adaltof

### Obtain bottleneck features from another pre-trained CNN.

filename = 'bottleneck_features/DogResnet50Data.npz'
bottleneck_url = 'https://s3-us-west-1.amazonaws.com/udacity-aind/dog-project/DogResnet50Data.npz'

if not exists(filename):
    urllib.request.urlretrieve(bottleneck_url, filename)

bottleneck_features = np.load(filename)
train_new = bottleneck_features['train']

adaltof

### Function that takes a path to an image as input
### and returns the dog breed that is predicted by the model.

def predict_breed(img_path):
    # extract bottleneck features
    bottleneck_feature = extract_Resnet50(path_to_tensor(img_path))
    # obtain predicted vector
    predicted_vector = new_model.predict(bottleneck_feature)
    # return dog breed that is predicted by the model
    return dog_names[np.argmax(predicted_vector)]

adaltof

### Obtain bottleneck features from another pre-trained CNN.

filename = 'bottleneck_features/DogResnet50Data.npz'
bottleneck_url = 'https://s3-us-west-1.amazonaws.com/udacity-aind/dog-project/DogResnet50Data.npz'

if not exists(filename):
    urllib.request.urlretrieve(bottleneck_url, filename)

bottleneck_features = np.load(filename)
train_new = bottleneck_features['train']

adaltof

from keras.layers import Conv2D, MaxPooling2D, GlobalAveragePooling2D
from keras.layers import Dropout, Flatten, Dense
from keras.models import Sequential

model = Sequential()

### CNN Architecture for Dog Classifier built from Scracth

model.add(Conv2D(16, 2, activation='relu', input_shape=(224,224,3)))
model.add(MaxPooling2D(pool_size=(2,2)))

adaltof

from keras.applications.resnet50 import ResNet50, preprocess_input, decode_predictions
from keras.preprocessing import image                  
from tqdm import tqdm

# define ResNet50 model
ResNet50_model = ResNet50(weights='imagenet')

def path_to_tensor(img_path):
    # loads RGB image as PIL.Image.Image type
    img = image.load_img(img_path, target_size=(224, 224))

adaltof

import cv2                
import matplotlib.pyplot as plt                        
%matplotlib inline                               

# extract pre-trained face detector
face_cascade = cv2.CascadeClassifier('haarcascades/haarcascade_frontalface_alt.xml')

def detect_human_face(img):

    # convert BGR image to grayscale

adaltof

Keybase proof

I hereby claim:

• I am adaltof on github.
• I am acorreia (https://keybase.io/acorreia) on keybase.
• I have a public key ASCrL4Ume03y_jaddsiGZ0e0hfwo4sawXNOcXdM3bKQR3Ao

To claim this, I am signing this object: