Upload 6 files

.gitattributes

@@ -1,35 +1,2 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz 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
+*.keras filter=lfs diff=lfs merge=lfs -text
+tokenizer.pkl filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,105 @@
+import streamlit as st
+import tensorflow as tf
+import numpy as np
+import pickle
+import tempfile
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+from PIL import Image
+import matplotlib.pyplot as plt
+@st.cache_resource
+def load_captioning_model():
+    return tf.keras.models.load_model("image_caption_model.keras")
+
+@st.cache_resource
+def load_tokenizer():
+    with open("tokenizer.pkl", "rb") as f:
+        return pickle.load(f)
+
+model = load_captioning_model()
+tokenizer = load_tokenizer()
+max_length = 36  # Replace with actual value from training
+
+# Load encoder model
+from tensorflow.keras.applications.inception_v3 import InceptionV3, preprocess_input
+from tensorflow.keras.preprocessing.image import load_img, img_to_array
+from tensorflow.keras.models import Model
+
+base_model = InceptionV3(weights="imagenet")
+encoder_model = Model(base_model.input, base_model.layers[-2].output)
+def preprocess_image(img_path):
+    img = load_img(img_path, target_size=(299, 299))
+    img_array = img_to_array(img)
+    img_array = preprocess_input(img_array)
+    return np.expand_dims(img_array, axis=0)
+
+def generate_caption(model, tokenizer, photo, max_length):
+    in_text = '<start>'
+    for _ in range(max_length):
+        sequence = tokenizer.texts_to_sequences([in_text])[0]
+        sequence = pad_sequences([sequence], maxlen=max_length, padding='post')[0]
+        sequence = np.array(sequence, dtype=np.int32).reshape(1, max_length)
+        photo = np.reshape(photo, (1, 2048))
+
+        yhat = model.predict([photo, sequence], verbose=0)
+        yhat = np.argmax(yhat)
+        word = tokenizer.index_word.get(yhat)
+        if word is None:
+            break
+        in_text += ' ' + word
+        if word == 'end':
+            break
+
+    return in_text.replace('<start>', '').replace('<end>', '').strip()
+
+def caption_this_image(image_path, model, tokenizer, encoder_model, max_length):
+    img = preprocess_image(image_path)
+    feature = encoder_model.predict(img, verbose=0)
+    caption = generate_caption(model, tokenizer, feature, max_length)
+    return caption
+def preprocess_image(img_path):
+    img = load_img(img_path, target_size=(299, 299))
+    img_array = img_to_array(img)
+    img_array = preprocess_input(img_array)
+    return np.expand_dims(img_array, axis=0)
+
+def generate_caption(model, tokenizer, photo, max_length):
+    in_text = '<start>'
+    for _ in range(max_length):
+        sequence = tokenizer.texts_to_sequences([in_text])[0]
+        sequence = pad_sequences([sequence], maxlen=max_length, padding='post')[0]
+        sequence = np.array(sequence, dtype=np.int32).reshape(1, max_length)
+        photo = np.reshape(photo, (1, 2048))
+
+        yhat = model.predict([photo, sequence], verbose=0)
+        yhat = np.argmax(yhat)
+        word = tokenizer.index_word.get(yhat)
+        if word is None:
+            break
+        in_text += ' ' + word
+        if word == 'end':
+            break
+
+    return in_text.replace('<start>', '').replace('<end>', '').strip()
+
+def caption_this_image(image_path, model, tokenizer, encoder_model, max_length):
+    img = preprocess_image(image_path)
+    feature = encoder_model.predict(img, verbose=0)
+    caption = generate_caption(model, tokenizer, feature, max_length)
+    return caption
+
+st.title("🖼️ Image Captioning App")
+
+uploaded_file = st.file_uploader("Upload an image...", type=["jpg", "jpeg", "png"])
+
+if uploaded_file is not None:
+    temp_file = tempfile.NamedTemporaryFile(delete=False)
+    temp_file.write(uploaded_file.read())
+    temp_file.close()
+
+    st.image(uploaded_file, caption="Uploaded Image", use_column_width=True)
+
+    st.write("Generating caption...")
+    caption = caption_this_image(temp_file.name, model, tokenizer, encoder_model, max_length)
+
+    st.success("Generated Caption:")
+    st.markdown(f"**{caption}**")

image_caption_model.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa3e26037480067d4c7e65ba0323b0e94bc42d9fdac682449c8845812e3e35d8
+size 61399991

requirements.txt

@@ -1,3 +1,9 @@
-altair
-pandas
-streamlit
+streamlit
+tensorflow==2.10.0
+keras==2.10.0
+Pillow
+numpy
+pandas
+scikit-learn
+matplotlib
+tqdm

runtime.txt

@@ -0,0 +1 @@
+python-3.10

tokenizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5238bfd9630169ec7f7d2dda069f448b7945621e53690945db4f098207abb21
+size 306889