Commit
Browse files
app.py
CHANGED
@@ -1,63 +1,20 @@
|
|
1 |
-
# Load Image to Text model
|
2 |
import streamlit as st
|
3 |
-
import
|
4 |
-
import spaces
|
5 |
-
from transformers import AutoProcessor, AutoModelForCausalLM, MBart50TokenizerFast, MBartForConditionalGeneration
|
6 |
-
import requests
|
7 |
-
# Carregamento de imagens locais
|
8 |
-
import sys
|
9 |
-
import cv2
|
10 |
from PIL import Image
|
11 |
-
# Load Translation model
|
12 |
|
13 |
-
|
14 |
-
image_to_text_model = AutoModelForCausalLM.from_pretrained("sezenkarakus/image-GIT-description-model-v3")
|
15 |
|
16 |
-
|
17 |
-
|
18 |
-
tokenizer = MBart50TokenizerFast.from_pretrained(ckpt)
|
19 |
-
translation_model = MBartForConditionalGeneration.from_pretrained(ckpt)
|
20 |
-
|
21 |
-
tokenizer.src_lang = 'en_XX'
|
22 |
|
23 |
file_name = st.file_uploader("Upload a hot dog candidate image")
|
24 |
|
25 |
-
|
26 |
-
|
27 |
-
generated_ids = image_to_text_model.generate(pixel_values=pixel_values, max_length=200)
|
28 |
-
generated_caption = image_processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
29 |
-
|
30 |
-
return generated_caption
|
31 |
-
|
32 |
-
def translate(text):
|
33 |
-
inputs = tokenizer(text, return_tensors='pt')
|
34 |
-
input_ids = inputs.input_ids
|
35 |
-
attention_mask = inputs.attention_mask
|
36 |
-
|
37 |
-
try:
|
38 |
-
input_ids = input_ids.to('cuda')
|
39 |
-
attention_mask = attention_mask.to('cuda')
|
40 |
-
model = translation_model.to("cuda")
|
41 |
-
except:
|
42 |
-
print('No NVidia GPU, model performance may not be as good')
|
43 |
-
model = translation_model
|
44 |
-
|
45 |
-
output = model.generate(input_ids, attention_mask=attention_mask, forced_bos_token_id=tokenizer.lang_code_to_id['pt_XX'])
|
46 |
-
translated = tokenizer.decode(output[0], skip_special_tokens=True)
|
47 |
-
|
48 |
-
return translated
|
49 |
-
|
50 |
-
|
51 |
-
img_url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
|
52 |
-
# img_url = 'https://farm4.staticflickr.com/3733/9000662079_ce3599d0d8_z.jpg'
|
53 |
-
# img_url = 'https://farm4.staticflickr.com/3088/5793281956_2a15b2559c_z.jpg'
|
54 |
-
# img_url = 'https://farm5.staticflickr.com/4073/4816939054_844feb0078_z.jpg'
|
55 |
-
|
56 |
-
image = Image.open(file_name)
|
57 |
-
# image = Image.open(requests.get(img_url, stream=True).raw)
|
58 |
|
59 |
-
|
60 |
-
|
|
|
61 |
|
62 |
-
|
63 |
-
|
|
|
|
|
|
1 |
import streamlit as st
|
2 |
+
from transformers import pipeline
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
from PIL import Image
|
|
|
4 |
|
5 |
+
pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")
|
|
|
6 |
|
7 |
+
st.title("Hot Dog? Or Not?")
|
|
|
|
|
|
|
|
|
|
|
8 |
|
9 |
file_name = st.file_uploader("Upload a hot dog candidate image")
|
10 |
|
11 |
+
if file_name is not None:
|
12 |
+
col1, col2 = st.columns(2)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
|
14 |
+
image = Image.open(file_name)
|
15 |
+
col1.image(image, use_column_width=True)
|
16 |
+
predictions = pipeline(image)
|
17 |
|
18 |
+
col2.header("Probabilities")
|
19 |
+
for p in predictions:
|
20 |
+
col2.subheader(f"{ p['label'] }: { round(p['score'] * 100, 1)}%")
|