-
Notifications
You must be signed in to change notification settings - Fork 1
/
classifier.py
476 lines (343 loc) · 21.8 KB
/
classifier.py
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
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
#!/usr/bin/env python
# coding: utf-8
# # Developing an AI application
#
# Going forward, AI algorithms will be incorporated into more and more everyday applications. For example, you might want to include an image classifier in a smart phone app. To do this, you'd use a deep learning model trained on hundreds of thousands of images as part of the overall application architecture. A large part of software development in the future will be using these types of models as common parts of applications.
#
# In this project, you'll train an image classifier to recognize different species of flowers. You can imagine using something like this in a phone app that tells you the name of the flower your camera is looking at. In practice you'd train this classifier, then export it for use in your application. We'll be using [this dataset](http://www.robots.ox.ac.uk/~vgg/data/flowers/102/index.html) of 102 flower categories, you can see a few examples below.
#
# <img src='assets/Flowers.png' width=500px>
#
# The project is broken down into multiple steps:
#
# * Load and preprocess the image dataset
# * Train the image classifier on your dataset
# * Use the trained classifier to predict image content
#
# We'll lead you through each part which you'll implement in Python.
#
# When you've completed this project, you'll have an application that can be trained on any set of labeled images. Here your network will be learning about flowers and end up as a command line application. But, what you do with your new skills depends on your imagination and effort in building a dataset. For example, imagine an app where you take a picture of a car, it tells you what the make and model is, then looks up information about it. Go build your own dataset and make something new.
#
# First up is importing the packages you'll need. It's good practice to keep all the imports at the beginning of your code. As you work through this notebook and find you need to import a package, make sure to add the import up here.
# In[1]:
# Imports here
import torch
import torch.nn.functional as F
import numpy as np
import matplotlib.pyplot as plt
import time
from torch import nn
from torch import optim
from PIL import Image
from collections import OrderedDict
from torchvision import datasets, transforms, models
# ## Load the data
#
# Here you'll use `torchvision` to load the data ([documentation](http://pytorch.org/docs/0.3.0/torchvision/index.html)). The data should be included alongside this notebook, otherwise you can [download it here](https://s3.amazonaws.com/content.udacity-data.com/nd089/flower_data.tar.gz). The dataset is split into three parts, training, validation, and testing. For the training, you'll want to apply transformations such as random scaling, cropping, and flipping. This will help the network generalize leading to better performance. You'll also need to make sure the input data is resized to 224x224 pixels as required by the pre-trained networks.
#
# The validation and testing sets are used to measure the model's performance on data it hasn't seen yet. For this you don't want any scaling or rotation transformations, but you'll need to resize then crop the images to the appropriate size.
#
# The pre-trained networks you'll use were trained on the ImageNet dataset where each color channel was normalized separately. For all three sets you'll need to normalize the means and standard deviations of the images to what the network expects. For the means, it's `[0.485, 0.456, 0.406]` and for the standard deviations `[0.229, 0.224, 0.225]`, calculated from the ImageNet images. These values will shift each color channel to be centered at 0 and range from -1 to 1.
#
# In[2]:
data_dir = 'flowers'
train_dir = data_dir + '/train'
valid_dir = data_dir + '/valid'
test_dir = data_dir + '/test'
# In[3]:
# TODO: Define your transforms for the training, validation, and testing sets
data_transforms = {'train': transforms.Compose([transforms.RandomRotation(30),
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])]),
'valid': transforms.Compose([transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])]),
'test': transforms.Compose([transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])
}
# TODO: Load the datasets with ImageFolder
dirs = {'train': train_dir,
'valid': valid_dir,
'test' : test_dir}
image_datasets = {x: datasets.ImageFolder(dirs[x], transform=data_transforms[x])
for x in ['train', 'valid', 'test']}
# TODO: Using the image datasets and the trainforms, define the dataloaders
dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=32, shuffle=True) for x in ['train', 'valid', 'test']}
# ### Label mapping
#
# You'll also need to load in a mapping from category label to category name. You can find this in the file `cat_to_name.json`. It's a JSON object which you can read in with the [`json` module](https://docs.python.org/2/library/json.html). This will give you a dictionary mapping the integer encoded categories to the actual names of the flowers.
# In[4]:
import json
with open('cat_to_name.json', 'r') as f:
cat_to_name = json.load(f)
# # Building and training the classifier
#
# Now that the data is ready, it's time to build and train the classifier. As usual, you should use one of the pretrained models from `torchvision.models` to get the image features. Build and train a new feed-forward classifier using those features.
#
# We're going to leave this part up to you. Refer to [the rubric](https://review.udacity.com/#!/rubrics/1663/view) for guidance on successfully completing this section. Things you'll need to do:
#
# * Load a [pre-trained network](http://pytorch.org/docs/master/torchvision/models.html) (If you need a starting point, the VGG networks work great and are straightforward to use)
# * Define a new, untrained feed-forward network as a classifier, using ReLU activations and dropout
# * Train the classifier layers using backpropagation using the pre-trained network to get the features
# * Track the loss and accuracy on the validation set to determine the best hyperparameters
#
# We've left a cell open for you below, but use as many as you need. Our advice is to break the problem up into smaller parts you can run separately. Check that each part is doing what you expect, then move on to the next. You'll likely find that as you work through each part, you'll need to go back and modify your previous code. This is totally normal!
#
# When training make sure you're updating only the weights of the feed-forward network. You should be able to get the validation accuracy above 70% if you build everything right. Make sure to try different hyperparameters (learning rate, units in the classifier, epochs, etc) to find the best model. Save those hyperparameters to use as default values in the next part of the project.
#
# One last important tip if you're using the workspace to run your code: To avoid having your workspace disconnect during the long-running tasks in this notebook, please read in the earlier page in this lesson called Intro to
# GPU Workspaces about Keeping Your Session Active. You'll want to include code from the workspace_utils.py module.
#
# <font color='red'>**Note for Workspace users:** If your network is over 1 GB when saved as a checkpoint, there might be issues with saving backups in your workspace. Typically this happens with wide dense layers after the convolutional layers. If your saved checkpoint is larger than 1 GB (you can open a terminal and check with `ls -lh`), you should reduce the size of your hidden layers and train again.</font>
# In[5]:
# TODO: Build and train your network
model = models.vgg13(pretrained=True)
model
# ## Testing your network
#
# It's good practice to test your trained network on test data, images the network has never seen either in training or validation. This will give you a good estimate for the model's performance on completely new images. Run the test images through the network and measure the accuracy, the same way you did validation. You should be able to reach around 70% accuracy on the test set if the model has been trained well.
# In[6]:
# TODO: Do validation on the test set
# Freeze parameters
for param in model.parameters():
param.requires_grad = False
# feed forward network
classifier = nn.Sequential(OrderedDict([('fc1', nn.Linear(25088, 4096)),
('relu', nn.ReLU()),
('dropout1',nn.Dropout(0.2)),
('fc2', nn.Linear(4096, 102)),
('output', nn.LogSoftmax(dim=1))]))
# pass the classifier to the pre-trained model
model.classifier = classifier
# train it
criterion = nn.NLLLoss()
optimizer = optim.Adam(model.classifier.parameters(), lr=0.001)
# In[7]:
epochs = 30
model.to('cuda')
for e in range(epochs):
for dataset in ['train', 'valid']:
if dataset == 'train':
model.train()
else:
model.eval()
running_loss = 0.0
running_accuracy = 0
for inputs, labels in dataloaders[dataset]:
inputs, labels = inputs.to('cuda'), labels.to('cuda')
optimizer.zero_grad()
# Forward
with torch.set_grad_enabled(dataset == 'train'):
outputs = model(inputs)
_, preds = torch.max(outputs, 1)
loss = criterion(outputs, labels)
# Backward
if dataset == 'train':
loss.backward()
optimizer.step()
running_loss += loss.item() * inputs.size(0)
running_accuracy += torch.sum(preds == labels.data)
dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'valid', 'test']}
epoch_loss = running_loss / dataset_sizes[dataset]
epoch_accuracy = running_accuracy.double() / dataset_sizes[dataset]
print("Epoch: {}/{}... ".format(e+1, epochs),
"{} Loss: {:.4f} Accurancy: {:.4f}".format(dataset, epoch_loss, epoch_accuracy))
# In[8]:
# validation on the test set
def check_accuracy_on_test(test_loader):
correct = 0
total = 0
model.to('cuda')
with torch.no_grad():
for data in test_loader:
images, labels = data
images, labels = images.to('cuda'), labels.to('cuda')
outputs = model(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Accuracy of the network on the test images: %d %%' % (100 * correct / total))
# In[9]:
check_accuracy_on_test(dataloaders['train'])
# ## Save the checkpoint
#
# Now that your network is trained, save the model so you can load it later for making predictions. You probably want to save other things such as the mapping of classes to indices which you get from one of the image datasets: `image_datasets['train'].class_to_idx`. You can attach this to the model as an attribute which makes inference easier later on.
#
# ```model.class_to_idx = image_datasets['train'].class_to_idx```
#
# Remember that you'll want to completely rebuild the model later so you can use it for inference. Make sure to include any information you need in the checkpoint. If you want to load the model and keep training, you'll want to save the number of epochs as well as the optimizer state, `optimizer.state_dict`. You'll likely want to use this trained model in the next part of the project, so best to save it now.
# In[10]:
# TODO: Save the checkpoint
model.class_to_idx = image_datasets['train'].class_to_idx
model.cpu()
torch.save({'model': 'vgg13',
'state_dict': model.state_dict(),
'class_to_idx': model.class_to_idx},
'save_checkpoint.pth')
# ## Loading the checkpoint
#
# At this point it's good to write a function that can load a checkpoint and rebuild the model. That way you can come back to this project and keep working on it without having to retrain the network.
# In[11]:
# TODO: Write a function that loads a checkpoint and rebuilds the model
def loading_model(checkpoint_path):
check_path = torch.load(checkpoint_path)
model = models.vgg13(pretrained=True)
for param in model.parameters():
param.requires_grad = False
model.class_to_idx = check_path['class_to_idx']
# Build a feed-forward network
classifier = nn.Sequential(OrderedDict([('fc1', nn.Linear(25088, 4096)),
('relu', nn.ReLU()),
('dropout1',nn.Dropout(0.2)),
('fc2', nn.Linear(4096, 102)),
('output', nn.LogSoftmax(dim=1))]))
# Put the classifier on the pretrained network
model.classifier = classifier
model.load_state_dict(check_path['state_dict'])
return model
# In[12]:
model = loading_model('save_checkpoint.pth')
model
# # Inference for classification
#
# Now you'll write a function to use a trained network for inference. That is, you'll pass an image into the network and predict the class of the flower in the image. Write a function called `predict` that takes an image and a model, then returns the top $K$ most likely classes along with the probabilities. It should look like
#
# ```python
# probs, classes = predict(image_path, model)
# print(probs)
# print(classes)
# > [ 0.01558163 0.01541934 0.01452626 0.01443549 0.01407339]
# > ['70', '3', '45', '62', '55']
# ```
#
# First you'll need to handle processing the input image such that it can be used in your network.
#
# ## Image Preprocessing
#
# You'll want to use `PIL` to load the image ([documentation](https://pillow.readthedocs.io/en/latest/reference/Image.html)). It's best to write a function that preprocesses the image so it can be used as input for the model. This function should process the images in the same manner used for training.
#
# First, resize the images where the shortest side is 256 pixels, keeping the aspect ratio. This can be done with the [`thumbnail`](http://pillow.readthedocs.io/en/3.1.x/reference/Image.html#PIL.Image.Image.thumbnail) or [`resize`](http://pillow.readthedocs.io/en/3.1.x/reference/Image.html#PIL.Image.Image.thumbnail) methods. Then you'll need to crop out the center 224x224 portion of the image.
#
# Color channels of images are typically encoded as integers 0-255, but the model expected floats 0-1. You'll need to convert the values. It's easiest with a Numpy array, which you can get from a PIL image like so `np_image = np.array(pil_image)`.
#
# As before, the network expects the images to be normalized in a specific way. For the means, it's `[0.485, 0.456, 0.406]` and for the standard deviations `[0.229, 0.224, 0.225]`. You'll want to subtract the means from each color channel, then divide by the standard deviation.
#
# And finally, PyTorch expects the color channel to be the first dimension but it's the third dimension in the PIL image and Numpy array. You can reorder dimensions using [`ndarray.transpose`](https://docs.scipy.org/doc/numpy-1.13.0/reference/generated/numpy.ndarray.transpose.html). The color channel needs to be first and retain the order of the other two dimensions.
# In[13]:
def process_image(image):
''' Scales, crops, and normalizes a PIL image for a PyTorch model,
returns an Numpy array
'''
# TODO: Process a PIL image for use in a PyTorch model
pil_image = Image.open(image)
# Edit Images
edit_image = transforms.Compose([transforms.Resize(256),
transforms.RandomCrop(224),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])])
# Images Dimensions
img_tensor = edit_image(pil_image)
processed_image = np.array(img_tensor)
processed_image = processed_image.transpose((0, 2, 1))
return processed_image
# In[14]:
# Test images
image_path = 'flowers/test/1/image_06743.jpg'
img = process_image(image_path)
print(img.shape)
# To check your work, the function below converts a PyTorch tensor and displays it in the notebook. If your `process_image` function works, running the output through this function should return the original image (except for the cropped out portions).
# In[17]:
def imshow(image, ax=None, title=None):
if ax is None:
fig, ax = plt.subplots()
if title:
plt.title(title)
# PyTorch tensors assume the color channel is the first dimension
# but matplotlib assumes is the third dimension
image = image.transpose((1, 2, 0))
# Undo preprocessing
mean = np.array([0.485, 0.456, 0.406])
std = np.array([0.229, 0.224, 0.225])
image = std * image + mean
# Image needs to be clipped between 0 and 1 or it looks like noise when displayed
image = np.clip(image, 0, 1)
ax.imshow(image)
return ax
# In[21]:
imshow(process_image("flowers/test/10/image_07090.jpg"));
# ## Class Prediction
#
# Once you can get images in the correct format, it's time to write a function for making predictions with your model. A common practice is to predict the top 5 or so (usually called top-$K$) most probable classes. You'll want to calculate the class probabilities then find the $K$ largest values.
#
# To get the top $K$ largest values in a tensor use [`x.topk(k)`](http://pytorch.org/docs/master/torch.html#torch.topk). This method returns both the highest `k` probabilities and the indices of those probabilities corresponding to the classes. You need to convert from these indices to the actual class labels using `class_to_idx` which hopefully you added to the model or from an `ImageFolder` you used to load the data ([see here](#Save-the-checkpoint)). Make sure to invert the dictionary so you get a mapping from index to class as well.
#
# Again, this method should take a path to an image and a model checkpoint, then return the probabilities and classes.
#
# ```python
# probs, classes = predict(image_path, model)
# print(probs)
# print(classes)
# > [ 0.01558163 0.01541934 0.01452626 0.01443549 0.01407339]
# > ['70', '3', '45', '62', '55']
# ```
# In[22]:
def predict(image_path, model, topk=5):
''' Predict the class (or classes) of an image using a trained deep learning model.
'''
# TODO: Implement the code to predict the class from an image file
model.class_to_idx = image_datasets['train'].class_to_idx
model.to('cuda')
img_torch = process_image(image_path)
img_torch = torch.from_numpy(img_torch).type(torch.FloatTensor)
img_torch = img_torch.unsqueeze(0)
img_torch = img_torch.float()
with torch.no_grad():
output = model.forward(img_torch.cuda())
probability = F.softmax(output.data,dim=1)
probabilies = probability.topk(topk)
score = np.array(probabilies[0][0])
index = 1
flowers_list = [cat_to_name[str(index + 1)] for index in np.array(probabilies[1][0])]
return score, flowers_list
# ## Sanity Checking
#
# Now that you can use a trained model for predictions, check to make sure it makes sense. Even if the testing accuracy is high, it's always good to check that there aren't obvious bugs. Use `matplotlib` to plot the probabilities for the top 5 classes as a bar graph, along with the input image. It should look like this:
#
# <img src='assets/inference_example.png' width=300px>
#
# You can convert from the class integer encoding to actual flower names with the `cat_to_name.json` file (should have been loaded earlier in the notebook). To show a PyTorch tensor as an image, use the `imshow` function defined above.
# In[23]:
# TODO: Display an image along with the top 5 classes
def display_top(image_path, model):
# Setting plot area
plt.figure(figsize = (3,6))
ax = plt.subplot(2,1,1)
# Display test flower
img = process_image(image_path)
get_title = image_path.split('/')
print(cat_to_name[get_title[2]])
imshow(img, ax, title = cat_to_name[get_title[2]]);
# Making prediction
score, flowers_list = predict(image_path, model)
fig,ax = plt.subplots(figsize=(4,3))
sticks = np.arange(len(flowers_list))
ax.barh(sticks, score, height=0.3, linewidth=2.0, align = 'center')
ax.set_yticks(ticks = sticks)
ax.set_yticklabels(flowers_list)
# In[37]:
images_paths = ['flowers/test/28/image_05214.jpg',
'flowers/test/100/image_07896.jpg',
'flowers/test/15/image_06351.jpg',
'flowers/test/25/image_06583.jpg']
for i in images_paths:
display_top(i, model)
# <font color='red'>**Reminder for Workspace users:** If your network becomes very large when saved as a checkpoint, there might be issues with saving backups in your workspace. You should reduce the size of your hidden layers and train again.
#
# We strongly encourage you to delete these large interim files and directories before navigating to another page or closing the browser tab.</font>
# In[1]:
# TODO remove .pth files or move it to a temporary `~/opt` directory in this Workspace