Download app.py from chhetri123/caption_generation_transformer: direct link, hf CLI and curl.
- Browser
- Download file 1.56 kB
-
https://huggingface.co/spaces/chhetri123/caption_generation_transformer/resolve/main/app.py
- Command line
-
hf download hf://spaces/chhetri123/caption_generation_transformer/app.py
-
curl -L -o app.py https://huggingface.co/spaces/chhetri123/caption_generation_transformer/resolve/main/app.py
1.56 kB
| import cv2 | |
| import numpy as np | |
| import os | |
| import tempfile | |
| import pickle | |
| import tensorflow as tf | |
| import gradio as gr | |
| from PIL import Image | |
| # | |
| # Transformer | |
| from library.prediction import evaluate_single_image | |
| from library.transformer import Transformer | |
| from library.customSchedule import learning_rate | |
| top_k = 25000 | |
| num_layer = 4 | |
| d_model = 512 | |
| dff = 2048 | |
| num_heads = 8 | |
| row_size = 8 | |
| col_size = 8 | |
| target_vocab_size = top_k + 1 | |
| dropout_rate = 0.1 | |
| loaded_transformer = Transformer(num_layer, d_model, num_heads, dff, row_size, col_size, | |
| target_vocab_size, max_pos_encoding=target_vocab_size, | |
| rate=dropout_rate) | |
| # Load the weights into the model | |
| loaded_transformer.load_weights('model/') | |
| # Use the loaded custom objects | |
| loaded_transformer.compile(optimizer=tf.keras.optimizers.Adam(learning_rate)) | |
| print("Trasformer model loaded successfully") | |
| global tokenizer | |
| with open('transformer/tokenizer.pickle', 'rb') as handle: | |
| tokenizer = pickle.load(handle) | |
| tokenizer.word_index['<pad>'] = 0 | |
| tokenizer.index_word[0] = '<pad>' | |
| print("Tokenizer loaded successfully") | |
| def transformer(image_pil): | |
| print(image_pil) | |
| temp_file, temp_file_path = tempfile.mkstemp(suffix=".jpg") | |
| os.close(temp_file) | |
| image_pil.save(temp_file_path) | |
| caption = evaluate_single_image(temp_file_path, tokenizer, loaded_transformer) | |
| return caption | |
| interface = gr.Interface(fn=transformer, inputs=gr.Image(type="pil"), outputs="text", api_name="predict") | |
| interface.launch(debug=True) |