def get_image():
global model, lb
img = CropIm("..\\testim\\acer_platanoides__03.jpg")
label, prob = Classify(img, model, lb)
print("success")
result = label.replace("_", " ")
result = result.capitalize()
print("I am %d%% confident this is %s" % (prob, result))
def get_image(bot, update):
global model, lb
file_id = update.message.photo[-1].file_id
photo = bot.getFile(file_id)
photo.download(file_id + '.png')
img = CropIm(file_id + '.png')
os.remove(file_id + '.png')
update.message.reply_text(
random.choice([
'Recognition in progress',
"One moment, I'll check what tree is that", 'Processing...'
]))
label, prob = Classify(img, model, lb)
print("success")
result = label.replace("_", " ")
result = result.capitalize()
update.message.reply_text("I am %d%% confident this is %s" %
(prob, result))
def get_image(bot, update):
global model, lb
file_id = update.message.photo[-1].file_id
#print("hm")
photo = bot.getFile(file_id)
#print("got it")
photo.download(file_id+'.png')
# print("downloaded")
img = CropIm(file_id+'.png')
# print("cropped")
os.remove(file_id+'.png')
#print("removed")
update.message.reply_text(random.choice([
'Recognition in progress',
"One moment, I'll check what tree is that",
'Processing...'
]))
prob, first, second, third = Classify(img)
print("success")
if first == "none":
update.message.reply_text("I'm not sure what is it. Please, try another image1")
else:
first = np.array2string(first)
first = first.replace("_", " ")
first = first.replace("['", "")
first = first.replace("']", "")
first = first.capitalize()
second = np.array2string(second)
second = second.replace("_", " ")
second = second.replace("['", "")
second = second.replace("']", "")
second = second.capitalize()
third = np.array2string(third)
third = third.replace("_", " ")
third = third.replace("['", "")
third = third.replace("']", "")
third = third.capitalize()
update.message.reply_text("I am %d%% sure this is %s. It might also be %s or %s, though!" % (prob, first, second, third))
def get_image():
# global model, lb
img = CropIm("..\\testim\\acer_platanoides__03.jpg")
first, second, third = Classify(img)
print("success")
if first == "none":
print("I'm not sure what is it. Please, try another image1")
else:
first = np.array2string(first)
first = first.replace("_", " ")
first = first.replace("['", "")
first = first.replace("']", "")
first = first.capitalize()
second = np.array2string(second)
second = second.replace("_", " ")
second = second.replace("['", "")
second = second.replace("']", "")
second = second.capitalize()
third = np.array2string(third)
third = third.replace("_", " ")
third = third.replace("['", "")
third = third.replace("']", "")
third = third.capitalize()
print("This is most probably %s. It might also be %s or %s, though!" % (first, second, third))
import os
args = {
"model1": '..\\model\\3c98a.model',
"model2": '..\\model\\5c85a.model',
"model3": '..\\model\\5c33a200e.model',
"model4": '..\\model\\6c79a200e.model',
"lb1": '..\\model\\3c98a.pickle',
"lb2": '..\\model\\5c85a.pickle',
"lb3": '..\\model\\5c33a200e.pickle',
"lb4": '..\\model\\6c79a200e.pickle'
}
# load the image
path = '..\\testim\\acer_platanoides__03.jpg'
image = CropIm(path)
output = cv2.imread(path,3)
# pre-process the image for classification
image = cv2.resize(image, (120, 120))
image = image.astype("float") / 255.0
image = img_to_array(image)
image = np.expand_dims(image, axis=0)
# load the trained convolutional neural network and the label
# binarizer
print("[info] loading network...")
model = load_model(args["model4"])
lb = pickle.loads(open(args["lb4"], "rb").read())
# classify the input image
print("[info] classifying image...")
IMAGE_DIMS = (120, 120, 3)
#initialize data labels
data = []
labels = []
print("[info] loading paths...")
imagePaths = sorted(list(paths.list_images(args["dataset"])))
random.seed(42)
random.shuffle(imagePaths)
print('[info] loading images...')
for imagePath in imagePaths:
# image = cv2.imread(imagePath, 3)
image = CropIm(imagePath)
# print(imagePath)
image = cv2.resize(image, (IMAGE_DIMS[1], IMAGE_DIMS[0]))
image = img_to_array(image)
data.append(image)
label = imagePath.split(os.path.sep)[-2]
labels.append(label)
print('[info] images collected')
data = np.array(data, dtype="float") / 255.0
labels = np.array(labels)
print("[info] data matrix: {:.2f}MB".format(data.nbytes / (1024 * 1000.0)))
lb = LabelBinarizer()
labels = lb.fit_transform(labels)