[Solved] leaf disease detection using keras

[arunksoman]

Could you please follow my steps:

1. Uninstall your current Python 3.7 version
2. Install Python 3.6.5
3. If you are using spyder editor make a change to vscode.
4. Go to integrated terminal of vscode and create a virtual environment

python -m venv venv

5. Activate your virtual environment

.\venv\Scripts\activate

6. Create a requirements.txt over your current working directory. Contents for requirements.txt given below:

h5py==2.8.0
imutils==0.5.1
Keras==2.2.4
Keras-Applications==1.0.6
Keras-Preprocessing==1.0.5
kiwisolver==1.0.1
matplotlib==3.0.2
numpy==1.15.3
opencv-contrib-python==3.4.3.18
Pillow==5.3.0
PyWavelets==1.0.1
scikit-image==0.14.1
scikit-learn==0.20.0
scipy==1.1.0
six==1.11.0
sklearn==0.0
tensorboard==1.12.0
tensorflow==1.12.0
termcolor==1.1.0
toolz==0.9.0

7. Then install necessary packages using requirements.txt file

pip install -r requirements.txt

8. Then run your code within this venv and say what happened as reply here.

[sreu13]

@SuperGops
i also have another pickle file "label_transform", which I got as an output from referring the initial code from gaggle, is there any use of this file?

label_binarizer = LabelBinarizer()
image_labels = label_binarizer.fit_transform(label_list)
pickle.dump(label_binarizer,open('label_transform.pkl', 'wb'))
n_classes = len(label_binarizer.classes_)

Kaggle >https://www.kaggle.com/emmarex/plant-disease-detection-using-keras/data

[sreu13]

@arunksoman
i'll follow this proceedure, but would I be able to deploy this code in raspberry pi 4?

[arunksoman]

@sreu13 As the @SuperGops says you have to use fit_transform. It can be implemented on Raspberry Pi 4. But if it slows down your pi you have use multiprocessing as well as threads to improve that.

[sreu13]

@arunksoman
by multiprocessing, do you mean to use multilabel binarizer, if yes , then I have already used it during the training process.
@SuperGops , fit_transform has also been used in the code prior to using label_binarizer.

[arunksoman]

@sreu13 I didn't mean that. I said if you are trying to run your code on RasPi4 or any other version of RasPi, you have to do some optimization on the code for better performance. Then Multiprocessing and threading Module comes into the picture.

[sreu13]

@arunksoman
i followed your proceedure to and installed the requirements.txt file
after running the code, I got the following error

File "C:\Users\admin\Anaconda3\envs\test2\lib\site-packages\scipy\special\basic.py", line 15, in <module>
from ._ufuncs import (ellipkm1, mathieu_a, mathieu_b, iv, jv, gamma,

ImportError: cannot import name 'ellipkm1'

[arunksoman]

@sreu13 I didn't tell you to install anything via anaconda package manager. You have to uninstall those things first and install python 3.6.5. It was the first step.You have to read things carefully before executing anything.

[salmanfaris]

@sreu13 how is the progress?

[sreu13]

@salmanfaris i know there was a delay in replies, i thought of finishing the project and replying here!....
i ddnt get the exact reason, but the problem was solved

what i did was , label binarized was working fine when i did created the training model. So i loaded my training model and deleted the script for the training procedure. i ended up with the code given below. and it worked up fine.

import numpy as np
import pickle
import cv2
from os import listdir
from sklearn.preprocessing import LabelBinarizer
from keras.models import Sequential
from keras.layers.normalization import BatchNormalization
from keras.layers.convolutional import Conv2D
from keras.layers.convolutional import MaxPooling2D
from keras.layers.core import Activation, Flatten, Dropout, Dense
from keras import backend as K
from keras.preprocessing.image import ImageDataGenerator
from keras.optimizers import Adam
from keras.preprocessing import image
from keras.preprocessing.image import img_to_array
from sklearn.preprocessing import MultiLabelBinarizer
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt

EPOCHS = 25
INIT_LR = 1e-3
BS = 32
default_image_size = tuple((256, 256))
image_size = 0
directory_root = 'PlantVillage'
width=256
height=256
depth=3

#Function to convert images to array
def convert_image_to_array(image_dir):
    try:
        image = cv2.imread(image_dir)
        if image is not None :
            image = cv2.resize(image, default_image_size)   
            return img_to_array(image)
        else :
            return np.array([])
    except Exception as e:
        print(f"Error : {e}")
        return None

listdir(directory_root)

image_list, label_list = [], []
try:
    print("[INFO] Loading images ...")
    root_dir = listdir(directory_root)
    for directory in root_dir :
        # remove .DS_Store from list
        if directory == ".DS_Store" :
            root_dir.remove(directory)

    for plant_folder in root_dir :
        plant_disease_folder_list = listdir(f"{directory_root}/{plant_folder}")
        
        for disease_folder in plant_disease_folder_list :
            # remove .DS_Store from list
            if disease_folder == ".DS_Store" :
                plant_disease_folder_list.remove(disease_folder)

        for plant_disease_folder in plant_disease_folder_list:
            print(f"[INFO] Processing {plant_disease_folder} ...")
            plant_disease_image_list = listdir(f"{directory_root}/{plant_folder}/{plant_disease_folder}")
           
                
            for single_plant_disease_image in plant_disease_image_list :
                if single_plant_disease_image == ".DS_Store" :
                    plant_disease_image_list.remove(single_plant_disease_image)

            for image in plant_disease_image_list[:200]:
                image_directory = f"{directory_root}/{plant_folder}/{plant_disease_folder}/{image}"
                if image_directory.endswith(".jpg") == True or image_directory.endswith(".JPG") == True:
                    image_list.append(convert_image_to_array(image_directory))
                    label_list.append(plant_disease_folder)
    print("[INFO] Image loading completed")  
except Exception as e:
    print(f"Error : {e}")

image_size = len(image_list)

#Transform Image Labels uisng Scikit Learn's LabelBinarizer
label_binarizer = LabelBinarizer()
image_labels = label_binarizer.fit_transform(label_list)
pickle.dump(label_binarizer,open('label_transform.pkl', 'wb'))
n_classes = len(label_binarizer.classes_)

#Print the classes
print(label_binarizer.classes_)

#load saved pickle model
loaded_model = pickle.load(open('cnn_model.pkl', 'rb'))
model_disease=loaded_model


#load plant leaf image
image_dir="plantdisease/Validation_Set/Potato___Early_blight/1d301622-e359-49d5-b4ca-6837f254fd1b___RS_Early.B 6719.JPG"

#convert leaf image to arrays
im=convert_image_to_array(image_dir)
np_image_li = np.array(im, dtype=np.float16) / 225.0
npp_image = np.expand_dims(np_image_li, axis=0)

result=model_disease.predict(npp_image)
print(result)

#printing result
itemindex = np.where(result==np.max(result))
print("probability:"+str(np.max(result))+"\n"+label_binarizer.classes_[itemindex[1][0]])