App file created

app.py

@@ -0,0 +1,179 @@
+# -*- coding: utf-8 -*-
+"""lung cancerdetection.ipynb
+
+Automatically generated by Colaboratory.
+
+Original file is located at
+    https://colab.research.google.com/drive/1f7VybSnYLPbUVLRLMNQboxQkCYaBCXMs
+"""
+
+! pip install -q kaggle
+!pip install gradio
+
+from google.colab import files
+
+files.upload()
+
+! mkdir ~/.kaggle
+
+! cp kaggle.json ~/.kaggle/
+
+! chmod 600 ~/.kaggle/kaggle.json
+
+! kaggle datasets list
+
+!kaggle datasets download -d andrewmvd/lung-and-colon-cancer-histopathological-images
+
+!unzip /content/lung-and-colon-cancer-histopathological-images.zip
+
+# This Python 3 environment comes with many helpful analytics libraries installed
+# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python
+# For example, here's several helpful packages to load
+
+import numpy as np # linear algebra
+import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
+
+# Input data files are available in the read-only "../input/" directory
+# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory
+
+import os
+for dirname, _, filenames in os.walk('/kaggle/content'):
+    for filename in filenames:
+        print(os.path.join(dirname, filename))
+
+# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using "Save & Run All" 
+# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session
+
+# importing libraries
+
+import tensorflow as tf
+from tensorflow.keras.layers import Input, Lambda, Dense, Flatten
+from tensorflow.keras.models import Model
+from tensorflow.keras.applications.resnet50 import ResNet50
+from tensorflow.keras.applications.resnet50 import preprocess_input
+from tensorflow.keras.preprocessing import image
+from tensorflow.keras.preprocessing.image import ImageDataGenerator,load_img
+from tensorflow.keras.models import Sequential
+import numpy as np
+from glob import glob
+import matplotlib.pyplot as plt
+
+image_set =  "../content/lung_colon_image_set/lung_image_sets"
+
+SIZE_X = SIZE_Y = 224
+
+datagen = tf.keras.preprocessing.image.ImageDataGenerator(validation_split = 0.2)
+
+train_set = datagen.flow_from_directory(image_set,
+                                       class_mode = "categorical",
+                                       target_size = (SIZE_X,SIZE_Y),
+                                       color_mode="rgb",
+                                       batch_size = 128, 
+                                       shuffle = False,
+                                       subset='training',
+                                       seed = 42)
+
+validate_set = datagen.flow_from_directory(image_set,
+                                       class_mode = "categorical",
+                                       target_size = (SIZE_X, SIZE_Y),
+                                       color_mode="rgb",
+                                       batch_size = 128, 
+                                       shuffle = False,
+                                       subset='validation',
+                                       seed = 42)
+
+from google.colab import drive
+drive.mount('/content/drive')
+
+IMAGE_SIZE = [224, 224]
+
+resnet = ResNet50(input_shape=IMAGE_SIZE + [3], weights='imagenet', include_top=False)
+
+# don't train existing weights
+for layer in resnet.layers:
+    layer.trainable = False
+
+flatten = Flatten()(resnet.output)
+dense = Dense(256, activation = 'relu')(flatten)
+dense = Dense(128, activation = 'relu')(dense)
+prediction = Dense(3, activation = 'softmax')(dense)
+
+#creating a model
+model = Model(inputs = resnet.input, outputs = prediction )
+
+model.summary()
+
+model.compile(loss = 'categorical_crossentropy', optimizer = 'adam', metrics = ['accuracy'])
+
+#executing the model
+history = model.fit_generator(train_set, validation_data = (validate_set), epochs = 5, verbose = 1)
+
+# plotting the loss
+plt.plot(history.history['loss'],label = 'train_loss')
+plt.plot(history.history['val_loss'], label = 'testing_loss')
+plt.title('loss')
+plt.legend()
+plt.show()
+
+# Both Validation and Training accuracy is shown here
+
+plt.plot(history.history['accuracy'], label='training_accuracy')
+plt.plot(history.history['val_accuracy'], label='validation accuracy')
+plt.title('Accuracy')
+plt.legend()
+plt.show()
+
+# CHECKING THE CONFUSION MATRIX
+
+from sklearn.metrics import classification_report
+from sklearn.metrics import confusion_matrix
+from sklearn.metrics import f1_score
+Y_pred = model.predict(validate_set)
+y_pred = np.argmax(Y_pred ,axis =1)
+print('Confusion Matrix')
+confusion_matrix = confusion_matrix(validate_set.classes, y_pred)
+print(confusion_matrix)
+print('Classification Report')
+target_names = ['aca','n', 'scc']
+print(classification_report(validate_set.classes, y_pred, target_names=target_names))
+
+result = model.evaluate(validate_set,batch_size=128)
+print("test_loss, test accuracy",result)
+
+import pickle
+
+with open('model_pkl', 'wb') as files:
+    pickle.dump(model, files)
+
+img = tf.keras.utils.load_img('/content/lung_colon_image_set/lung_image_sets/lung_aca/lungaca1.jpeg', target_size=(224, 224))
+img_array = tf.keras.utils.img_to_array(img)
+img_array = tf.expand_dims(img_array, 0)
+
+# load saved model
+with open('model_pkl' , 'rb') as f:
+    lr = pickle.load(f)
+    predi=lr.predict(img_array)
+    print(predi)
+    image_output_class=target_names[np.argmax(predi)]
+
+print("The predicted class is", image_output_class)
+
+import gradio as gd
+from PIL import Image
+
+target_names = ['aca','n', 'scc']
+
+def greet_user(name):
+    image=gd.inputs.Image()
+    pil_image = Image.fromarray(name.astype('uint8'), 'RGB')
+    pil_image_resized = pil_image.resize((224,224))
+    img_array = tf.keras.utils.img_to_array(pil_image_resized)
+    img_array = tf.expand_dims(img_array, 0)
+    with open('/content/model_pkl' , 'rb') as f:
+        lr = pickle.load(f)
+        predi=lr.predict(img_array)
+        image_output_class=target_names[np.argmax(predi)]
+    return  image_output_class
+
+app =  gd.Interface(fn = greet_user, inputs='image', outputs='text')
+app.launch(share=True,debug=True)