-
-
Save ageitgey/a40dded08e82e59724c70da23786bbf0 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding: utf-8 -*- | |
from __future__ import division, print_function, absolute_import | |
import tflearn | |
from tflearn.layers.core import input_data, dropout, fully_connected | |
from tflearn.layers.conv import conv_2d, max_pool_2d | |
from tflearn.layers.estimator import regression | |
from tflearn.data_preprocessing import ImagePreprocessing | |
from tflearn.data_augmentation import ImageAugmentation | |
import scipy | |
import numpy as np | |
import argparse | |
parser = argparse.ArgumentParser(description='Decide if an image is a picture of a bird') | |
parser.add_argument('image', type=str, help='The image image file to check') | |
args = parser.parse_args() | |
# Same network definition as before | |
img_prep = ImagePreprocessing() | |
img_prep.add_featurewise_zero_center() | |
img_prep.add_featurewise_stdnorm() | |
img_aug = ImageAugmentation() | |
img_aug.add_random_flip_leftright() | |
img_aug.add_random_rotation(max_angle=25.) | |
img_aug.add_random_blur(sigma_max=3.) | |
network = input_data(shape=[None, 32, 32, 3], | |
data_preprocessing=img_prep, | |
data_augmentation=img_aug) | |
network = conv_2d(network, 32, 3, activation='relu') | |
network = max_pool_2d(network, 2) | |
network = conv_2d(network, 64, 3, activation='relu') | |
network = conv_2d(network, 64, 3, activation='relu') | |
network = max_pool_2d(network, 2) | |
network = fully_connected(network, 512, activation='relu') | |
network = dropout(network, 0.5) | |
network = fully_connected(network, 2, activation='softmax') | |
network = regression(network, optimizer='adam', | |
loss='categorical_crossentropy', | |
learning_rate=0.001) | |
model = tflearn.DNN(network, tensorboard_verbose=0, checkpoint_path='bird-classifier.tfl.ckpt') | |
model.load("bird-classifier.tfl.ckpt-50912") | |
# Load the image file | |
img = scipy.ndimage.imread(args.image, mode="RGB") | |
# Scale it to 32x32 | |
img = scipy.misc.imresize(img, (32, 32), interp="bicubic").astype(np.float32, casting='unsafe') | |
# Predict | |
prediction = model.predict([img]) | |
# Check the result. | |
is_bird = np.argmax(prediction[0]) == 1 | |
if is_bird: | |
print("That's a bird!") | |
else: | |
print("That's not a bird!") |
Hi, can you tell me what your Y dataset looks like? The way I did it was [[1., 0.], ... , [0., 1.]]. I'm always getting [0., 1.] as my prediction.
how to run can u explain
in parser.add_argument('image', type=str, help='The image image file to check') does 'image' refers to the path to the image file?
types of image file is not clear. Should it be jpeg, bmp, GIF, TIF for testing data ?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
If somebody is still wondering, this script is a part of Adam's nice tutorial on machine learning, over on Medium. https://medium.com/@ageitgey/machine-learning-is-fun-80ea3ec3c471#.7pmvr7722.
You'll find a reference for this bird dataset in part 3.