Spaces:
Runtime error
Runtime error
ydshieh
commited on
Commit
·
0514a3d
1
Parent(s):
9711ed9
fix desc
Browse files
app.py
CHANGED
|
@@ -5,12 +5,11 @@ import numpy as np
|
|
| 5 |
|
| 6 |
# Designing the interface
|
| 7 |
st.title("French Image Caption App")
|
| 8 |
-
# For newline
|
| 9 |
-
st.write('\n')
|
| 10 |
|
| 11 |
st.markdown(
|
| 12 |
"""
|
| 13 |
-
An image caption model by combining the ViT model and a French GPT2 model.
|
|
|
|
| 14 |
The pretained weights of both models are loaded, with a set of randomly initialized cross-attention weigths.
|
| 15 |
The model is trained on 65000 images from the COCO dataset for about 1500 steps, with the original english cpationis are translated to french for training purpose.
|
| 16 |
"""
|
|
|
|
| 5 |
|
| 6 |
# Designing the interface
|
| 7 |
st.title("French Image Caption App")
|
|
|
|
|
|
|
| 8 |
|
| 9 |
st.markdown(
|
| 10 |
"""
|
| 11 |
+
An image caption model [ViT-GPT2](https://huggingface.co/flax-community/vit-gpt2/tree/main) by combining the ViT model and a French GPT2 model.
|
| 12 |
+
[Part of the [Huggingface JAX/Flax event](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/).]\n
|
| 13 |
The pretained weights of both models are loaded, with a set of randomly initialized cross-attention weigths.
|
| 14 |
The model is trained on 65000 images from the COCO dataset for about 1500 steps, with the original english cpationis are translated to french for training purpose.
|
| 15 |
"""
|