def test_decode_predictions():
x = np.zeros((2, 1000))
x[0, 372] = 1.0
x[1, 549] = 1.0
outs = utils.decode_predictions(x, top=1)
scores = [out[0][2] for out in outs]
assert scores[0] == scores[1]
# the numbers of columns and ImageNet classes are not identical.
with pytest.raises(ValueError):
utils.decode_predictions(np.ones((2, 100)))
def predict():
data = {
"success": False
}
if request.method == "POST":
if request.files.get("image"):
file = request.files['image']
# image = request.files["image"].read()
image = file.read()
image = Image.open(io.BytesIO(image))
image = prepare_image(image, target=(224, 224))
with graph.as_default():
preds = model.predict(image)
results = imagenet_utils.decode_predictions(preds)
data["predictions"] = []
for (imagenetID, label, prob) in results[0]:
r = {"label": label, "probability": float(prob)}
data["predictions"].append(r)
data["success"] = True
f = os.path.join(app.config['UPLOAD_FOLDER'], file.filename)
file.save(f)
return jsonify(data)
def get_preds(model):
size = model.input_shape[1]
filename = os.path.join(os.path.dirname(__file__), 'data', 'cat.jpg')
batch = KE.preprocess_input(
img_to_array(load_img(filename, target_size=(size, size))))
batch = np.expand_dims(batch, 0)
pred = decode_predictions(model.predict(batch), backend=K, utils=utils)
return pred
def _test_application(name,
input_shape=(224, 224, 3),
last_dim=1000,
label='bull_mastiff'):
classifier, preprocess_input = Classifiers.get(name)
model = classifier(input_shape=input_shape, weights='imagenet')
output_shape, preds = _get_output_shape(model, preprocess_input)
assert output_shape == (None, last_dim)
names = [p[1] for p in decode_predictions(preds, **KWARGS)[0]]
assert label in names[:3]
maxpool = model.get_layer(name='block5_pool')
shape = maxpool.output_shape[1:]
dense = model.get_layer(name='fc1')
layer_utils.convert_dense_weights_data_format(
dense, shape, 'channels_first')
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
return model
if __name__ == '__main__':
model = VGG19(include_top=True, weights='imagenet')
img_path = 'cat.jpg'
img = image.load_img(img_path, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
print('Input image shape:', x.shape)
preds = model.predict(x)
print('Predicted:', decode_predictions(preds))
def decode_predictions(*args, **kwargs):
return imagenet_utils.decode_predictions(*args, **kwargs)
# Load pre-trained models
# -------------------------------------
resnet50 = resnet.ResNet50(weights='imagenet')
resnet101 = resnet.ResNet101(weights='imagenet')
resnet152 = resnet.ResNet152(weights='imagenet')
# -------------------------------------
# Helper functions
# -------------------------------------
def path_to_tensor(image_path, target_size):
image = load_img(image_path, target_size=target_size)
tensor = img_to_array(image)
tensor = np.expand_dims(tensor, axis=0)
return tensor
# -------------------------------------
# Make predictions
# -------------------------------------
image_path = 'images/dog.jpeg'
image_tensor = path_to_tensor(image_path, (224, 224))
pred_resnet50 = resnet50.predict(image_tensor)
print("Resnet50: {}".format(decode_predictions(pred_resnet50, top=1)))
pred_resnet101 = resnet101.predict(image_tensor)
print("Resnet101: {}".format(decode_predictions(pred_resnet101, top=1)))
pred_resnet152 = resnet152.predict(image_tensor)
print("Resnet152: {}".format(decode_predictions(pred_resnet152, top=1)))
model.load_weights(weights_path)
if K.backend() == 'theano':
convert_all_kernels_in_model(model)
return model
def preprocess_input(x):
x /= 255.
x -= 0.5
x *= 2.
return x
if __name__ == '__main__':
model = InceptionV1(include_top=True, weights='imagenet')
img_path = 'elephant.jpg'
img = image.load_img(img_path, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
preds = model.predict(x)
# Extra shift to remove 'background' as entry0
preds_1000 = preds[:, 1:]
print('Predicted:', decode_predictions(preds_1000))
def decode_predictions(*args, **kwargs):
return imagenet_utils.decode_predictions(
*args, **kwargs)
def decode_predictions(*args, **kwargs):
kwargs['backend'] = backend
kwargs['utils'] = keras_utils
return utils.decode_predictions(*args, **kwargs)
