Upload 2 files

app.py

@@ -0,0 +1,71 @@
+import gradio as gr
+from PIL import Image
+import numpy as np
+import tensorflow as tf
+from tensorflow.keras.applications.vgg16 import VGG16, preprocess_input
+from tensorflow.keras.preprocessing.image import img_to_array
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+import pickle
+
+# Load your pre-trained model and tokenizer
+model = tf.keras.models.load_model("model.h5")
+with open("tokenizer.pkl", "rb") as handle:
+    tokenizer = pickle.load(handle)
+
+# Load your precomputed features if required (else comment out)
+# with open("features.pkl", "rb") as f:
+#     features = pickle.load(f)
+
+# Image feature extractor model
+feature_extractor = VGG16()
+feature_extractor = tf.keras.Model(feature_extractor.input, feature_extractor.layers[-2].output)
+
+# Description generation function
+def generate_caption(image):
+    # Preprocess the image
+    image = image.resize((224, 224))
+    image = img_to_array(image)
+    image = np.expand_dims(image, axis=0)
+    image = preprocess_input(image)
+
+    # Extract features
+    feature = feature_extractor.predict(image, verbose=0)
+
+    # Generate caption (mock example: replace with your real inference loop)
+    input_text = 'startseq'
+    max_length = 34  # set this to your model's max_length
+
+    for _ in range(max_length):
+        sequence = tokenizer.texts_to_sequences([input_text])[0]
+        sequence = pad_sequences([sequence], maxlen=max_length)
+        yhat = model.predict([feature, sequence], verbose=0)
+        yhat = np.argmax(yhat)
+        word = ''
+        for w, i in tokenizer.word_index.items():
+            if i == yhat:
+                word = w
+                break
+        if word == 'endseq' or word == '':
+            break
+        input_text += ' ' + word
+
+    caption = input_text.replace('startseq', '').strip()
+    return caption
+
+# Gradio Interface
+title = "📸 Image Caption Generator"
+description = "Upload an image and let the AI generate a descriptive caption for it."
+theme = "soft"
+
+iface = gr.Interface(
+    fn=generate_caption,
+    inputs=gr.Image(type="pil"),
+    outputs=gr.Textbox(label="Generated Caption"),
+    title=title,
+    description=description,
+    theme=theme,
+    allow_flagging="never"
+)
+
+if __name__ == "__main__":
+    iface.launch()

requirements.txt

@@ -0,0 +1,86 @@
+gdown
+absl-py==1.4.0
+altair==5.1.0
+astunparse==1.6.3
+attrs==23.1.0
+blinker==1.6.2
+cachetools==5.3.1
+certifi==2023.7.22
+charset-normalizer==3.2.0
+click==8.1.7
+colorama==0.4.6
+contourpy==1.1.0
+cycler==0.11.0
+flatbuffers==23.5.26
+fonttools==4.42.1
+gast==0.4.0
+google-auth==2.22.0
+google-auth-oauthlib==1.0.0
+google-pasta==0.2.0
+grpcio==1.57.0
+h5py==3.9.0
+idna==3.4
+importlib-metadata==6.8.0
+jax==0.4.14
+Jinja2==3.1.2
+joblib==1.3.2
+jsonschema==4.19.0
+jsonschema-specifications==2023.7.1
+# Removed keras==2.15.0 since tensorflow includes keras now
+kiwisolver==1.4.5
+libclang==16.0.6
+Markdown==3.4.4
+markdown-it-py==3.0.0
+MarkupSafe==2.1.3
+matplotlib==3.7.2
+mdurl==0.1.2
+ml-dtypes==0.2.0
+nltk==3.8.1
+numpy==1.23.5
+oauthlib==3.2.2
+opt-einsum==3.3.0
+packaging==23.1
+pandas==2.0.3
+Pillow==9.5.0
+protobuf==4.24.2
+pyarrow==13.0.0
+pyasn1==0.5.0
+pyasn1-modules==0.3.0
+pydeck==0.8.0
+Pygments==2.16.1
+Pympler==1.0.1
+pyparsing==3.0.9
+python-dateutil==2.8.2
+pytz==2023.3
+pytz-deprecation-shim==0.1.0.post0
+referencing==0.30.2
+regex==2023.8.8
+requests==2.31.0
+requests-oauthlib==1.3.1
+rich==13.5.2
+rpds-py==0.10.0
+rsa==4.9
+scipy==1.11.2
+six==1.16.0
+smmap==5.0.0
+streamlit==1.38.0
+tenacity==8.2.3
+tensorboard==2.15.2
+tensorboard-data-server==0.7.1
+tensorflow==2.15.0
+tensorflow-estimator==2.15.0
+tensorflow-io-gcs-filesystem==0.31.0
+termcolor==2.3.0
+toml==0.10.2
+toolz==0.12.0
+tornado==6.3.3
+tqdm==4.66.1
+typing_extensions==4.5.0
+tzdata==2023.3
+tzlocal==4.3.1
+urllib3==1.26.16
+validators==0.21.2
+watchdog==3.0.0
+Werkzeug==2.3.7
+wrapt==1.14.1
+zipp==3.16.2