def predict_plant_disease(request):
# try:
if request.method == "GET":
return_data = {"error": "0", "message": "Working!!!"}
else:
if request.body:
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:
model_file = f"{BASE_DIR}/ml_files/sequential.pkl"
saved_classifier_model = pickle.load(open(model_file, 'rb'))
prediction = saved_classifier_model.predict(image_array)
label_binarizer = pickle.load(
open(f"{BASE_DIR}/ml_files/label_bin.pkl", 'rb'))
disease_name = label_binarizer.inverse_transform(prediction)[0]
f = open(f"cure_data/{disease_name}.txt", "r+")
suggestion = f.read()
return_data = {
"error": "0",
"data": f"{disease_name}",
"suggestion": f"{suggestion}"
}
return HttpResponse(json.dumps(return_data),
content_type='application/json; charset=utf-8')
def predict_plant_disease(request):
try:
if request.method == "GET":
return_data = {
"error":
"0",
"message":
"Plant Disease Recognition API. Built by Lichen Wang @Team 13 CS260"
}
else:
if request.body:
request_data = request.data["plant_image"]
request_data += "=" * ((4 - len(request_data) % 4) % 4)
image_array, err_msg = image_converter.convert_image(
request_data)
print(err_msg)
if err_msg == None:
with graph.as_default():
prediction = model.predict(image_array)
prediction_flatten = prediction.flatten()
max_val_index = np.argmax(prediction_flatten)
result = output_list[max_val_index]
prob = max(prediction_flatten) * 100
# return Response({'result': result})
# model_file = f"{BASE_DIR}/ml_files/cnn_model.pkl"
# saved_classifier_model = pickle.load(open(model_file,'rb'))
# prediction = saved_classifier_model.predict(image_array)
# label_binarizer = pickle.load(open(f"{BASE_DIR}/ml_files/label_transform.pkl",'rb'))
return_data = {"prob": '%.2f%%' % prob, "data": result}
else:
return_data = {
"error": "4",
"message": f"Error : {err_msg}"
}
else:
return_data = {
"error": "1",
"message": "Request Body is empty",
}
except Exception as e:
return_data = {
"error": "3",
"message": f"Error : {str(e)}",
}
return HttpResponse(json.dumps(return_data),
content_type='application/json; charset=utf-8')
def predict_plant_disease(request):
with open(f"{BASE_DIR}/download.jpg", "rb") as f:
image_data = base64.b64encode(f.read())
image_array, err_msg = image_converter.convert_image(image_data)
model_file = f"{BASE_DIR}/ml_files/cnn_model.pkl"
saved_classifier_model = pickle.load(open(model_file, 'rb'))
prediction = saved_classifier_model.predict(image_array)
label_binarizer = pickle.load(
open(f"{BASE_DIR}/ml_files/label_transform.pkl", 'rb'))
return_data = {
"error": "0",
"data": f"{label_binarizer.inverse_transform(prediction)[0]}"
}
return HttpResponse(json.dumps(return_data),
content_type='application/json; charset=utf-8')
def predict_plant_disease(request):
try:
if request.method == "GET":
return_data = {
"error":
"0",
"message":
"Plant Disease Recognition Api. Built for NaijaHacks 2018"
}
else:
if request.body:
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:
model_file = f"{BASE_DIR}/ml_files/cnn_model.pkl"
saved_classifier_model = pickle.load(open(
model_file, 'rb'))
prediction = saved_classifier_model.predict(image_array)
label_binarizer = pickle.load(
open(f"{BASE_DIR}/ml_files/label_transform.pkl", 'rb'))
return_data = {
"error":
"0",
"data":
f"{label_binarizer.inverse_transform(prediction)[0]}"
}
else:
return_data = {
"error": "4",
"message": f"Error : {err_msg}"
}
else:
return_data = {
"error": "1",
"message": "Request Body is empty",
}
except Exception as e:
return_data = {
"error": "3",
"message": f"Error : {str(e)}",
}
return HttpResponse(json.dumps(return_data),
content_type='application/json; charset=utf-8')
def predict_plant_disease(request):
print('Runing predict_plant_disease')
try:
if request.method == "GET" :
return_data = {
"error" : "0",
"message" : "SinghSahani Enterprise"
}
else:
if request.body:
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 :
model_file = f'{BASE_DIR}/ml_files/cnn.h5'
saved_classifier_model = tf.keras.models.load_model(model_file)
prediction = saved_classifier_model.predict(image_array)
label_binarizer = pickle.load(open(f"{BASE_DIR}/ml_files/label_transform.pkl",'rb'))
return_data = {
"error" : "0",
"data" : f"{label_binarizer.inverse_transform(prediction)[0]}"
}
else :
return_data = {
"error" : "4",
"message" : f"Error : {err_msg}"
}
else :
return_data = {
"error" : "1",
"message" : "Request Body is empty",
}
except Exception as e:
return_data = {
"error" : "3",
"message" : f"Error : {str(e)}",
}
return HttpResponse(json.dumps(return_data), content_type='application/json; charset=utf-8')