def is_hot_dog(preds): decoded = decode_predictions(preds, top=1) # pull out predicted label, which is in d[0][1] due to how decode_predictions structures results labels = [d[0][1] for d in decoded] out = [l == 'hotdog' for l in labels] return out
def is_hot_dog(preds): ''' inputs: preds_array: array of predictions from pre-trained model outputs: is_hot_dog_list: a list indicating which predictions show hotdog as the most likely label ''' decoded = decode_predictions(preds, top=1) # pull out predicted label, which is in d[0][1] due to how decode_predictions structures results labels = [d[0][1] for d in decoded] out = [l == 'hotdog' for l in labels] return out
img_width=image_size): imgs = [ load_img(img_path, target_size=(img_height, img_width)) for img_path in img_paths ] img_array = np.array([img_to_array(img) for img in imgs]) output = preprocess_input(img_array) return (output) my_model = ResNet50( weights='../input/resnet50/resnet50_weights_tf_dim_ordering_tf_kernels.h5') test_data = read_and_prep_images(img_paths) preds = my_model.predict(test_data) most_likely_labels = decode_predictions(preds, top=3) for i, img_path in enumerate(img_paths): display(Image(img_path)) print(most_likely_labels[i]) # Set up code checking from learntools.core import binder binder.bind(globals()) from learntools.deep_learning.exercise_3 import * print("Setup Complete") # Experiment with code outside the function, then move it into the function once you think it is right # the following lines are given as a hint to get you started decoded = decode_predictions(preds, top=1)
def read_and_prep_images(img_paths, img_height=image_size, img_width=image_size): imgs = [ load_img(img_path, target_size=(img_height, img_width)) for img_path in img_paths ] img_array = np.array([img_to_array(img) for img in imgs]) output = preprocess_input(img_array) return (output) from tensorflow.python.keras.applications import ResNet50 my_model = ResNet50( weights='../input/resnet50/resnet50_weights_tf_dim_ordering_tf_kernels.h5') test_data = read_and_prep_images(img_paths) preds = my_model.predict(test_data) from learntools.deep_learning.decode_predictions import decode_predictions from IPython.display import Image, display most_likely_labels = decode_predictions( preds, top=3, class_list_path='../input/resnet50/imagenet_class_index.json') for i, img_path in enumerate(img_paths): display(Image(img_path)) print(most_likely_labels[i])
img = [ load_img(img_path, target_size=(img_height, img_width)) for img_path in img_paths ] img_array = np.array([img_to_array(img) for img in imgs]) output = preprocess_output(img_array) return (output) from tensorflow.python.keras.applications import ResNet50 my_model = ResNet50( weights= 'Desktop/Kartikey DS/Deep Learning/resnet50_weights_tf_dim_ordering_tf_kernels.h5' ) test_data = read_and_prep_images(img_paths) preds = my_model.predict(test_data) from learntools.deep_learning.decode_predictions import decode_predictions from IPython.display import Image, display most_likely_labels = decode_predictions( preds, top=3, class_list_path= 'Desktop/Kartikey DS/Deep Learning/imagenet_class_index.json') for i, img_path in enumerate(img_paths): display(Image(img_path)) print(most_likely_labels[i])