Skip to content

2
22_23-J 21
Commit 55d24997 authored by Karunarathna K.M.D.Y.K's avatar Karunarathna K.M.D.Y.K
Browse files
Options

Merge branch 'master' into IT19975382

parents fd7c6290 069ed7eb
Hide whitespace changes
Inline Side-by-side
Showing with 2198 additions and 1 deletion
BackEnd/Beans_Cassava_Corn_Tomato_Diseases.ipynb 0 → 100644
View file @ 55d24997
This source diff could not be displayed because it is too large. You can view the blob instead.
BackEnd/Saduni_Leaf_Identification.ipynb 0 → 100644
View file @ 55d24997
This source diff could not be displayed because it is too large. You can view the blob instead.
BackEnd/Saduni_Leaf_Identificationv2.ipynb 0 → 100644
View file @ 55d24997
This source diff could not be displayed because it is too large. You can view the blob instead.
BackEnd/Sanduni_Okra_Diseases_Identification.ipynb 0 → 100644
View file @ 55d24997
This source diff could not be displayed because it is too large. You can view the blob instead.
BackEnd/Sanduni_disease_Identification_Okra_updated.ipynb 0 → 100644
View file @ 55d24997
{"cells":[{"cell_type":"markdown","metadata":{"id":"Y2jOdgL3j-o8"},"source":["# 🟨 Getting the Data"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"lDXyIngTMaXf","colab":{"base_uri":"https://localhost:8080/"},"outputId":"0367ec34-3f2b-4efc-ca93-82ae82f77f33","executionInfo":{"status":"ok","timestamp":1681147605246,"user_tz":-330,"elapsed":61704,"user":{"displayName":"Sanduni Rathnayake","userId":"14630985962646048848"}}},"outputs":[{"output_type":"stream","name":"stdout","text":["Mounted at /content/drive\n"]}],"source":["from google.colab import drive\n","drive.mount('/content/drive')"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"t-ZDw43fiy-1"},"outputs":[],"source":["data_location = 'content/drive/MyDrive/research/Okra_diseases.zip'"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"U-MmiQnjF9gG","colab":{"base_uri":"https://localhost:8080/","height":356},"executionInfo":{"status":"error","timestamp":1681147955614,"user_tz":-330,"elapsed":1065,"user":{"displayName":"Sanduni Rathnayake","userId":"14630985962646048848"}},"outputId":"2e08b354-99cc-4ed5-a3c9-3be40dd1fe23"},"outputs":[{"output_type":"error","ename":"FileNotFoundError","evalue":"ignored","traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mFileNotFoundError\u001b[0m Traceback (most recent call last)","\u001b[0;32m<ipython-input-5-2a9895ce9af5>\u001b[0m in \u001b[0;36m<cell line: 3>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mzipfile\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[0;31m#unzip our data\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 3\u001b[0;31m \u001b[0mzip_ref\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mzipfile\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mZipFile\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata_location\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"r\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 4\u001b[0m \u001b[0mzip_ref\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mextractall\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0mzip_ref\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mclose\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/lib/python3.9/zipfile.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, file, mode, compression, allowZip64, compresslevel, strict_timestamps)\u001b[0m\n\u001b[1;32m 1246\u001b[0m \u001b[0;32mwhile\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1247\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1248\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfp\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mio\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mopen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfile\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfilemode\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1249\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mOSError\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1250\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mfilemode\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mmodeDict\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: 'content/drive/MyDrive/research/Okra_diseases.zip'"]}],"source":["import zipfile\n","#unzip our data\n","zip_ref = zipfile.ZipFile(data_location, \"r\")\n","zip_ref.extractall()\n","zip_ref.close()"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"_YdAEKT6GSoX"},"outputs":[],"source":["import os\n","for dirpath , dirnames , filenames in os.walk(\"Okra_diseases\"):\n"," print(f\"There are {len(dirnames)} directories and {len(filenames)} images in '{dirpath}'.\")"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"gLo3FV6OGVP0","colab":{"base_uri":"https://localhost:8080/"},"outputId":"36736836-f814-4e7e-e879-fd0272e96f27","executionInfo":{"status":"ok","timestamp":1681148090040,"user_tz":-330,"elapsed":630,"user":{"displayName":"Sanduni Rathnayake","userId":"14630985962646048848"}}},"outputs":[{"output_type":"stream","name":"stdout","text":["[]\n"]}],"source":["train_dir = \"Okra_diseases/Training\"\n","test_dir = \"Okra_diseases/Testing\"\n","\n","#lets get the class names\n","import pathlib\n","import numpy as np\n","\n","data_dir = pathlib.Path(train_dir)\n","class_names = np.array(sorted([item.name for item in data_dir.glob('*')]))\n","print(class_names)"]},{"cell_type":"markdown","metadata":{"id":"HvDEsB_fj7_7"},"source":["# 🟨 Data Visualization"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"vVCpvSuKlGG1"},"outputs":[],"source":["import matplotlib.pyplot as plt\n","import matplotlib.image as mpimg\n","import random\n","import os\n","\n","def view_random_image(target_dir , target_class):\n"," target_folder = target_dir+\"/\"+target_class\n"," random_image = random.sample(os.listdir(target_folder) ,1)\n","\n"," img = mpimg.imread(target_folder+\"/\"+random_image[0])\n"," plt.imshow(img)\n"," plt.title(target_class)\n"," plt.axis(\"off\")\n","\n"," print(f\"Image Shape:{img.shape}\") \n","\n"," return img"]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":321},"id":"tVx10O9CGXn2","outputId":"ef6b2816-6ea2-4382-d1a2-b7c96edac192","executionInfo":{"status":"error","timestamp":1681148102389,"user_tz":-330,"elapsed":875,"user":{"displayName":"Sanduni Rathnayake","userId":"14630985962646048848"}}},"outputs":[{"output_type":"error","ename":"IndexError","evalue":"ignored","traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mIndexError\u001b[0m Traceback (most recent call last)","\u001b[0;32m<ipython-input-9-c8fbca14f51a>\u001b[0m in \u001b[0;36m<cell line: 2>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mrandom\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2\u001b[0m img = view_random_image(target_dir=train_dir , \n\u001b[0;32m----> 3\u001b[0;31m target_class = random.choice(class_names))\n\u001b[0m","\u001b[0;32m/usr/lib/python3.9/random.py\u001b[0m in \u001b[0;36mchoice\u001b[0;34m(self, seq)\u001b[0m\n\u001b[1;32m 344\u001b[0m \u001b[0;34m\"\"\"Choose a random element from a non-empty sequence.\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 345\u001b[0m \u001b[0;31m# raises IndexError if seq is empty\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 346\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mseq\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_randbelow\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mseq\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 347\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 348\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mshuffle\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrandom\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;31mIndexError\u001b[0m: index 0 is out of bounds for axis 0 with size 0"]}],"source":["import random\n","img = view_random_image(target_dir=train_dir , \n"," target_class = random.choice(class_names))"]},{"cell_type":"markdown","metadata":{"id":"RFJbEeyUlUgn"},"source":["# 🟨 DATA Preprocessing"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"8uTOAKV80c_S"},"outputs":[],"source":["def to_grayscale_then_rgb(image):\n"," image = tf.image.rgb_to_grayscale(image)\n"," image = tf.image.grayscale_to_rgb(image)\n"," return image"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"oIC5RKBhG-t-"},"outputs":[],"source":["from tensorflow.keras.preprocessing.image import ImageDataGenerator\n","\n","#Creating Image Data Generators for Training Data with augmentation\n","train_data_gen = ImageDataGenerator(rescale=1/255.,\n"," #preprocessing_function=to_grayscale_then_rgb,\n"," rotation_range = 0.2,\n"," shear_range = 0.2,\n"," zoom_range = 0.2,\n"," width_shift_range=0.3,\n"," height_shift_range = 0.3,\n"," horizontal_flip= True)\n","\n","#Create ImageDatagenerator for testing data\n","test_data_gen = ImageDataGenerator(rescale=1/255. \n"," #preprocessing_function=to_grayscale_then_rgb\n"," )\n","\n","#Import and Transform/pre process the data\n","train_data_multi = train_data_gen.flow_from_directory(train_dir,\n"," target_size = (448,448),\n"," batch_size = 16,\n"," class_mode = 'categorical',\n"," shuffle = True)\n","test_data_multi = test_data_gen.flow_from_directory(test_dir,\n"," target_size = (448, 448),\n"," batch_size = 16,\n"," class_mode = 'categorical', #This will gives us one-hot encoded data\n"," shuffle = True)"]},{"cell_type":"markdown","source":["#TransferLoearning Models\n"],"metadata":{"id":"z_3CSlVYgcU7"}},{"cell_type":"code","source":["efficientnetb7_url = \"https://tfhub.dev/tensorflow/efficientnet/b7/feature-vector/1\"\n","resnet_v2_50_url = \"https://tfhub.dev/google/imagenet/resnet_v2_50/feature_vector/5\"\n","inception_v3_url = \"https://tfhub.dev/google/tf2-preview/inception_v3/feature_vector/4\"\n","resnet_152_v2_url = \"https://tfhub.dev/google/imagenet/resnet_v2_152/feature_vector/5\"\n","mobileNetv3_url = \"https://tfhub.dev/google/imagenet/mobilenet_v1_025_224/feature_vector/5\"\n"],"metadata":{"id":"UMfVmghAgha4"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["import tensorflow as tf\n","import tensorflow_hub as hub\n","from tensorflow.keras import layers\n","def create_model(model_url , num_classes=7):\n","\n"," feature_extractor_layer = hub.KerasLayer(model_url,\n"," trainable = False, #freeze the already learned patterns \n"," name = \"feature_extraction_layer\",\n"," input_shape = (448, 448,3)) \n"," #Create our own model\n"," model = tf.keras.Sequential([\n"," feature_extractor_layer,\n"," layers.Dense(num_classes , activation=\"softmax\" , name=\"output_layer\")\n"," ])\n","\n"," return model"],"metadata":{"id":"cO9abOkFgnNs"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":["# 01 - efficientnetb7_"],"metadata":{"id":"rX3XVcMpgoPE"}},{"cell_type":"code","source":["efficientnetb7_model = create_model(efficientnetb7_url , \n"," num_classes = 2)\n","efficientnetb7_model.compile(loss='categorical_crossentropy',\n"," optimizer = tf.keras.optimizers.Adam(),\n"," metrics=[\"accuracy\"])\n","\n","efficientnetb7_hist = efficientnetb7_model.fit(train_data_multi,\n"," epochs=5,\n"," steps_per_epoch=len(train_data_multi),\n"," validation_data = test_data_multi,\n"," validation_steps = len(test_data_multi)\n"," )"],"metadata":{"id":"HzB5iBCig11l"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["efficientnetb7_model.save('/content/drive/MyDrive/research/private/save_models/Okra_diseases_efficientnetb7.h5')"],"metadata":{"id":"eTHdQekBuSoD"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":["# 02 - resnet_v2_50"],"metadata":{"id":"-zsedWS-u5VT"}},{"cell_type":"code","source":["resnet_v2_50_model = create_model(resnet_v2_50_url , \n"," num_classes = 2)\n","resnet_v2_50_model.compile(loss='categorical_crossentropy',\n"," optimizer = tf.keras.optimizers.Adam(),\n"," metrics=[\"accuracy\"])\n","\n","resnet_v2_50_hist = resnet_v2_50_model.fit(train_data_multi,\n"," epochs=1,\n"," steps_per_epoch=len(train_data_multi),\n"," validation_data = test_data_multi,\n"," validation_steps = len(test_data_multi)\n"," )"],"metadata":{"id":"lqYx2WVNvAh6"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["resnet_v2_50_model.save('/content/drive/MyDrive/research/private/save_models/Okra_diseases_resnet_v2_50.h5')"],"metadata":{"id":"mc0hnm08x0-k"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":["# 03 - inception_v3"],"metadata":{"id":"lteOh74Hxcnr"}},{"cell_type":"code","source":["inception_v3_model = create_model(inception_v3_url , \n"," num_classes = 2)\n","inception_v3_model.compile(loss='categorical_crossentropy',\n"," optimizer = tf.keras.optimizers.Adam(),\n"," metrics=[\"accuracy\"])\n","\n","inception_v3_hist = inception_v3_model.fit(train_data_multi,\n"," epochs=1,\n"," steps_per_epoch=len(train_data_multi),\n"," validation_data = test_data_multi,\n"," validation_steps = len(test_data_multi)\n"," )"],"metadata":{"id":"45K34_uzxf3C"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["inception_v3_model.save('/content/drive/MyDrive/research/private/save_models/Okra_diseases_inception_v3.h5')"],"metadata":{"id":"5SxvrQ6Txlxo"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":["# 04 - resnet_152_v2 "],"metadata":{"id":"GbyS-F1NzXLb"}},{"cell_type":"code","source":["resnet_152_v2_model = create_model(resnet_152_v2_url , \n"," num_classes = 2)\n","resnet_152_v2_model.compile(loss='categorical_crossentropy',\n"," optimizer = tf.keras.optimizers.Adam(),\n"," metrics=[\"accuracy\"])\n","resnet_152_v2_hist = resnet_152_v2_model.fit(train_data_multi,\n"," epochs=1,\n"," steps_per_epoch=len(train_data_multi),\n"," validation_data = test_data_multi,\n"," validation_steps = len(test_data_multi)\n"," )"],"metadata":{"id":"v-AOU2_4zbdy"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["resnet_152_v2_model.save('/content/drive/MyDrive/research/private/save_models/Okra_diseases_resnet_152_v2.h5')"],"metadata":{"id":"BjfGnetqzcza"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":["# 05 - Mobile Net"],"metadata":{"id":"VL76DAJATZPz"}},{"cell_type":"code","source":["mobileNetv3_model = create_model(mobileNetv3_url , \n"," num_classes = 2)\n","mobileNetv3_model.compile(loss='categorical_crossentropy',\n"," optimizer = tf.keras.optimizers.Adam(),\n"," metrics=[\"accuracy\"])\n","\n","mobileNetv3_hist = mobileNetv3_model.fit(train_data_multi,\n"," epochs=1,\n"," steps_per_epoch=len(train_data_multi),\n"," validation_data = test_data_multi,\n"," validation_steps = len(test_data_multi)\n"," )"],"metadata":{"id":"pZrZ-ekXT4gU"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":["#PLOTS"],"metadata":{"id":"dd5VJMBEr-iq"}},{"cell_type":"code","source":["def plot_loss_curve(history):\n"," '''\n"," Return separate loss curves for training and validation metrics\n"," '''\n"," loss = history.history[\"loss\"]\n"," val_loss = history.history[\"val_loss\"]\n","\n"," accuracy = history.history[\"accuracy\"]\n"," val_accuracy = history.history[\"val_accuracy\"]\n","\n"," #get the number of epochs that we run for\n"," epochs = range(len(history.history[\"loss\"]))\n","\n"," #Plot the lost\n"," plt.plot(epochs , loss , label=\"Training Loss\")\n"," plt.plot(epochs , val_loss , label=\"Validation Loss\")\n"," plt.title(\"Loss\")\n"," plt.xlabel(\"Epochs\")\n"," plt.legend()\n","\n"," #Plot the accuracy\n"," plt.figure()\n"," plt.plot(epochs , accuracy , label=\"Training accuracy\")\n"," plt.plot(epochs , val_accuracy , label=\"Validation accuracy\")\n"," plt.title(\"accuracy\")\n"," plt.xlabel(\"Epochs\")\n"," plt.legend()\n"],"metadata":{"id":"bb6t1J5NsB5-"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["plot_loss_curve(mobileNetv3_hist)"],"metadata":{"id":"fQ97QRodq06f"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"gx3orjVQMLLt"},"source":["#Make Predictions"]},{"cell_type":"code","source":["#Create a function to improt an image and resize it to be able to used with our model\n","def load_and_prep_image(filename , img_shape=224):\n"," \"\"\"\n"," Reads an image from file name , turns it into a tensor and reshapes it to (img_shape , color_channel\n"," \"\"\"\n"," print('FILe Name type - ', type(filename))\n"," #Read in the image\n"," img = tf.io.read_file(filename)\n"," print('img 1- ', type(img))\n","\n"," #Decode the read file into a tensor\n"," img = tf.image.decode_image(img)\n"," print('img 2- ', type(img))\n","\n"," #Resiz the Image\n"," img = tf.image.resize(img , size=[img_shape , img_shape])\n","\n"," #Re scale the image - get all values between 0 and 255\n"," img = img/255.\n","\n"," return img\n"],"metadata":{"id":"0AiHHV3BhBjK"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["def pred_and_plot(model, filename , class_names = class_names):\n"," \"\"\"\n"," Import an image located at filename , makes a prediction with model,\n"," and plot the image with the prediced class as the title\n"," \"\"\"\n"," #Import the target image and pre-process\n"," img = load_and_prep_image(filename)\n"," print('FILe Name type - ', type(filename))\n","\n"," #Make a Prediction\n"," pred = model.predict(tf.expand_dims(img , axis=0))\n","\n"," #Get the predicted class\n"," pred_class = class_names[np.argmax(tf.round(pred))]\n","\n"," #Plot the image and the predicted class\n"," plt.imshow(img)\n"," plt.title(f\"Prediction :{pred_class}\")\n"," plt.axis(False)\n","\n"," "],"metadata":{"id":"NJWZDQ58hV_T"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["image_path = \"/content/Leaf_Identification/Testing/Corn/RS_Rust 1570.JPG\"\n","pred_and_plot(resnet_model , image_path)"],"metadata":{"id":"OyOk8CB_hbDi"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["image_path2 = \"/content/Leaf_Identification/Testing/Cassava/1616768383552.jpg\"\n","pred_and_plot(resnet_model , image_path2)"],"metadata":{"id":"L0aoGSOX_zkG"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["image_path3 = \"/content/Leaf_Identification/Testing/Beans/angular_leaf_spot_23.jpg\"\n","pred_and_plot(resnet_model , image_path3)"],"metadata":{"id":"13h_bFKo_9SN"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["image_path4 = \"/content/Leaf_Identification/Testing/Okra/20210607_164357.jpg\"\n","pred_and_plot(resnet_model , image_path4)"],"metadata":{"id":"yIR2nFWnAGDo"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["image_path5 = \"/content/Leaf_Identification/Testing/Tomato/0ff228a7-60f4-47f0-b1a3-96969a63105f___GCREC_Bact.Sp 6056.JPG\"\n","pred_and_plot(resnet_model , image_path5)"],"metadata":{"id":"rZBWANZuAUPg"},"execution_count":null,"outputs":[]}],"metadata":{"accelerator":"GPU","colab":{"provenance":[]},"gpuClass":"standard","kernelspec":{"display_name":"Python 3","name":"python3"},"language_info":{"name":"python"}},"nbformat":4,"nbformat_minor":0}
\ No newline at end of file
BackEnd/Test.txt
View file @ 55d24997
IC
\ No newline at end of file
changed
\ No newline at end of file
BackEnd/deep_transfer_cnn_classifier.py 0 → 100644
View file @ 55d24997
# -*- coding: utf-8 -*-
"""deep_transfer_cnn_classifier.ipynb
Automatically generated by Colaboratory.
Original file is located at
https://colab.research.google.com/drive/1hZV9IeMob8g41niThWxjhhyHh37jOY40
"""
class DeepCNNClassifier:
def __init__(self , dataset_link , model_name):
self.dataset_link = dataset_link
self.model_name = model_name
self.number_of_classes = 2 #Default
#---------------------------------------------------SHOULD_CALL_BY_USER------------------------------------------------------------------------------
def extract_dataset(self):
import zipfile
import os
destination_path = '/content'
zip_ref = zipfile.ZipFile(self.dataset_link, "r")
extracted = zip_ref.namelist()
zip_ref.extractall(destination_path)
zip_ref.close()
extracted_file = os.path.join(destination_path, extracted[0])
print("=========== Dataset Extracted to - {}===========".format(extracted_file))
self.extracted_file_path = extracted_file
#return extracted_file
#---------------------------------------------------SHOULD_CALL_BY_USER------------------------------------------------------------------------------
def set_details(self , train_dir , test_dir , transfer_model_url = None , image_height= 224 , image_width = 224 , isGrayScale = False):
self.train_dir = train_dir
self.test_dir = test_dir
self.transfer_model_url = transfer_model_url
self.image_height =image_height
self.image_width = image_width
self.isGrayScale = isGrayScale
if(self.isGrayScale):
self.num_color_channels = 1
else:
self.num_color_channels = 3
print("=========== Train/Test Directories Configured===========")
#---------------------------------------------------SHOULD_CALL_BY_USER------------------------------------------------------------------------------
def show_dataset_summary(self):
import os
for dirpath , dirnames , filenames in os.walk(self.extracted_file_path):
print(f"-->{len(dirnames)} directories AND {len(filenames)} images in '{dirpath}'.")
#----------------------------------------------------WILL_USE_BY_ANOTHER_FUNCTION-----------------------------------------------------------------------------
def get_class_names(self):
import pathlib
import numpy as np
data_dir = pathlib.Path(self.train_dir)
class_names = np.array(sorted([item.name for item in data_dir.glob('*')]))
print("=========== Class Names Obtained - {} ".format(class_names))
self.class_names = class_names
self.number_of_classes = len(class_names)
#---------------------------------------------------SHOULD_CALL_BY_USER------------------------------------------------------------------------------
def view_random_image(self):
self.get_class_names()
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
import random
import os
target_dir = self.train_dir
target_class = random.choice(self.class_names)
target_folder = target_dir+"/"+target_class
random_image = random.sample(os.listdir(target_folder) ,1)
img = mpimg.imread(target_folder+"/"+random_image[0])
plt.imshow(img)
plt.title(target_class)
plt.axis("off")
print(f"Image Shape:{img.shape}")
#----------------------------------------------------WILL_USE_BY_ANOTHER_FUNCTION-----------------------------------------------------------------------------
def preprocess_dataset(self):
print("=========== Data Pre-Processing Started ===========")
from tensorflow.keras.preprocessing.image import ImageDataGenerator
import tensorflow as tf
PRE_RPOCESS_FUNC = None
CLASS_MODE = 'binary'
def to_grayscale_then_rgb(image):
image = tf.image.rgb_to_grayscale(image)
image = tf.image.grayscale_to_rgb(image)
return image
if(self.isGrayScale):
print("=========== Training will use GrayScale Images !!!")
PRE_RPOCESS_FUNC = to_grayscale_then_rgb
if(self.number_of_classes >2):
CLASS_MODE = 'categorical'
train_data_gen = ImageDataGenerator(rescale=1/255.,
preprocessing_function= PRE_RPOCESS_FUNC,
rotation_range = 0.2,
shear_range = 0.2,
zoom_range = 0.2,
width_shift_range=0.3,
height_shift_range = 0.3,
horizontal_flip= True)
test_data_gen = ImageDataGenerator(rescale=1/255. ,
preprocessing_function=PRE_RPOCESS_FUNC)
#Import and Transform/pre process the data
train_data_ = train_data_gen.flow_from_directory(self.train_dir,
target_size = (self.image_height,self.image_width),
batch_size = 32,
class_mode = CLASS_MODE,
shuffle = True)
test_data_ = test_data_gen.flow_from_directory(self.test_dir,
target_size = (self.image_height, self.image_width),
batch_size = 32,
class_mode = CLASS_MODE, #This will gives us one-hot encoded data
shuffle = True)
print("=========== Data Pre-Processing Completed ===========")
return (train_data_ , test_data_)
#----------------------------------------------------WILL_USE_BY_ANOTHER_FUNCTION-----------------------------------------------------------------------------
def create_model(self):
import tensorflow as tf
import tensorflow_hub as hub
from tensorflow.keras import layers
#Download the pretrained model and save it as a keras layer
feature_extractor_layer = hub.KerasLayer(self.transfer_model_url,
trainable = False, #freeze the already learned patterns
name = "feature_extraction_layer",
input_shape = (self.image_height, self.image_width, self.num_color_channels))
self.activation_func = 'sigmoid'
if(self.number_of_classes > 2):
self.activation_func = 'softmax'
model = tf.keras.Sequential([
feature_extractor_layer,
layers.Dense(self.number_of_classes , activation= self.activation_func , name="output_layer")
])
print("=========== Model is Created ==========")
return model
#---------------------------------------------------SHOULD_CALL_BY_USER------------------------------------------------------------------------------
def start_training(self , num_epochs = 5):
import tensorflow as tf
train_data_ , test_data_ = self.preprocess_dataset()
cnn_model = self.create_model()
self.loss_function = 'binary_crossentropy'
if(self.number_of_classes > 2):
self.loss_function = 'categorical_crossentropy'
cnn_model.compile(loss=self.loss_function,
optimizer = tf.keras.optimizers.Adam(),
metrics=["accuracy"])
print("=========== Model Compiled SuccessFully ==========")
model_hist = cnn_model.fit(train_data_,
epochs=num_epochs,
steps_per_epoch=len(train_data_),
validation_data = test_data_,
validation_steps = len(test_data_))
print("=========== Model Trained SuccessFully ==========")
self.trained_model = cnn_model
self.model_train_history = model_hist
return cnn_model
#---------------------------------------------------SHOULD_CALL_BY_USER------------------------------------------------------------------------------
def save_model(self, save_to_path = '/content'):
model_name = str(self.model_name)+".h5"
model = self.trained_model
model.save(model_name)
print("=========== Model Saved to --> {}".format(model_name))
#---------------------------------------------------SHOULD_CALL_BY_USER / Function------------------------------------------------------------------------------
def plot_loss_curves(self, ):
import matplotlib.pyplot as plt
history = self.model_train_history
loss = history.history["loss"]
val_loss = history.history["val_loss"]
accuracy = history.history["accuracy"]
val_accuracy = history.history["val_accuracy"]
#get the number of epochs that we run for
epochs = range(len(history.history["loss"]))
#Plot the lost
plt.plot(epochs , loss , label="Training Loss")
plt.plot(epochs , val_loss , label="Validation Loss")
plt.title("Loss")
plt.xlabel("Epochs")
plt.legend()
#Plot the accuracy
plt.figure()
plt.plot(epochs , accuracy , label="Training accuracy")
plt.plot(epochs , val_accuracy , label="Validation accuracy")
plt.title("accuracy")
plt.xlabel("Epochs")
plt.legend()
#----------------------------------------------------WILL_USE_BY_ANOTHER_FUNCTION-----------------------------------------------------------------------------
def load_and_prep_image(self, filename):
import tensorflow as tf
img = tf.io.read_file(filename)
img = tf.image.decode_image(img)
#Resiz the Image
img = tf.image.resize(img , size=[self.image_height , self.image_width])
#Re scale the image - get all values between 0 and 255
img = img/255.
return img
#---------------------------------------------------SHOULD_CALL_BY_USER------------------------------------------------------------------------------
def pred_and_plot(self, filename):
import tensorflow as tf
import matplotlib.pyplot as plt
import numpy as np
model = self.trained_model
class_names = self.class_names
img = self.load_and_prep_image(filename)
pred = model.predict(tf.expand_dims(img , axis=0))
pred_class = class_names[np.argmax(tf.round(pred))]
#Plot the image and the predicted class
plt.imshow(img)
plt.title(f"Prediction :{pred_class}")
plt.axis(False)
FrontEnd/lib/models/error_model.dart 0 → 100644
View file @ 55d24997
class ErrorModel {
static String errorMessage = 'Something went wrong , please try again';
}
FrontEnd/lib/screens/login.dart 0 → 100644
View file @ 55d24997
import 'package:flutter/gestures.dart';
import 'package:flutter/material.dart';
import 'package:govimithura/constants/user_types.dart';
import 'package:govimithura/models/error_model.dart';
import 'package:govimithura/providers/authentication_provider.dart';
import 'package:govimithura/screens/admin_home.dart';
import 'package:govimithura/screens/forget_password.dart';
import 'package:govimithura/screens/register.dart';
import 'package:govimithura/utils/loading_overlay.dart';
import 'package:govimithura/utils/screen_size.dart';
import 'package:govimithura/utils/utils.dart';
import 'package:govimithura/widgets/utils/buttons/custom_elevated_button.dart';
import 'package:govimithura/widgets/utils/common_widget.dart';
import 'package:govimithura/widgets/utils/text_fields/primary_textfield.dart';
import 'package:provider/provider.dart';
import 'home.dart';
class LoginScreen extends StatefulWidget {
const LoginScreen({super.key});
@override
State<LoginScreen> createState() => _LoginScreenState();
}
class _LoginScreenState extends State<LoginScreen> {
late AuthenticationProvider pAuthentication;
GlobalKey<FormState> loginFormKey = GlobalKey<FormState>();
@override
void initState() {
super.initState();
pAuthentication =
Provider.of<AuthenticationProvider>(context, listen: false);
}
@override
Widget build(BuildContext context) {
return Scaffold(
body: SingleChildScrollView(
child: SizedBox(
height: ScreenSize.height,
width: ScreenSize.width,
child: Form(
key: loginFormKey,
child: Column(
mainAxisSize: MainAxisSize.max,
mainAxisAlignment: MainAxisAlignment.center,
children: [
Padding(
padding: const EdgeInsets.symmetric(horizontal: 20),
child: Column(
children: [
const LogoText(),
spacingWidget(30, SpaceDirection.vertical),
Text(
'Welcome again to Govimithura',
style: Theme.of(context).textTheme.titleLarge,
),
spacingWidget(20, SpaceDirection.vertical),
PrimaryTextField(
hintText: "Enter your email",
validator: (value) {
if (value == null || value.isEmpty) {
return 'Required';
} else if (!(value.contains("@") &&
value.contains("."))) {
return 'Enter valid Email Address';
}
return null;
},
onChanged: (value) {
pAuthentication.setEmail(value.trim());
},
),
spacingWidget(20, SpaceDirection.vertical),
PrimaryTextField(
isPassword: true,
hintText: "Enter password",
validator: (value) {
if (value == null || value.isEmpty) {
return 'Required';
}
return null;
},
onChanged: (value) {
pAuthentication.setPassWord(value.trim());
},
),
spacingWidget(10, SpaceDirection.vertical),
GestureDetector(
onTap: () {
Navigator.push(
context,
MaterialPageRoute(
builder: (_) => const ForgetPasswordScreen(),
),
);
},
child: const Align(
alignment: Alignment.centerRight,
child: Text(
'Forgot Password?',
style: TextStyle(
fontSize: 15,
),
textAlign: TextAlign.end,
),
),
),
spacingWidget(20, SpaceDirection.vertical),
CustomElevatedButton(
text: "Login",
onPressed: () async {
if (loginFormKey.currentState!.validate()) {
bool success = await LoadingOverlay.of(context)
.during(pAuthentication.login());
if (success) {
if (mounted) {
Navigator.pushReplacement(
context,
MaterialPageRoute(
builder: (_) =>
pAuthentication.authModel.userType ==
UserType.user
? const Home()
: const AdminHome(),
),
);
}
} else {
if (mounted) {
Utils.showDialogBox(
context, ErrorModel.errorMessage);
}
}
}
},
),
spacingWidget(20, SpaceDirection.vertical),
RichText(
text: TextSpan(
text: "Don't have an account? ",
style: Theme.of(context).textTheme.bodyLarge,
children: [
TextSpan(
text: "Sign Up",
style: Theme.of(context)
.textTheme
.bodyLarge
?.copyWith(
color: Theme.of(context).primaryColor,
),
recognizer: TapGestureRecognizer()
..onTap = () {
Navigator.pushReplacement(
context,
MaterialPageRoute(
builder: (context) =>
const RegisterScreen(),
),
);
},
),
],
),
)
],
),
),
],
),
),
),
),
);
}
}
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