In this notebook, some template code has already been provided for you, and you will need to implement additional functionality to successfully complete this project. You will not need to modify the included code beyond what is requested. Sections that begin with '(IMPLEMENTATION)' in the header indicate that the following block of code will require additional functionality which you must provide. Instructions will be provided for each section, and the specifics of the implementation are marked in the code block with a 'TODO' statement. Please be sure to read the instructions carefully!
Note: Once you have completed all of the code implementations, you need to finalize your work by exporting the iPython Notebook as an HTML document. Before exporting the notebook to html, all of the code cells need to have been run so that reviewers can see the final implementation and output. You can then export the notebook by using the menu above and navigating to \n", "File -> Download as -> HTML (.html). Include the finished document along with this notebook as your submission.
In addition to implementing code, there will be questions that you must answer which relate to the project and your implementation. Each section where you will answer a question is preceded by a 'Question X' header. Carefully read each question and provide thorough answers in the following text boxes that begin with 'Answer:'. Your project submission will be evaluated based on your answers to each of the questions and the implementation you provide.
Note: Code and Markdown cells can be executed using the Shift + Enter keyboard shortcut. Markdown cells can be edited by double-clicking the cell to enter edit mode.
The rubric contains optional "Stand Out Suggestions" for enhancing the project beyond the minimum requirements. If you decide to pursue the "Stand Out Suggestions", you should include the code in this IPython notebook.
In this notebook, you will make the first steps towards developing an algorithm that could be used as part of a mobile or web app. At the end of this project, your code will accept any user-supplied image as input. If a dog is detected in the image, it will provide an estimate of the dog's breed. If a human is detected, it will provide an estimate of the dog breed that is most resembling. The image below displays potential sample output of your finished project (... but we expect that each student's algorithm will behave differently!).
In this real-world setting, you will need to piece together a series of models to perform different tasks; for instance, the algorithm that detects humans in an image will be different from the CNN that infers dog breed. There are many points of possible failure, and no perfect algorithm exists. Your imperfect solution will nonetheless create a fun user experience!
We break the notebook into separate steps. Feel free to use the links below to navigate the notebook.
In the code cell below, we import a dataset of dog images. We populate a few variables through the use of the load_files
function from the scikit-learn library:
train_files
, valid_files
, test_files
- numpy arrays containing file paths to imagestrain_targets
, valid_targets
, test_targets
- numpy arrays containing onehot-encoded classification labels dog_names
- list of string-valued dog breed names for translating labelsfrom sklearn.datasets import load_files
from keras.utils import np_utils
import numpy as np
from glob import glob
# define function to load train, test, and validation datasets
def load_dataset(path):
data = load_files(path)
dog_files = np.array(data['filenames'])
dog_targets = np_utils.to_categorical(np.array(data['target']), 133)
return dog_files, dog_targets
# load train, test, and validation datasets
train_files, train_targets = load_dataset('/data/dog_images/train')
valid_files, valid_targets = load_dataset('/data/dog_images/valid')
test_files, test_targets = load_dataset('/data/dog_images/test')
# load list of dog names
dog_names = [item[20:-1] for item in sorted(glob("/data/dog_images/train/*/"))]
# print statistics about the dataset
print('There are %d total dog categories.' % len(dog_names))
print('There are %s total dog images.\n' % len(np.hstack([train_files, valid_files, test_files])))
print('There are %d training dog images.' % len(train_files))
print('There are %d validation dog images.' % len(valid_files))
print('There are %d test dog images.'% len(test_files))
In the code cell below, we import a dataset of human images, where the file paths are stored in the numpy array human_files
.
import random
random.seed(8675309)
# load filenames in shuffled human dataset
human_files = np.array(glob("/data/lfw/*/*"))
random.shuffle(human_files)
# print statistics about the dataset
print('There are %d total human images.' % len(human_files))
We use OpenCV's implementation of Haar feature-based cascade classifiers to detect human faces in images. OpenCV provides many pre-trained face detectors, stored as XML files on github. We have downloaded one of these detectors and stored it in the haarcascades
directory.
In the next code cell, we demonstrate how to use this detector to find human faces in a sample image.
import cv2
import matplotlib.pyplot as plt
%matplotlib inline
# extract pre-trained face detector
face_cascade = cv2.CascadeClassifier('haarcascades/haarcascade_frontalface_alt.xml')
# load color (BGR) image
img = cv2.imread(human_files[3])
# convert BGR image to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# find faces in image
faces = face_cascade.detectMultiScale(gray)
# print number of faces detected in the image
print('Number of faces detected:', len(faces))
# get bounding box for each detected face
for (x,y,w,h) in faces:
# add bounding box to color image
cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)
# convert BGR image to RGB for plotting
cv_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
# display the image, along with bounding box
plt.imshow(cv_rgb)
plt.show()
Before using any of the face detectors, it is standard procedure to convert the images to grayscale. The detectMultiScale
function executes the classifier stored in face_cascade
and takes the grayscale image as a parameter.
In the above code, faces
is a numpy array of detected faces, where each row corresponds to a detected face. Each detected face is a 1D array with four entries that specifies the bounding box of the detected face. The first two entries in the array (extracted in the above code as x
and y
) specify the horizontal and vertical positions of the top left corner of the bounding box. The last two entries in the array (extracted here as w
and h
) specify the width and height of the box.
We can use this procedure to write a function that returns True
if a human face is detected in an image and False
otherwise. This function, aptly named face_detector
, takes a string-valued file path to an image as input and appears in the code block below.
# returns "True" if face is detected in image stored at img_path
def face_detector(img_path):
img = cv2.imread(img_path)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray)
return len(faces) > 0
Question 1: Use the code cell below to test the performance of the face_detector
function.
human_files
have a detected human face? dog_files
have a detected human face? Ideally, we would like 100% of human images with a detected face and 0% of dog images with a detected face. You will see that our algorithm falls short of this goal, but still gives acceptable performance. We extract the file paths for the first 100 images from each of the datasets and store them in the numpy arrays human_files_short
and dog_files_short
.
Answer:
human_files_short = human_files[:100]
dog_files_short = train_files[:100]
# Do NOT modify the code above this line.
def count_faces(batch):
count = 0
for x in batch:
if(face_detector(x)):
count = count + 1
return count/len(batch)
result = count_faces(human_files_short)
print('Human faces in human pictures:', result*100, '%, should be 100%')
result = count_faces(dog_files_short)
print('Human faces in dog pictures:', result*100, '%, should be 0%')
Question 2: This algorithmic choice necessitates that we communicate to the user that we accept human images only when they provide a clear view of a face (otherwise, we risk having unneccessarily frustrated users!). In your opinion, is this a reasonable expectation to pose on the user? If not, can you think of a way to detect humans in images that does not necessitate an image with a clearly presented face?
Answer:
I think its fairly reasonable to expect that the user inputs a face. Just like the snapchat face recognition app, it may not be effective without the a picture of a face. We should convey to the users in laymans terms as to how the application works and try to convince them to provide clear face input.
It is possible to train the app on human body and dog body shapes, but it doesn't serve the purpose of this app and would add an extra layer of complexity.
## (Optional) TODO: Report the performance of another
## face detection algorithm on the LFW dataset
### Feel free to use as many code cells as needed.
In this section, we use a pre-trained ResNet-50 model to detect dogs in images. Our first line of code downloads the ResNet-50 model, along with weights that have been trained on ImageNet, a very large, very popular dataset used for image classification and other vision tasks. ImageNet contains over 10 million URLs, each linking to an image containing an object from one of 1000 categories. Given an image, this pre-trained ResNet-50 model returns a prediction (derived from the available categories in ImageNet) for the object that is contained in the image.
from keras.applications.resnet50 import ResNet50
# define ResNet50 model
ResNet50_model = ResNet50(weights='imagenet')
When using TensorFlow as backend, Keras CNNs require a 4D array (which we'll also refer to as a 4D tensor) as input, with shape
$$ (\text{nb_samples}, \text{rows}, \text{columns}, \text{channels}), $$where nb_samples
corresponds to the total number of images (or samples), and rows
, columns
, and channels
correspond to the number of rows, columns, and channels for each image, respectively.
The path_to_tensor
function below takes a string-valued file path to a color image as input and returns a 4D tensor suitable for supplying to a Keras CNN. The function first loads the image and resizes it to a square image that is $224 \times 224$ pixels. Next, the image is converted to an array, which is then resized to a 4D tensor. In this case, since we are working with color images, each image has three channels. Likewise, since we are processing a single image (or sample), the returned tensor will always have shape
The paths_to_tensor
function takes a numpy array of string-valued image paths as input and returns a 4D tensor with shape
Here, nb_samples
is the number of samples, or number of images, in the supplied array of image paths. It is best to think of nb_samples
as the number of 3D tensors (where each 3D tensor corresponds to a different image) in your dataset!
from keras.preprocessing import image
from tqdm import tqdm
def path_to_tensor(img_path):
# loads RGB image as PIL.Image.Image type
img = image.load_img(img_path, target_size=(224, 224))
# convert PIL.Image.Image type to 3D tensor with shape (224, 224, 3)
x = image.img_to_array(img)
# convert 3D tensor to 4D tensor with shape (1, 224, 224, 3) and return 4D tensor
return np.expand_dims(x, axis=0)
def paths_to_tensor(img_paths):
list_of_tensors = [path_to_tensor(img_path) for img_path in tqdm(img_paths)]
return np.vstack(list_of_tensors)
Getting the 4D tensor ready for ResNet-50, and for any other pre-trained model in Keras, requires some additional processing. First, the RGB image is converted to BGR by reordering the channels. All pre-trained models have the additional normalization step that the mean pixel (expressed in RGB as $[103.939, 116.779, 123.68]$ and calculated from all pixels in all images in ImageNet) must be subtracted from every pixel in each image. This is implemented in the imported function preprocess_input
. If you're curious, you can check the code for preprocess_input
here.
Now that we have a way to format our image for supplying to ResNet-50, we are now ready to use the model to extract the predictions. This is accomplished with the predict
method, which returns an array whose $i$-th entry is the model's predicted probability that the image belongs to the $i$-th ImageNet category. This is implemented in the ResNet50_predict_labels
function below.
By taking the argmax of the predicted probability vector, we obtain an integer corresponding to the model's predicted object class, which we can identify with an object category through the use of this dictionary.
from keras.applications.resnet50 import preprocess_input, decode_predictions
def ResNet50_predict_labels(img_path):
# returns prediction vector for image located at img_path
img = preprocess_input(path_to_tensor(img_path))
return np.argmax(ResNet50_model.predict(img))
While looking at the dictionary, you will notice that the categories corresponding to dogs appear in an uninterrupted sequence and correspond to dictionary keys 151-268, inclusive, to include all categories from 'Chihuahua'
to 'Mexican hairless'
. Thus, in order to check to see if an image is predicted to contain a dog by the pre-trained ResNet-50 model, we need only check if the ResNet50_predict_labels
function above returns a value between 151 and 268 (inclusive).
We use these ideas to complete the dog_detector
function below, which returns True
if a dog is detected in an image (and False
if not).
### returns "True" if a dog is detected in the image stored at img_path
def dog_detector(img_path):
prediction = ResNet50_predict_labels(img_path)
return ((prediction <= 268) & (prediction >= 151))
Question 3: Use the code cell below to test the performance of your dog_detector
function.
human_files_short
have a detected dog? dog_files_short
have a detected dog?Answer:
humans = 0
for x in human_files_short:
if dog_detector(x):
humans = humans + 1
dogs = 0
for x in dog_files_short:
if dog_detector(x):
dogs = dogs + 1
print(humans, "% rate of dogs in human pictures")
print(dogs, "% rate of dogs in dog pictures")
Now that we have functions for detecting humans and dogs in images, we need a way to predict breed from images. In this step, you will create a CNN that classifies dog breeds. You must create your CNN from scratch (so, you can't use transfer learning yet!), and you must attain a test accuracy of at least 1%. In Step 5 of this notebook, you will have the opportunity to use transfer learning to create a CNN that attains greatly improved accuracy.
Be careful with adding too many trainable layers! More parameters means longer training, which means you are more likely to need a GPU to accelerate the training process. Thankfully, Keras provides a handy estimate of the time that each epoch is likely to take; you can extrapolate this estimate to figure out how long it will take for your algorithm to train.
We mention that the task of assigning breed to dogs from images is considered exceptionally challenging. To see why, consider that even a human would have great difficulty in distinguishing between a Brittany and a Welsh Springer Spaniel.
Brittany | Welsh Springer Spaniel |
---|---|
It is not difficult to find other dog breed pairs with minimal inter-class variation (for instance, Curly-Coated Retrievers and American Water Spaniels).
Curly-Coated Retriever | American Water Spaniel |
---|---|
Likewise, recall that labradors come in yellow, chocolate, and black. Your vision-based algorithm will have to conquer this high intra-class variation to determine how to classify all of these different shades as the same breed.
Yellow Labrador | Chocolate Labrador | Black Labrador |
---|---|---|
We also mention that random chance presents an exceptionally low bar: setting aside the fact that the classes are slightly imabalanced, a random guess will provide a correct answer roughly 1 in 133 times, which corresponds to an accuracy of less than 1%.
Remember that the practice is far ahead of the theory in deep learning. Experiment with many different architectures, and trust your intuition. And, of course, have fun!
We rescale the images by dividing every pixel in every image by 255.
from PIL import ImageFile
ImageFile.LOAD_TRUNCATED_IMAGES = True
# pre-process the data for Keras
train_tensors = paths_to_tensor(train_files).astype('float32')/255
valid_tensors = paths_to_tensor(valid_files).astype('float32')/255
test_tensors = paths_to_tensor(test_files).astype('float32')/255
Create a CNN to classify dog breed. At the end of your code cell block, summarize the layers of your model by executing the line:
model.summary()
We have imported some Python modules to get you started, but feel free to import as many modules as you need. If you end up getting stuck, here's a hint that specifies a model that trains relatively fast on CPU and attains >1% test accuracy in 5 epochs:
Question 4: Outline the steps you took to get to your final CNN architecture and your reasoning at each step. If you chose to use the hinted architecture above, describe why you think that CNN architecture should work well for the image classification task.
Answer:
from keras.layers import Conv2D, MaxPooling2D, GlobalAveragePooling2D, Activation
from keras.layers import Dropout, Flatten, Dense
from keras.models import Sequential
model = Sequential()
model.add(
Conv2D(
filters=16,
kernel_size=5,
padding='same',
activation='relu',
input_shape=(224, 224, 3),
)
)
model.add(MaxPooling2D(pool_size=2))
model.add(
Conv2D(
filters=16,
kernel_size=5,
padding='same',
activation='relu',
)
)
model.add(MaxPooling2D(pool_size=2))
model.add(Flatten())
model.add(Dense(133, activation='softmax'))
model.summary()
model.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])
Train your model in the code cell below. Use model checkpointing to save the model that attains the best validation loss.
You are welcome to augment the training data, but this is not a requirement.
from keras.callbacks import ModelCheckpoint
### TODO: specify the number of epochs that you would like to use to train the model.
epochs = 3
checkpointer = ModelCheckpoint(filepath='saved_models/weights.best.from_scratch.hdf5',
verbose=1, save_best_only=True)
model.fit(train_tensors, train_targets,
validation_data=(valid_tensors, valid_targets),
epochs=epochs, batch_size=20, callbacks=[checkpointer], verbose=1)
model.load_weights('saved_models/weights.best.from_scratch.hdf5')
Try out your model on the test dataset of dog images. Ensure that your test accuracy is greater than 1%.
# get index of predicted dog breed for each image in test set
dog_breed_predictions = [np.argmax(model.predict(np.expand_dims(tensor, axis=0))) for tensor in test_tensors]
# report test accuracy
test_accuracy = 100*np.sum(np.array(dog_breed_predictions)==np.argmax(test_targets, axis=1))/len(dog_breed_predictions)
print('Test accuracy: %.4f%%' % test_accuracy)
bottleneck_features = np.load('/data/bottleneck_features/DogVGG16Data.npz')
train_VGG16 = bottleneck_features['train']
valid_VGG16 = bottleneck_features['valid']
test_VGG16 = bottleneck_features['test']
The model uses the the pre-trained VGG-16 model as a fixed feature extractor, where the last convolutional output of VGG-16 is fed as input to our model. We only add a global average pooling layer and a fully connected layer, where the latter contains one node for each dog category and is equipped with a softmax.
VGG16_model = Sequential()
VGG16_model.add(GlobalAveragePooling2D(input_shape=train_VGG16.shape[1:]))
VGG16_model.add(Dense(133, activation='softmax'))
VGG16_model.summary()
VGG16_model.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])
checkpointer = ModelCheckpoint(filepath='saved_models/weights.best.VGG16.hdf5',
verbose=1, save_best_only=True)
VGG16_model.fit(train_VGG16, train_targets,
validation_data=(valid_VGG16, valid_targets),
epochs=20, batch_size=20, callbacks=[checkpointer], verbose=1)
VGG16_model.load_weights('saved_models/weights.best.VGG16.hdf5')
Now, we can use the CNN to test how well it identifies breed within our test dataset of dog images. We print the test accuracy below.
# get index of predicted dog breed for each image in test set
VGG16_predictions = [np.argmax(VGG16_model.predict(np.expand_dims(feature, axis=0))) for feature in test_VGG16]
# report test accuracy
test_accuracy = 100*np.sum(np.array(VGG16_predictions)==np.argmax(test_targets, axis=1))/len(VGG16_predictions)
print('Test accuracy: %.4f%%' % test_accuracy)
from extract_bottleneck_features import *
def VGG16_predict_breed(img_path):
# extract bottleneck features
bottleneck_feature = extract_VGG16(path_to_tensor(img_path))
# obtain predicted vector
predicted_vector = VGG16_model.predict(bottleneck_feature)
# return dog breed that is predicted by the model
return dog_names[np.argmax(predicted_vector)]
You will now use transfer learning to create a CNN that can identify dog breed from images. Your CNN must attain at least 60% accuracy on the test set.
In Step 4, we used transfer learning to create a CNN using VGG-16 bottleneck features. In this section, you must use the bottleneck features from a different pre-trained model. To make things easier for you, we have pre-computed the features for all of the networks that are currently available in Keras. These are already in the workspace, at /data/bottleneck_features. If you wish to download them on a different machine, they can be found at:
The files are encoded as such:
Dog{network}Data.npz
where {network}
, in the above filename, can be one of VGG19
, Resnet50
, InceptionV3
, or Xception
.
The above architectures are downloaded and stored for you in the /data/bottleneck_features/
folder.
This means the following will be in the /data/bottleneck_features/
folder:
DogVGG19Data.npz
DogResnet50Data.npz
DogInceptionV3Data.npz
DogXceptionData.npz
In the code block below, extract the bottleneck features corresponding to the train, test, and validation sets by running the following:
bottleneck_features = np.load('/data/bottleneck_features/Dog{network}Data.npz')
train_{network} = bottleneck_features['train']
valid_{network} = bottleneck_features['valid']
test_{network} = bottleneck_features['test']
bottleneck_features = np.load('/data/bottleneck_features/DogInceptionV3Data.npz')
train_inception = bottleneck_features['train']
valid_inception = bottleneck_features['valid']
test_inception = bottleneck_features['test']
Create a CNN to classify dog breed. At the end of your code cell block, summarize the layers of your model by executing the line:
<your model's name>.summary()
Question 5: Outline the steps you took to get to your final CNN architecture and your reasoning at each step. Describe why you think the architecture is suitable for the current problem.
Answer:
In this experiment I will use global average pooling. Pooling in general helps us make the model invariant. Although we lose some specific information such as location etc.., our model will become robust at detection and we don't really care where the face is, except that it is present. Using pooling also drastically reduces the dimensionality of the features.
I followed with a Dense Layer to get the correct shape and added the RELU activiation for non-linearity. RELU activation allows us to solve the problem of vanishing gradients.
I added a dropout layer to fight overfitting and set it to 20% dropout. I wanted to use a softmax layer as well so I added another dense layer.
I have chosen the inception features because they are pretrained on ImageNet which contains many pictures of including animals and people. This will shortcut a large amount of training time required to create a good model from scratch.
This model should work well because it is tailored to the use case of finding a face somewhere in the image, and classifying it. It also has pre-existing knowledge of many images and trains relatively quickly. The output of the fully connected dense layer is 133, which corresponds to the number of possible breeds.
model = Sequential()
model.add(GlobalAveragePooling2D(input_shape=train_inception.shape[1:]))
model.add(Dense(500))
model.add(Activation("relu"))
model.add(Dropout(0.2))
model.add(Dense(133, activation='softmax'))
model.summary()
model.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])
Train your model in the code cell below. Use model checkpointing to save the model that attains the best validation loss.
You are welcome to augment the training data, but this is not a requirement.
checkpointer = ModelCheckpoint(filepath='saved_models/weights.best.model.hdf5',
verbose=1, save_best_only=True)
model.fit(train_inception, train_targets,
validation_data=(valid_inception, valid_targets),
epochs=5, batch_size=20, callbacks=[checkpointer], verbose=1)
model.load_weights('saved_models/weights.best.model.hdf5')
Try out your model on the test dataset of dog images. Ensure that your test accuracy is greater than 60%.
predictions = [np.argmax(model.predict(np.expand_dims(feature, axis=0))) for feature in test_inception]
# report test accuracy
test_accuracy = 100*np.sum(np.array(predictions)==np.argmax(test_targets, axis=1))/len(predictions)
print('Test accuracy: %.4f%%' % test_accuracy)
Write a function that takes an image path as input and returns the dog breed (Affenpinscher
, Afghan_hound
, etc) that is predicted by your model.
Similar to the analogous function in Step 5, your function should have three steps:
dog_names
array defined in Step 0 of this notebook to return the corresponding breed.The functions to extract the bottleneck features can be found in extract_bottleneck_features.py
, and they have been imported in an earlier code cell. To obtain the bottleneck features corresponding to your chosen CNN architecture, you need to use the function
extract_{network}
where {network}
, in the above filename, should be one of VGG19
, Resnet50
, InceptionV3
, or Xception
.
def predict_breed(img_path):
bottleneck_feature = extract_InceptionV3(path_to_tensor(img_path))
predicted_vector = model.predict(bottleneck_feature)
return dog_names[np.argmax(predicted_vector)]
Write an algorithm that accepts a file path to an image and first determines whether the image contains a human, dog, or neither. Then,
You are welcome to write your own functions for detecting humans and dogs in images, but feel free to use the face_detector
and dog_detector
functions developed above. You are required to use your CNN from Step 5 to predict dog breed.
Some sample output for our algorithm is provided below, but feel free to design your own user experience!
import matplotlib.image as mpimg
def looks_like_breed(img_path):
if dog_detector(img_path):
species = "dog"
elif face_detector(img_path):
species = "human"
else:
species = "unknown"
breed = predict_breed(img_path)
print("Hello, ", species)
plt.imshow(mpimg.imread(img_path))
print("You look like a ... ", breed)
In this section, you will take your new algorithm for a spin! What kind of dog does the algorithm think that you look like? If you have a dog, does it predict your dog's breed accurately? If you have a cat, does it mistakenly think that your cat is a dog?
Test your algorithm at least six images on your computer. Feel free to use any images you like. Use at least two human and two dog images.
Question 6: Is the output better than you expected :) ? Or worse :( ? Provide at least three possible points of improvement for your algorithm.
Answer: Due to the extremely limited processing power that I have available, I wasn't able to experiment with large neural networks. I built the simplest models I could to keep the training time down. I do believe that I could have added more layers, batch normalization, and more filters with larger windows. All of these improvements would have drasitcally increased the training time of the model. I don't really believe I look like the breed of dog suggested, but I may have confused the algorithm with a picture that contained two faces.
looks_like_breed("images/dog-1.jpg")
looks_like_breed("images/dog-2.jpg")
looks_like_breed("images/dog-3.jpg")
looks_like_breed("images/human-1.jpg")
looks_like_breed("images/human-2.jpg")
looks_like_breed("images/human-3.jpeg")
looks_like_breed("images/dog-4.jpg")
looks_like_breed("images/dog-5.jpeg")
looks_like_breed("images/dog-6.jpeg"
In order to submit, please do the following:
zip -r dog-project.zip dog-project