### Verify predictions\n",
    "\n",
    "With the model trained, you can use it to make predictions about some images.\n",
    "\n",
    "Let's look at the 0th image, predictions, and prediction array. Correct prediction labels are blue and incorrect prediction labels are red. The number gives the percentage (out of 100) for the predicted label."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8ad7c1ab-7b7b-4674-9909-433721060870",
   "metadata": {},
   "outputs": [],
   "source": [
    "i = 0\n",
    "plt.figure(figsize=(6,3))\n",
    "plt.subplot(1,2,1)\n",
    "plot_image(i, predictions[i], test_labels, test_images)\n",
    "plt.subplot(1,2,2)\n",
    "plot_value_array(i, predictions[i],  test_labels)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e94e37f6-15b8-4426-9221-78784ca119d8",
   "metadata": {},
   "outputs": [],
   "source": [
    "i = 12\n",
    "plt.figure(figsize=(6,3))\n",
    "plt.subplot(1,2,1)\n",
    "plot_image(i, predictions[i], test_labels, test_images)\n",
    "plt.subplot(1,2,2)\n",
    "plot_value_array(i, predictions[i],  test_labels)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "95d4a145-1f2e-4ec7-8b1f-b5db1124211e",
   "metadata": {},
   "source": [
    "Let's plot several images with their predictions. Note that the model can be wrong even when very confident."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "143c82ab-2d72-43ec-91ba-a6cd96e6700d",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Plot the first X test images, their predicted labels, and the true labels.\n",
    "# Color correct predictions in blue and incorrect predictions in red.\n",
    "num_rows = 5\n",
    "num_cols = 3\n",
    "num_images = num_rows*num_cols\n",
    "plt.figure(figsize=(2*2*num_cols, 2*num_rows))\n",
    "for i in range(num_images):\n",
    "  plt.subplot(num_rows, 2*num_cols, 2*i+1)\n",
    "  plot_image(i, predictions[i], test_labels, test_images)\n",
    "  plt.subplot(num_rows, 2*num_cols, 2*i+2)\n",
    "  plot_value_array(i, predictions[i], test_labels)\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1dda2d9e-e389-417b-98d8-5ebf3cfe5ae0",
   "metadata": {},
   "source": [
    "## Use the trained model\n",
    "\n",
    "Finally, use the trained model to make a prediction about a single image."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "dd526bca-2702-4db6-bff9-6a516cd26253",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Grab an image from the test dataset.\n",
    "img = test_images[7]\n",
    "plt.figure()\n",
    "plt.imshow(img)\n",
    "plt.colorbar()\n",
    "plt.grid(False)\n",
    "plt.show()\n",
    "print(img.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f71ad288-5142-4585-809e-0306023ea40a",
   "metadata": {},
   "source": [
    "[tf.keras](https://www.tensorflow.org/api_docs/python/tf/keras) models are optimized to make predictions on a batch, or collection, of examples at once. Accordingly, even though you're using a single image, you need to add it to a list:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4000f224-98a2-4187-bf59-1bda7bc79ec0",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Add the image to a batch where it's the only member.\n",
    "img = (np.expand_dims(img,0))\n",
    "\n",
    "print(img.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9e44a542-866c-420d-b7a0-538359158e9f",
   "metadata": {},
   "source": [
    "Now predict the correct label for this image:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "548678d8-8e2b-4fd5-8038-0f1d2fc7337c",
   "metadata": {},
   "outputs": [],
   "source": [
    "predictions_single = probability_model.predict(img)\n",
    "\n",
    "print(predictions_single)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5c597d1b-c328-4b0c-8988-3f727fa3caa7",
   "metadata": {},
   "outputs": [],
   "source": [
    "plot_value_array(1, predictions_single[0], test_labels)\n",
    "_ = plt.xticks(range(10), class_names, rotation=45)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "885e997f-f073-413d-8e8f-756a646a276e",
   "metadata": {},
   "source": [
    "[tf.keras.Model.predict](https://www.tensorflow.org/api_docs/python/tf/keras/Model#predict) returns a list of lists—one list for each image in the batch of data. Grab the predictions for our (only) image in the batch:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cd887d2d-cd3f-4caf-a8c2-800e6dada870",
   "metadata": {},
   "outputs": [],
   "source": [
    "np.argmax(predictions_single[0])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f9a55cdf-7518-4332-bfb1-5fc9c785f4ad",
   "metadata": {},
   "source": [
    "And the model predicts a label as expected."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}