Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,19 +1,19 @@
|
|
| 1 |
-
import
|
| 2 |
import numpy as np
|
| 3 |
from PIL import Image
|
| 4 |
-
|
| 5 |
-
import
|
| 6 |
-
from transformers import BartTokenizer, BartForConditionalGeneration
|
| 7 |
-
|
| 8 |
-
# Load pre-trained BART model and tokenizer
|
| 9 |
-
tokenizer_2 = BartTokenizer.from_pretrained("facebook/bart-large-cnn")
|
| 10 |
-
model_2 = BartForConditionalGeneration.from_pretrained("facebook/bart-large-cnn")
|
| 11 |
|
| 12 |
-
#
|
| 13 |
model = VisionEncoderDecoderModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
|
| 14 |
feature_extractor = ViTFeatureExtractor.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
|
| 15 |
tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
|
| 16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
def generate_captions(image):
|
| 18 |
image = Image.open(image).convert("RGB")
|
| 19 |
generated_caption = tokenizer.decode(model.generate(feature_extractor(image, return_tensors="pt").pixel_values.to("cpu"))[0])
|
|
@@ -22,6 +22,7 @@ def generate_captions(image):
|
|
| 22 |
generated_caption = sentence.replace(text_to_remove, "")
|
| 23 |
return generated_caption
|
| 24 |
|
|
|
|
| 25 |
def generate_paragraph(caption):
|
| 26 |
# Tokenize the caption
|
| 27 |
inputs = tokenizer_2([caption], max_length=1024, truncation=True, padding="longest", return_tensors="pt")
|
|
@@ -31,10 +32,8 @@ def generate_paragraph(caption):
|
|
| 31 |
|
| 32 |
# Decode the generated output
|
| 33 |
generated_text = tokenizer_2.decode(output[0], skip_special_tokens=True)
|
| 34 |
-
|
| 35 |
return generated_text
|
| 36 |
|
| 37 |
-
|
| 38 |
# create the Streamlit app
|
| 39 |
def app():
|
| 40 |
st.title('Image from your Side, Detailed description from my site')
|
|
|
|
| 1 |
+
import torch
|
| 2 |
import numpy as np
|
| 3 |
from PIL import Image
|
| 4 |
+
import streamlit as st
|
| 5 |
+
from transformers import AutoTokenizer, ViTFeatureExtractor, VisionEncoderDecoderModel, BartTokenizer, BartForConditionalGeneration
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
|
| 7 |
+
# pre-trained model to arrive at context
|
| 8 |
model = VisionEncoderDecoderModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
|
| 9 |
feature_extractor = ViTFeatureExtractor.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
|
| 10 |
tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
|
| 11 |
|
| 12 |
+
# pre-trained to arrive at description
|
| 13 |
+
tokenizer_2 = BartTokenizer.from_pretrained("facebook/bart-large-cnn")
|
| 14 |
+
model_2 = BartForConditionalGeneration.from_pretrained("facebook/bart-large-cnn")
|
| 15 |
+
|
| 16 |
+
# function to generate context
|
| 17 |
def generate_captions(image):
|
| 18 |
image = Image.open(image).convert("RGB")
|
| 19 |
generated_caption = tokenizer.decode(model.generate(feature_extractor(image, return_tensors="pt").pixel_values.to("cpu"))[0])
|
|
|
|
| 22 |
generated_caption = sentence.replace(text_to_remove, "")
|
| 23 |
return generated_caption
|
| 24 |
|
| 25 |
+
# function to generate description
|
| 26 |
def generate_paragraph(caption):
|
| 27 |
# Tokenize the caption
|
| 28 |
inputs = tokenizer_2([caption], max_length=1024, truncation=True, padding="longest", return_tensors="pt")
|
|
|
|
| 32 |
|
| 33 |
# Decode the generated output
|
| 34 |
generated_text = tokenizer_2.decode(output[0], skip_special_tokens=True)
|
|
|
|
| 35 |
return generated_text
|
| 36 |
|
|
|
|
| 37 |
# create the Streamlit app
|
| 38 |
def app():
|
| 39 |
st.title('Image from your Side, Detailed description from my site')
|