Skip to content

2
22_23-J 07
Commit 86287840 authored by Ekanayake G.B.E.M.K's avatar Ekanayake G.B.E.M.K
Browse files
Options

Add more models

parent 5fe4f1fd
Hide whitespace changes
Inline Side-by-side
Showing with 6135 additions and 0 deletions
Disease Detection - IT19956718/Anomaly_Detection_Image.ipynb 0 → 100644
View file @ 86287840
This source diff could not be displayed because it is too large. You can view the blob instead.
Disease Detection - IT19956718/Mobilenet.ipynb 0 → 100644
View file @ 86287840
This source diff could not be displayed because it is too large. You can view the blob instead.
Disease Detection - IT19956718/Xception change layers.ipynb 0 → 100644
View file @ 86287840
This source diff could not be displayed because it is too large. You can view the blob instead.
Disease Detection - IT19956718/Xception.ipynb 0 → 100644
View file @ 86287840
{
"cells": [
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"data_path = 'data/'\n",
"model_weights = 'disease_classification.h5'\n",
"\n",
"batch_size = 32\n",
"valid_size = 16\n",
"color_mode = 'rgb'\n",
"\n",
"width = 299\n",
"height = 299\n",
"\n",
"target_size = (width, height)\n",
"input_shape = (width, height, 3)\n",
"\n",
"zoom_range = 0.3\n",
"shear_range = 0.3\n",
"shift_range = 0.3\n",
"rotation_range = 30\n",
"\n",
"val_split = 0.2\n",
"\n",
"dense_1 = 512\n",
"dense_2 = 256\n",
"dense_3 = 64\n",
"num_classes = 5\n",
"\n",
"epochs = 100\n",
"rate = 0.2\n",
"\n",
"verbose = 1"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# Data Loader"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'\n",
"\n",
"import cv2 as cv\n",
"import numpy as np\n",
"import pandas as pd\n",
"import tensorflow as tf\n",
"from tensorflow.keras.preprocessing.image import img_to_array"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
"from tensorflow.keras.activations import relu\n",
"from tensorflow.keras.models import Model, load_model\n",
"from tensorflow.keras.layers import Dense, BatchNormalization, Dropout\n",
"############################################################################################\n",
"\n",
"def preprocessing_function(img):\n",
" img = tf.keras.applications.xception.preprocess_input(img)\n",
" return img\n",
"\n",
"def image_data_generator():\n",
" train_datagen = tf.keras.preprocessing.image.ImageDataGenerator(\n",
" rotation_range = rotation_range,\n",
" shear_range = shear_range,\n",
" zoom_range = zoom_range,\n",
" width_shift_range=shift_range,\n",
" height_shift_range=shift_range,\n",
" horizontal_flip = True,\n",
" validation_split= val_split,\n",
" preprocessing_function=preprocessing_function\n",
" )\n",
" test_datagen = tf.keras.preprocessing.image.ImageDataGenerator(\n",
" preprocessing_function=preprocessing_function\n",
" )\n",
"\n",
" train_generator = train_datagen.flow_from_directory(\n",
" data_path,\n",
" target_size = target_size,\n",
" color_mode = color_mode,\n",
" batch_size = batch_size,\n",
" class_mode = 'categorical',\n",
" subset = 'training',\n",
" shuffle = True\n",
" )\n",
"\n",
" validation_generator = train_datagen.flow_from_directory(\n",
" data_path,\n",
" target_size = target_size,\n",
" color_mode = color_mode,\n",
" batch_size = valid_size,\n",
" class_mode = 'categorical',\n",
" subset = 'validation',\n",
" shuffle = True\n",
" )\n",
"\n",
" return train_generator, validation_generator"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Found 4030 images belonging to 6 classes.\n",
"Found 1004 images belonging to 6 classes.\n"
]
},
{
"data": {
"text/plain": [
"{'Caterpillars': 0,\n",
" 'DryingofLeaflets': 1,\n",
" 'Flaccidity': 2,\n",
" 'Leaflets': 3,\n",
" 'Not_Leaf': 4,\n",
" 'Yellowing leaf': 5}"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train_generator, validation_generator = image_data_generator()\n",
"train_generator.class_indices"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [],
"source": [
"class DiseaseClassification(object):\n",
" def __init__(self):\n",
" self.train_generator = train_generator\n",
" self.validation_generator = validation_generator\n",
" self.train_step = self.train_generator.samples // batch_size\n",
" self.validation_step = self.validation_generator.samples // valid_size\n",
"\n",
" self.accuracy = tf.keras.metrics.CategoricalAccuracy()\n",
" self.recall = tf.keras.metrics.Recall()\n",
" self.precision = tf.keras.metrics.Precision()\n",
"\n",
" self.id2disease = {v:k for k, v in self.train_generator.class_indices.items()}\n",
"\n",
" def classifier(self, x):\n",
" if not self.trainable:\n",
" x = Dense(dense_1, activation='relu')(x)\n",
" x = Dense(dense_1)(x)\n",
" x = BatchNormalization()(x)\n",
" x = relu(x)\n",
" x = Dropout(rate)(x)\n",
"\n",
" x = Dense(dense_2, activation='relu')(x)\n",
" x = Dense(dense_2)(x)\n",
" x = BatchNormalization()(x)\n",
" x = relu(x)\n",
" x = Dropout(rate)(x)\n",
"\n",
" x = Dense(dense_3, activation='relu')(x)\n",
" x = Dense(dense_3)(x)\n",
" x = BatchNormalization()(x)\n",
" x = relu(x)\n",
" x = Dropout(rate)(x)\n",
" return x\n",
"\n",
" def model_conversion(self, trainable):\n",
" functional_model = tf.keras.applications.Xception(weights=\"imagenet\")\n",
" functional_model.trainable = trainable\n",
"\n",
" self.trainable = trainable\n",
"\n",
" inputs = functional_model.input\n",
"\n",
" x = functional_model.layers[-2].output\n",
" x = self.classifier(x)\n",
" outputs = Dense(num_classes, activation='softmax')(x)\n",
"\n",
" model = Model(\n",
" inputs=inputs,\n",
" outputs=outputs\n",
" )\n",
" \n",
" self.model = model\n",
" self.model.summary()\n",
"\n",
" def train(self):\n",
" callback = tf.keras.callbacks.EarlyStopping(\n",
" monitor='val_loss', \n",
" patience=5\n",
" )\n",
"\n",
" self.model.compile(\n",
" optimizer='Adam',\n",
" loss='categorical_crossentropy',\n",
" metrics=[\n",
" self.accuracy,\n",
" self.recall,\n",
" self.precision\n",
" ]\n",
" )\n",
" self.model.fit(\n",
" self.train_generator,\n",
" steps_per_epoch= self.train_step,\n",
" validation_data= self.validation_generator,\n",
" validation_steps = self.validation_step,\n",
" epochs=epochs,\n",
" verbose=verbose,\n",
" callbacks=[callback]\n",
" )\n",
"\n",
" def save_model(self):\n",
" self.model.save(model_weights)\n",
"\n",
" def load_model(self):\n",
" self.model = load_model(model_weights)\n",
" self.model.compile(\n",
" optimizer='Adam',\n",
" loss='categorical_crossentropy',\n",
" metrics=[\n",
" self.accuracy,\n",
" self.recall,\n",
" self.precision\n",
" ]\n",
" )\n",
"\n",
" # def predict(self, x):\n",
" # x = preprocessing_function(x)\n",
" # x = np.expand_dims(x, axis=0)\n",
" # P = self.model.predict(x)\n",
" # disease_id = np.argmax(P)\n",
" # disease = self.id2disease[disease_id]\n",
" # return disease\n",
" \n",
" def predict(self, x):\n",
" x = preprocessing_function(x)\n",
" x = np.expand_dims(x, axis=0)\n",
" P = self.model.predict(x)\n",
" disease_id = np.argmax(P)\n",
" disease = self.id2disease[disease_id]\n",
" confidence_score = np.max(P)\n",
" return disease, confidence_score\n",
"\n",
" def process(self):\n",
" if not os.path.exists(model_weights):\n",
" self.model_conversion(False)\n",
" self.train()\n",
" self.save_model()\n",
" \n",
" else:\n",
" self.load_model()"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [],
"source": [
"model = DiseaseClassification()\n",
"model.process()\n"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [],
"source": [
"def retrieve_treatments(disease):\n",
" treatment = pd.read_excel('Disease retrieve treatments.xlsx')\n",
" treatment = treatment[treatment['Folder name'] == disease]\n",
"\n",
" DiseaseNameSinhala = treatment['Disease name in sinhala'].values[0]\n",
" DiseaseNameEnglish = treatment['Disease name in English'].values[0]\n",
" TreatmentInSinhala = treatment['Treatment in Sinhala'].values[0]\n",
" TreatmentInEnglish = treatment['Treatment in English'].values[0]\n",
"\n",
" retreval_dict = {}\n",
" retreval_dict['DiseaseNameSinhala'] = DiseaseNameSinhala\n",
" retreval_dict['DiseaseNameEnglish'] = DiseaseNameEnglish\n",
" retreval_dict['TreatmentInSinhala'] = TreatmentInSinhala\n",
" retreval_dict['TreatmentInEnglish'] = TreatmentInEnglish\n",
"\n",
" return retreval_dict"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"1/1 [==============================] - 0s 241ms/step\n",
"1/1 [==============================] - 0s 166ms/step\n",
"Leaflets\n",
"{'DiseaseNameSinhala': 'ප්ලෙසිස්පා කුරුමිණියා', 'DiseaseNameEnglish': 'Plesispa beetle', 'TreatmentInSinhala': 'පත්\\u200dරවලට සිදු වූ හානිය දැකගත හැකි වන්නේ ගොබය විවෘත වු පසුය . හානිය හා ජීවී සතුන් දක්නට ලැබේ නම් පහත සඳහන් කෘමිනාශකය ඉසිය යුතුය . කාබොසල්ෆාන් ( මාෂල් 20 එස්.සී ) මි.ලී 3 ක් ජලය ලීටරයක දිය කරන්න . LAT ගොබය ප්\\u200dරදේශය හොඳින් තෙමෙන සේ කෘමිනාශකය ඉසීම අත්\\u200dයාවශ්\\u200dයය . නැවතත් මෙම කෘමි හානිය දක්නට ලැබුනහොත් නිර්දේශයට අනුව සති 03 ට පමණ පසු නැවත වරක් කෘමිනාශක ඉසිය යුතුය .', 'TreatmentInEnglish': 'If the damage and the live stages of the pest are observed, spray one of the following insecticides at the given dosage.\\n\\uf0d8\\tCarbosulfan20 SC 3 milliliter in one Liter of water\\n\\uf0d8\\tChlorpyrifos40 EC 3 milliliterofone Liter of water\\nIt is essential to wet the bud region thoroughly while spraying, to allow contact of the insecticide with the pest. If there is a re-infestation repeat the spraying at an interval of 3 weeks as per the recommendation.'}\n"
]
}
],
"source": [
"#Load h5 model\n",
"anomModel = load_model(\"Anomaly_model.h5\")\n",
"\n",
"# Load images for the model\n",
"img_path = 'data/5.jpg'\n",
"img = cv.imread(img_path)\n",
"img = cv.resize(img, (224,224))\n",
"img = img_to_array(img)\n",
"img = img.astype('float32')/255\n",
"\n",
"#Predict\n",
"pred = anomModel.predict(img[np.newaxis,:,:,:])\n",
"pred_class = np.argmax(pred)\n",
"\n",
"if(pred_class == 0):\n",
" img = cv.imread(img_path)\n",
" img = cv.resize(img, target_size)\n",
" P,conf = model.predict(img)\n",
" print(P)\n",
" print(retrieve_treatments(P))\n",
"else:\n",
" print(\"Invalid Image\")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3.10.5 64-bit",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.4"
},
"orig_nbformat": 4,
"vscode": {
"interpreter": {
"hash": "fd15a0266db25af44b6d1d40b652f652a5b83da6f218108c7bbca6f31ae43fc8"
}
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Disease Detection - IT19956718/all.ipynb 0 → 100644
View file @ 86287840
This source diff could not be displayed because it is too large. You can view the blob instead.
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment