uploaded remaining files

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+best_model_inceptionv3.keras filter=lfs diff=lfs merge=lfs -text
+feature_model.keras filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,66 @@
+import gradio as gr
+import numpy as np
+import pandas as pd
+import tensorflow as tf
+import pickle
+from PIL import Image
+
+with open('C:/Users/shlok/OneDrive/Desktop/Projects/Image-Caption-Generator/tokenizer.pkl', 'rb') as handle:
+    tokenizer = pickle.load(handle)
+feature_model=tf.keras.models.load_model('feature_model.keras')
+model = tf.keras.models.load_model('best_model_inceptionv3.keras')
+def idx_to_word(integer, tokenizer):
+    for word, index in tokenizer.word_index.items():
+        if index == integer:
+            return word
+    return None
+
+def predict_caption(image):
+    
+
+    in_text = 'startseq'
+    # iterate over the max length of sequence
+    for i in range(35):
+        # encode input sequence
+        sequence = tokenizer.texts_to_sequences([in_text])[0]
+        # pad the sequence
+        sequence = tf.keras.preprocessing.sequence.pad_sequences([sequence], 35, padding='post')
+        # predict next word
+        yhat = model.predict([image, sequence], verbose=0)
+        # get index with high probability
+        yhat = np.argmax(yhat)
+        # convert index to word
+        word = idx_to_word(yhat, tokenizer)
+        # stop if word not found
+        if word is None:
+            break
+        # append word as input for generating next word
+        in_text += " " + word
+        # stop if we reach end tag
+        if word == 'endseq':
+            break
+    # Split the generated sequence to exclude the first and last words
+    final_caption = in_text.split()[1:-1]
+    # Join the words to form the final caption
+    final_caption = ' '.join(final_caption)
+    
+    return final_caption
+    
+def generate_caption(image):
+    print(image)
+    
+    image = image.resize((299, 299))
+    image_array = tf.keras.preprocessing.image.img_to_array(image)
+    image_array = image_array.reshape((1, 299, 299, 3))
+    image = tf.keras.applications.inception_v3.preprocess_input(image_array)
+    feature = feature_model.predict(image, verbose=0)
+    caption = predict_caption(feature)
+    return caption
+
+gr.Interface(fn=generate_caption,
+             inputs=gr.Image(label='Upload a photo',type="pil"),
+             outputs=gr.Label(label='Caption'),
+             examples=['1028205764_7e8df9a2ea.jpg','123.jpg','1001773457.jpg','1024138940_f1fefbdce1.jpg'],
+             title='Image Caption Generator',
+             ).launch(share=True)
+

best_model_inceptionv3.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c2a83b6ce7d8e1e1e677cbd13ce7ee59f68ff2322fd143a471a499e8ee2c1a8
+size 59280932

captions.txt.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd405c85c04317175a79d282128626045da72dc2a3cc7af75fdf6b6feb03929f
+size 850962

feature_model.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c90d24d975e6f20e0bcbce2c5cc19de645539670431eea8e5ff87b44452240ec
+size 88217949

requirements.txt

@@ -0,0 +1,5 @@
+gradio
+numpy
+pandas
+tensorflow
+Pillow

tokenizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dabdab5afb1687437a8f7c271825dba6ea4f35129f29c81817f38bad91e7da2
+size 334854