Upload 15 files

BackPropogation.py

@@ -0,0 +1,53 @@
+import numpy as np
+from tqdm import tqdm
+
+
+class BackPropogation:
+    def __init__(self,learning_rate=0.01, epochs=100,activation_function='step'):
+        self.bias = 0
+        self.learning_rate = learning_rate
+        self.max_epochs = epochs
+        self.activation_function = activation_function
+
+
+    def activate(self, x):
+        if self.activation_function == 'step':
+            return 1 if x >= 0 else 0
+        elif self.activation_function == 'sigmoid':
+            return 1 if (1 / (1 + np.exp(-x)))>=0.5 else 0
+        elif self.activation_function == 'relu':
+            return 1 if max(0,x)>=0.5 else 0
+
+    def fit(self, X, y):
+        error_sum=0
+        n_features = X.shape[1]
+        self.weights = np.zeros((n_features))
+        for epoch in tqdm(range(self.max_epochs)):
+            for i in range(len(X)):
+                inputs = X[i]
+                target = y[i]
+                weighted_sum = np.dot(inputs, self.weights) + self.bias
+                prediction = self.activate(weighted_sum)
+                
+                # Calculating loss and updating weights.
+                error = target - prediction
+                self.weights += self.learning_rate * error * inputs
+                self.bias += self.learning_rate * error
+                
+            print(f"Updated Weights after epoch {epoch} with {self.weights}")
+        print("Training Completed")
+
+    def predict(self, X):
+        predictions = []
+        for i in range(len(X)):
+            inputs = X[i]
+            weighted_sum = np.dot(inputs, self.weights) + self.bias
+            prediction = self.activate(weighted_sum)
+            predictions.append(prediction)
+        return predictions
+
+
+    
+    
+    
+ 

Perceptron.py

@@ -0,0 +1,46 @@
+import numpy as np
+from tqdm import tqdm
+
+
+class Perceptron:
+    
+    def __init__(self,learning_rate=0.01, epochs=100,activation_function='step'):
+        self.bias = 0
+        self.learning_rate = learning_rate
+        self.max_epochs = epochs
+        self.activation_function = activation_function
+
+
+    def activate(self, x):
+        if self.activation_function == 'step':
+            return 1 if x >= 0 else 0
+        elif self.activation_function == 'sigmoid':
+            return 1 if (1 / (1 + np.exp(-x)))>=0.5 else 0
+        elif self.activation_function == 'relu':
+            return 1 if max(0,x)>=0.5 else 0
+
+    def fit(self, X, y):
+        n_features = X.shape[1]
+        self.weights = np.random.randint(n_features, size=(n_features))
+        for epoch in tqdm(range(self.max_epochs)):
+            for i in range(len(X)):
+                inputs = X[i]
+                target = y[i]
+                weighted_sum = np.dot(inputs, self.weights) + self.bias
+                prediction = self.activate(weighted_sum)
+        print("Training Completed")
+
+    def predict(self, X):
+        predictions = []
+        for i in range(len(X)):
+            inputs = X[i]
+            weighted_sum = np.dot(inputs, self.weights) + self.bias
+            prediction = self.activate(weighted_sum)
+            predictions.append(prediction)
+        return predictions
+
+
+    
+    
+    
+ 

app.py

@@ -0,0 +1,159 @@
+import streamlit as st
+import pickle
+import tensorflow as tf
+from tensorflow.keras.preprocessing import sequence
+from tensorflow.keras.saving import load_model
+import numpy as np
+import cv2
+from PIL import Image
+
+
+st.title('Classifier System')
+task = st.selectbox('Select Task', ['Choose one','Sentiment Classification', 'Tumor Detection'])
+
+if task=='Tumor Detection':
+    st.subheader('Tumor Detection with CNN')
+    # CNN
+    #with open(r"E:\DUK\DUKSEM3\DEEP_LEARNING\ASSIGN1\Multi-Modal_classifier_Image_Classification_Sentiment_Sentiment_Analysis\CNN\cnn_model.pkl",'rb') as file:
+        #cnn_model = pickle.load(file)
+    cnn_model = load_model(r"E:\DUK\DUKSEM3\DEEP_LEARNING\ASSIGN1\Multi-Modal_classifier_Image_Classification_Sentiment_Sentiment_Analysis\CNN\cnn_model1.h5")
+
+    img = st.file_uploader('Upload image', type=['jpeg', 'jpg', 'png'])
+
+    def cnn_make_prediction(img,model):
+        img=Image.open(img)
+        img=img.resize((128,128))
+        img=np.array(img)
+        input_img = np.expand_dims(img, axis=0)
+        res = model.predict(input_img)
+        if res:
+            return "Tumor Detected"
+        else:
+            return "No Tumor Detected"
+        
+    
+    if img is not None:
+        st.image(img, caption = "Image preview")
+        if st.button('Submit'):
+            pred = cnn_make_prediction(img, cnn_model)
+            st.write(pred)
+
+
+if task=='Sentiment Classification':
+    arcs = ['Perceptron', 'Backpropagation', 'DNN', 'RNN', 'LSTM']
+    arc = st.radio('Pick one:', arcs, horizontal=True)
+
+    if arc == arcs[0]:
+        # Perceptron
+        with open(r"E:\DUK\DUKSEM3\DEEP_LEARNING\ASSIGN1\Multi-Modal_classifier_Image_Classification_Sentiment_Sentiment_Analysis\Perceptron\pnn_model.pkl",'rb') as file:
+            perceptron = pickle.load(file)
+        with open(r"E:\DUK\DUKSEM3\DEEP_LEARNING\ASSIGN1\Multi-Modal_classifier_Image_Classification_Sentiment_Sentiment_Analysis\Perceptron\pnn_tokeniser.pkl",'rb') as file:
+            ppn_tokeniser = pickle.load(file)
+
+        def ppn_make_predictions(inp, model):
+            encoded_inp = ppn_tokeniser.texts_to_sequences([inp])
+            padded_inp = sequence.pad_sequences(encoded_inp, maxlen=500)
+            res = model.predict(padded_inp)
+            if res:
+                return "Not spam"
+            else:
+                return "Spam"       
+        
+        st.subheader('SMS spam Classification using Perceptron')
+        inp = st.text_area('Enter message')
+        if st.button('Check'):
+            pred = ppn_make_predictions([inp], perceptron)
+            st.write(pred)
+
+    elif arc == arcs[1]:
+        # BackPropogation
+        with open(r"E:\DUK\DUKSEM3\DEEP_LEARNING\ASSIGN1\Multi-Modal_classifier_Image_Classification_Sentiment_Sentiment_Analysis\BackPropagation\bpn_model.pkl",'rb') as file:
+            backprop = pickle.load(file)
+        with open(r"E:\DUK\DUKSEM3\DEEP_LEARNING\ASSIGN1\Multi-Modal_classifier_Image_Classification_Sentiment_Sentiment_Analysis\BackPropagation\bpn_tokeniser.pkl",'rb') as file:
+            bp_tokeniser = pickle.load(file)
+
+        def bp_make_predictions(inp, model):
+            encoded_inp = bp_tokeniser.texts_to_sequences([inp])
+            padded_inp = sequence.pad_sequences(encoded_inp, maxlen=500)
+            res = model.predict(padded_inp)
+            if res:
+                return "Not spam"
+            else:
+                return "Spam"        
+        
+        st.subheader('SMS spam Classification using Backpropagation')
+        inp = st.text_area('Enter message')
+        if st.button('Check'):
+            pred = bp_make_predictions([inp], backprop)
+            st.write(pred)
+
+
+    elif arc == arcs[2]:
+        # DNN
+        with open(r"E:\DUK\DUKSEM3\DEEP_LEARNING\ASSIGN1\Multi-Modal_classifier_Image_Classification_Sentiment_Sentiment_Analysis\DNN\dnn_model.pkl",'rb') as file:
+            dnn_model = pickle.load(file)
+        with open(r"E:\DUK\DUKSEM3\DEEP_LEARNING\ASSIGN1\Multi-Modal_classifier_Image_Classification_Sentiment_Sentiment_Analysis\DNN\dnn_tokeniser.pkl",'rb') as file:
+            dnn_tokeniser = pickle.load(file)
+
+        def dnn_make_predictions(inp, model):
+            inp = dnn_tokeniser.texts_to_sequences(inp)
+            inp = sequence.pad_sequences(inp, maxlen=500)
+            res = (model.predict(inp) > 0.5).astype("int32")
+            if res:
+                return "Not spam"
+            else:
+                return "Spam"       
+        
+        st.subheader('SMS spam Classification using DNN')
+        inp = st.text_area('Enter message')
+        if st.button('Check'):
+            pred = dnn_make_predictions([inp], dnn_model)
+            st.write(pred)
+
+
+    elif arc == arcs[3]:
+        # RNN 
+        with open(r"E:\DUK\DUKSEM3\DEEP_LEARNING\ASSIGN1\Multi-Modal_classifier_Image_Classification_Sentiment_Sentiment_Analysis\RNN\rnn_model.pkl",'rb') as file:
+            rnn_model = pickle.load(file) 
+
+        with open(r"E:\DUK\DUKSEM3\DEEP_LEARNING\ASSIGN1\Multi-Modal_classifier_Image_Classification_Sentiment_Sentiment_Analysis\RNN\rnn_tokeniser.pkl",'rb') as file:
+            rnn_tokeniser = pickle.load(file)
+
+        def rnn_make_predictions(inp, model):
+            encoded_inp = rnn_tokeniser.texts_to_sequences(inp)
+            padded_inp = sequence.pad_sequences(encoded_inp, maxlen=10, padding='post')
+            res = (model.predict(padded_inp) > 0.5).astype("int32")
+            if res:
+                return "Spam"
+            else:
+                return "Not spam"
+
+        st.subheader('SMS Spam Classification using RNN')
+        inp = st.text_area('Enter message')
+        if st.button('Check'):
+            pred = rnn_make_predictions([inp], rnn_model)
+            st.write(pred)
+    
+
+    elif arc == arcs[4]:
+        # LSTM
+        with open(r"E:\DUK\DUKSEM3\DEEP_LEARNING\ASSIGN1\Multi-Modal_classifier_Image_Classification_Sentiment_Sentiment_Analysis\LSTM\lstm_model.pkl",'rb') as file:
+            lstm_model = pickle.load(file) 
+
+        with open(r"E:\DUK\DUKSEM3\DEEP_LEARNING\ASSIGN1\Multi-Modal_classifier_Image_Classification_Sentiment_Sentiment_Analysis\LSTM\lstm_tokeniser.pkl",'rb') as file:
+            lstm_tokeniser = pickle.load(file)
+
+        def lstm_make_predictions(inp, model):
+            inp = lstm_tokeniser.texts_to_sequences(inp)
+            inp = sequence.pad_sequences(inp, maxlen=500)
+            res = (model.predict(inp) > 0.5).astype("int32")
+            if res:
+                return "Not spam"
+            else:
+                return "Spam"
+
+        st.subheader('SMS spam Classification using LSTM')
+        inp = st.text_area('Enter message')
+        if st.button('Check'):
+            pred = lstm_make_predictions([inp], lstm_model)
+            st.write(pred)  

bpn_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28e032769288ba5475fb55d8f3095a307ef6f78e1cda278aacc141d2aa2f7752
+size 4300

bpn_tokeniser.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:657d8fe699afcd9ade12d4e347319b382aa4565772343845c600785ed97437ed
+size 240973

cnn_model1.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f52777b9061b0891f0b4268c301b2e90b55f9e8bbf3daa1a41e1f5b19982ff45
+size 391811360

dnn_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883c57fdb6f20dad202012747b7dd96299bfc09726c78bc740c4cbeefd9138da
+size 445644

dnn_tokeniser.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fa862ba455ed4f56e64f584ce02928f89540ba001adefc32f3a17cd257dd8e4
+size 287385

lstm_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68d73f50f191f96ee20618e6d076baff7988c7679ce70d090aa2516ffceab2c4
+size 3513113

lstm_tokeniser.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f89d4a5a81f9f1ec173ad953ec5199271650041234e4c108fb3bc211362ebc1
+size 287385

pnn_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bc24f1b71170b633a1c5571b4703287616193588031ae0bff2cab94697a189a
+size 2267

pnn_tokeniser.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:168b7bb3b2abbf09e8d525f91b3779579a0be69a964721fb31a073c869f2b257
+size 287385

requirements.txt

@@ -0,0 +1,5 @@
+tensorflow
+numpy
+pillow
+gdown
+torch

rnn_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc7abc340c0570b7996691fb98d6dfe9e9ee169925416fa31449a4a3c3f13b51
+size 2230438

rnn_tokeniser.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9c66a925743edae19d84670280a8c2d4e5d8fab6e41cdf2912b17817f149cbc
+size 287385