def Standard(path, size):
img = image.load_img(path, target_size=(size, size))
x = image.img_to_array(img)
x /= 255.0
x -= 0.5
x *= 2.0
return x
def show_image(path):
"""Print an image to the notebook
#Arguments
path: location of image
"""
show_array(img_to_array(load_img(path)))
def load_img_array(fname, grayscale=False, target_size=None, data_format='channels_last'):
"""Loads and image file and returns an array."""
img = load_img(fname,
grayscale=grayscale,
target_size=target_size)
x = img_to_array(img, data_format=data_format)
return x
def ZeroCenter(path, size, BGRTranspose=False):
img = image.load_img(path, target_size=(size, size))
x = image.img_to_array(img)
if BGRTranspose == True:
x = x[..., ::-1]
x[..., 0] -= 103.939
x[..., 1] -= 116.779
x[..., 2] -= 123.68
return x
def Run(self, img_path, model_name):
# config variables
weights = 'imagenet'
include_top = 0
train_path = 'jpg'
classfier_file = 'output/flowers_17/' + model_name + '/classifier.cpickle'
# create the pretrained models
# check for pretrained weight usage or not
# check for top layers to be included or not
if model_name == "vgg16":
from vgg16 import VGG16, preprocess_input
base_model = VGG16(weights=weights)
model = Model(inputs=base_model.input,
outputs=base_model.get_layer('fc1').output)
image_size = (224, 224)
elif model_name == "vgg19":
from vgg19 import VGG19, preprocess_input
base_model = VGG19(weights=weights)
model = Model(inputs=base_model.input,
outputs=base_model.get_layer('fc1').output)
image_size = (224, 224)
elif model_name == "resnet50":
from resnet50 import ResNet50, preprocess_input
base_model = ResNet50(weights=weights)
model = Model(inputs=base_model.input,
outputs=base_model.get_layer('avg_pool').output)
image_size = (224, 224)
elif model_name == "inceptionv3":
from inception_v3 import InceptionV3, preprocess_input
base_model = InceptionV3(weights=weights)
model = Model(inputs=base_model.input,
outputs=base_model.get_layer('mixed9').output)
image_size = (299, 299)
elif model_name == "xception":
from xception import Xception, preprocess_input
base_model = Xception(weights=weights)
model = Model(inputs=base_model.input,
outputs=base_model.get_layer('avg_pool').output)
image_size = (299, 299)
else:
base_model = None
img = image.load_img(img_path, target_size=image_size)
img_array = image.img_to_array(img)
img_array = np.expand_dims(img_array, axis=0)
img_array = preprocess_input(img_array)
feature = model.predict(img_array)
feature = feature.flatten()
with open(classfier_file, 'rb') as f:
model2 = pickle.load(f)
pred = model2.predict(feature)
prob = model2.predict_proba(np.atleast_2d(feature))[0]
return pred, prob[0]
def detect():
if request.method == "GET":
return render_template("object.html")
if request.method == "POST":
path = request.form["path"]
img = image.load_img(path, target_size=(299, 299))
xy = image.img_to_array(img)
xy = np.expand_dims(xy, axis=0)
xy = preprocess_input(xy)
preds = model.predict(xy)
preds = decode_predictions(preds, top=3)[0]
acc = []
classes = []
for x in preds:
acc.append(x[2])
classes.append(x[1])
return render_template("object.html",
preds=acc,
classes=json.dumps(classes),
img=path)
def infer_mode(data):
class_indices = pickle.load(open(CLASS_INDEX_FILE, 'rb'))
img = image.load_img(data, target_size=IMG_TGT_SIZE)
inp_data = image.img_to_array(img)
inp_data = np.expand_dims(inp_data, axis=0)
model = False
result = -1
if os.path.isfile(MODEL_SAVE_FILE):
model = load_model(MODEL_SAVE_FILE)
elif os.path.isfile(MODEL_CKPT_FILE):
model = load_model(MODEL_CKPT_FILE)
if model:
predictions = model.predict(inp_data, verbose=1)
prediction = predictions[0]
logging.info("Prediction: %s", prediction)
for classname in class_indices:
logging.info("Prediction that sample is an '%s': %g", classname,
prediction[class_indices[classname]])
result = prediction
else:
logging.error("Error: cannot load tranied model")
return result
model = InceptionV3(weights='imagenet')
for i in range(0, 5000):
for j in range(0, 5000):
print("Here-1")
all_users = db.child("User").get()
#print("Here-2")
#user = db.child("User").get()
try:
#print(user.val())
for user in all_users.each():
key = user.key()
img_from_firebase = str(user.val())
imgByte = img_from_firebase.encode()
with open('D:\\abcd.png', 'wb') as fh:
fh.write(base64.decodebytes(imgByte))
img = image.load_img('D:\\abcd.png', target_size=(299, 299))
print("Here7")
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
preds = model.predict(x)
#print('predicted: ',decode_predictions(preds,top=5)[0])
resList = decode_predictions(preds, top=5)[0]
resNewList = []
for tmpTup in resList:
tmpTup = tmpTup[1]
resNewList.append((tmpTup))
db.child("Result").child(key).set(str(resNewList))
def Identity(path, size):
img = image.load_img(path, target_size=(size, size))
x = image.img_to_array(img)
return x
labels.append(21)
# In[5]:
# encode the labels using LabelEncoder
targetNames = np.unique(labels)
le = LabelEncoder()
le_labels = le.fit_transform(labels)
# In[11]:
# loop over all the labels in the folder
for label in train_labels:
cur_path = train_path + "/" + label
for image_path in glob.glob(cur_path):
img = image.load_img(image_path, target_size=image_size)
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
print(label + " complete")
sys.stdout.flush()
feature = model.predict(x)
flat = feature.flatten()
features.append(flat)
for img_file in enchinacea_imgfiles:
img = image.load_img(img_file, target_size=image_size)
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
print(img_file + " complete")
if include_top:
maxpool = model.get_layer(name='avg_pool')
shape = maxpool.output_shape[1:]
dense = model.get_layer(name='fc1000')
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 = ResNet50(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)
print('Input image shape:', x.shape)
preds = model.predict(x)
print('Predicted:', decode_predictions(preds))
def plots_idx(img_dir, filenames, idx, titles=None):
plots([image.load_img(img_dir + filenames[i]) for i in idx], titles=titles)