Add files via upload

Below I have added the dataset link
"https://www.kaggle.com/shadabhussain/automated-image-captioning-flickr8/data"

Author: Balajichandra

Image Captioning with Resnet50.ipynb

@@ -0,0 +1,154 @@
+from flask import Flask, render_template, request
+import cv2
+from keras.models import load_model
+import numpy as np
+from keras.applications import ResNet50
+from keras.optimizers import Adam
+from keras.layers import Dense, Flatten,Input, Convolution2D, Dropout, LSTM, TimeDistributed, Embedding, Bidirectional, Activation, RepeatVector,Concatenate
+from keras.models import Sequential, Model
+from keras.utils import np_utils
+from keras.preprocessing import image, sequence
+import cv2
+from keras.preprocessing.sequence import pad_sequences
+import tensorflow
+from tqdm import tqdm
+from keras.applications import resnet50
+from werkzeug.utils import secure_filename
+import os
+from tensorflow.compat.v1 import ConfigProto
+from tensorflow.compat.v1 import InteractiveSession
+
+config = ConfigProto()
+config.gpu_options.per_process_gpu_memory_fraction = 0.5
+config.gpu_options.allow_growth = True
+session = InteractiveSession(config=config)
+
+vocab = np.load('vocab.npy', allow_pickle=True)
+#vocab = np.load('C:\\Users\\Balaji\\Documents\\Machine Learning\\Deep Learning\\Image Captioning\\Flickr_Data\\Flickr_Data\vocab.npy',allow_pickle=True)
+vocab = vocab.item()
+
+inv_vocab = {v:k for k,v in vocab.items()}
+
+
+#print("+"*50)
+#print("vocabulary loaded")
+
+
+embedding_size = 128
+vocab_size = len(vocab)
+max_len = 40
+
+
+image_model = Sequential()
+
+image_model.add(Dense(embedding_size, input_shape=(2048,), activation='relu'))
+image_model.add(RepeatVector(max_len))
+
+
+language_model = Sequential()
+
+language_model.add(Embedding(input_dim=vocab_size, output_dim=embedding_size, input_length=max_len))
+language_model.add(LSTM(256, return_sequences=True))
+language_model.add(TimeDistributed(Dense(embedding_size)))
+
+
+conca = Concatenate()([image_model.output, language_model.output])
+x = LSTM(128, return_sequences=True)(conca)
+x = LSTM(512, return_sequences=False)(x)
+x = Dense(vocab_size)(x)
+out = Activation('softmax')(x)
+model = Model(inputs=[image_model.input, language_model.input], outputs = out)
+
+model.compile(loss='categorical_crossentropy', optimizer='RMSprop', metrics=['accuracy'])
+
+model.load_weights('C:\\Users\\Balaji\\Documents\\Machine Learning\\Deep Learning\\Image Captioning\\Flickr_Data\\Flickr_Data\\model.h5')
+
+print("="*150)
+print("MODEL LOADED")
+
+resnet = ResNet50(include_top=False,weights='imagenet',input_shape=(224,224,3),pooling='avg')
+
+
+#resnet = load_model('resnet.h5')
+
+print("="*150)
+print("RESNET MODEL LOADED")
+
+
+
+
+app = Flask(__name__)
+
+app.config['SEND_FILE_MAX_AGE_DEFAULT'] = 1
+
+
+@app.route('/')
+def index():
+    return render_template('index.html')
+
+@app.route('/after', methods=['GET', 'POST'])
+def after():
+
+    global model, resnet, vocab, inv_vocab
+
+    f = request.files['file1']
+#'C:\\Users\\Balaji\\Documents\\Machine Learning\Deep Learning\Image Captioning\\Flickr_Data\\Flickr_Data
+    basepath = "C:\\Users\\Balaji\\Documents\\Machine Learning\Deep Learning\\Image Captioning\\Flickr_Data\\Flickr_Data\\Images"
+    file_path = os.path.join(basepath, secure_filename(f.filename))
+    f.save(file_path)
+
+    print("="*50)
+    print("IMAGE SAVED")
+
+
+    
+    image = cv2.imread(file_path)
+    image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+
+    image = cv2.resize(image, (224,224))
+
+    image = np.reshape(image, (1,224,224,3))
+
+    
+    
+    incept = resnet.predict(image).reshape(1,2048)
+
+    print("="*50)
+    print("Predict Features")
+
+
+    text_in = ['startofseq']
+
+    final = ''
+
+    print("="*50)
+    print("GETING Captions")
+
+    count = 0
+    while tqdm(count < 20):
+
+        count += 1
+
+        encoded = []
+        for i in text_in:
+            encoded.append(vocab[i])
+
+        padded = pad_sequences([encoded], maxlen=max_len, padding='post', truncating='post').reshape(1,max_len)
+
+        sampled_index = np.argmax(model.predict([incept, padded]))
+
+        sampled_word = inv_vocab[sampled_index]
+
+        if sampled_word != 'endofseq':
+            final = final + ' ' + sampled_word
+
+        text_in.append(sampled_word)
+
+
+
+    return render_template('after.html', data=final)
+
+if __name__ == "__main__":
+    app.run(debug=False,threaded=False)
+
+

app.py

@@ -0,0 +1,22 @@
+{%extends "base.html"%}
+    
+{%block content%}
+
+<center>
+
+	<h1 class='display-2'>Predicted Caption </h1>
+
+	<br>
+	<br>
+	
+<img src="{{url_for('static', filename='file.jpg')}}" alt="image" height=340px>
+
+<br>
+
+<h2 class='text-white'>
+	{{data}}
+</h2>
+
+</center>
+
+{%endblock%}

templates/after.html

@@ -0,0 +1,30 @@
+<!doctype html>
+<html lang="en">
+  <head>
+    <!-- Required meta tags -->
+    <meta charset="utf-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
+
+    <!-- Bootstrap CSS -->
+    <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.5.2/css/bootstrap.min.css" integrity="sha384-JcKb8q3iqJ61gNV9KGb8thSsNjpSL0n8PARn9HuZOnIxN0hoP+VmmDGMN5t9UJ0Z" crossorigin="anonymous">
+
+    <link rel="stylesheet" href="{{url_for('static', filename='styles.css')}}">
+
+    <title>Image Captioning</title>
+  </head>
+  <body style="background-color: #b8de6f">
+    
+
+    {%block content%}
+
+    {%endblock%}
+
+    
+
+    <!-- Optional JavaScript -->
+    <!-- jQuery first, then Popper.js, then Bootstrap JS -->
+    <script src="https://code.jquery.com/jquery-3.5.1.slim.min.js" integrity="sha384-DfXdz2htPH0lsSSs5nCTpuj/zy4C+OGpamoFVy38MVBnE+IbbVYUew+OrCXaRkfj" crossorigin="anonymous"></script>
+    <script src="https://cdn.jsdelivr.net/npm/[email protected]/dist/umd/popper.min.js" integrity="sha384-9/reFTGAW83EW2RDu2S0VKaIzap3H66lZH81PoYlFhbGU+6BZp6G7niu735Sk7lN" crossorigin="anonymous"></script>
+    <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.5.2/js/bootstrap.min.js" integrity="sha384-B4gt1jrGC7Jh4AgTPSdUtOBvfO8shuf57BaghqFfPlYxofvL8/KUEfYiJOMMV+rV" crossorigin="anonymous"></script>
+  </body>
+</html>

templates/base.html

@@ -0,0 +1,19 @@
+{%extends "base.html"%}
+
+{%block content%}
+
+<center>
+	
+<h1 class='display-1'>Automated Image</h1>
+<h1 class='display-1'>Captioning</h1>
+
+<br>
+<br>
+
+<form action="{{url_for('after')}}" method='POST' enctype='multipart/form-data'>
+    <input type="file" name='file1'>
+<input type="submit" name="btn" value='predict caption' class='btn btn-warning'> 
+</form>
+</center>
+
+{%endblock%}