def predict_plant_disease(request):
try:
if request.method == "POST":
if request.body:
print("HIT-Disease")
request_data = request.data["plant_image"]
header, image_data = request_data.split(';base64,')
image_array, err_msg = image_converter.convert_image(
image_data)
if err_msg == None:
image_array = np.array(image_array,
dtype=np.float16) / 225.0
image_array = image_array.reshape((1, 256, 256, 3))
model_file = f"{BASE_DIR}/ml/cnn_model.pkl"
saved_classifier_model = pickle.load(open(
model_file, 'rb'))
prediction = saved_classifier_model.predict(image_array)
K.clear_session()
label_binarizer = pickle.load(
open(f"{BASE_DIR}/ml/label_transform.pkl", 'rb'))
ans = label_binarizer.inverse_transform(prediction)[0]
return_data = {"error": "0", "data": f"{ans}"}
else:
return_data = {
"error": "4",
"message": f"Error : {err_msg}"
}
else:
return_data = {
"error": "1",
"message": "Request Body is empty",
}
elif request.method == "GET":
return_data = {
"error": "0",
"message":
"Plant Disease Recognition Api. Request a POST request"
}
except Exception as e:
return_data = {
"error": "3",
"message": f"Error : {str(e)}",
}
print(return_data)
return HttpResponse(json.dumps(return_data),
content_type='application/json; charset=utf-8')
def answer_webp(update: Update, context: CallbackContext) -> None:
try:
id = str(update.message.from_user["id"])
except:
id = ""
chat_id = str(update.message.chat.id)
if (len(update.message.photo) > 0 and id == str(232424901)
and chat_id == str(232424901)):
photo = update.message.photo[-1]
newFile = photo.get_file()
temp_file_path = newFile.file_path
extw = temp_file_path.split("/")
fname = extw[len(extw) - 1]
newFile.download(fname)
sticker_fname = image_converter.convert_image(fname, "jpg")
update.message.reply_sticker(open(sticker_fname, "rb"))
os.remove(fname)
os.remove(sticker_fname)
def recognize_emotion(json_data):
data = json.loads(json_data)
image = data['image']
up = urlparse.urlparse(image)
head, data = up.path.split(',', 1)
plain_data = data.decode("base64")
if not os.path.exists(TMP_IMAGE_STORAGE):
os.makedirs(TMP_IMAGE_STORAGE)
with open(IMAGE_FILE, 'wb') as f:
f.write(plain_data)
cropped_face, face_detected = convert_image(TMP_IMAGE_STORAGE, IMAGE_FILE)
if (face_detected):
emotion = predict_emotion(cropped_face)
else:
emotion = "no_head"
# remove temporarily saved images from TMP_IMAGE_STORAGE
directory_cleanup(TMP_IMAGE_STORAGE)
return emotion
__all__ = ['propagator', 'image_converter']
if __name__ == "__main__":
import image_converter
import propagator
import numpy as np
from sys import argv
_object = image_converter.convert_image(argv[1], 'L')
z = propagator.z_const(_object, float(argv[3]))
hologram = propagator.holo_arr(_object, z, float(argv[4]), float(argv[4]),
float(argv[5]))
rhologram = propagator.reholo_arr(hologram, z, float(argv[4]),
float(argv[4]), float(argv[5]))
propagator.save_holo(hologram, argv[2], float(argv[4]))
propagator.save_holo(rhologram, argv[2] + '.png', float(argv[4]),
'reconstruct')
image_converter.holo_to_png(hologram, argv[2] + 'x.png')
from image_converter import input_folder, convert_image convert_image(input_folder())