UtkarshShivhare commited on
Commit
6df1a27
·
1 Parent(s): 798e7b1

Delete app.py

Browse files
Files changed (1) hide show
  1. app.py +0 -88
app.py DELETED
@@ -1,88 +0,0 @@
1
- import streamlit as st
2
- import tensorflow as tf
3
- from PIL import Image
4
- import numpy as np
5
- import json
6
- from tensorflow.keras.applications.vgg16 import VGG16,preprocess_input
7
- from tensorflow.keras.preprocessing.image import img_to_array
8
- from tensorflow.keras.preprocessing.text import Tokenizer,tokenizer_from_json
9
- from tensorflow.keras.preprocessing.sequence import pad_sequences
10
- from tensorflow.keras.models import Model
11
-
12
- from keras.models import load_model
13
-
14
- # Load the .h5 model
15
- model = load_model('image_caption.h5')
16
-
17
- with open('tokenizer_config.json', 'r') as f:
18
- tokenizer_config = json.load(f)
19
- tokenizer = tokenizer_from_json(tokenizer_config)
20
- # tokenizer.word_index = eval(tokenizer_config)['word_index']
21
-
22
- max_length=35
23
- # Load pre-trained model
24
- vgg_model = VGG16()
25
- vgg_model = Model(inputs=vgg_model.inputs, outputs=vgg_model.layers[-2].output)
26
-
27
- # Set Streamlit configurations
28
- st.set_page_config(page_title="Image Classifier App", layout="wide")
29
-
30
-
31
- # Function to preprocess the input image
32
- def preprocess_image(image):
33
- image = image.resize((224, 224))
34
- image = img_to_array(image)
35
- image = image.reshape((1, image.shape[0], image.shape[1], image.shape[2]))
36
- image = preprocess_input(image)
37
- return image
38
-
39
- # Function to make predictions on the input image
40
- def predict(image):
41
- image = preprocess_image(image)
42
- feature = vgg_model.predict(image, verbose=0)
43
- preds = predict_caption(model, feature, tokenizer, max_length)
44
- preds=preds[8:-7]
45
- return preds
46
-
47
- def idx_word(integer,tok):
48
- for word,index in tok.word_index.items():
49
- if index== integer:
50
- return word
51
- return None
52
-
53
- def predict_caption(model,image,tok,max_len):
54
- in_text="startseq"
55
- for i in range(max_len):
56
- seq=tok.texts_to_sequences([in_text])[0]
57
- seq=pad_sequences([seq],max_len)
58
- yhat = model.predict([image, seq], verbose=0)
59
- yhat = np.argmax(yhat)
60
- word = idx_word(yhat, tok)
61
- if word is None:
62
- break
63
- in_text += " " + word
64
- if word == 'endseq':
65
- break
66
- return in_text
67
-
68
- # Streamlit app
69
- def main():
70
- st.title("Image Captioning App")
71
- st.write("Upload an image and the app will predict its class.")
72
-
73
- uploaded_image = st.file_uploader("Choose an image", type=["jpg", "jpeg", "png"])
74
-
75
- if uploaded_image is not None:
76
- image = Image.open(uploaded_image)
77
- st.image(image, caption='Uploaded Image', use_column_width=True)
78
- st.write("")
79
-
80
- if st.button("Predict"):
81
- with st.spinner("Predicting..."):
82
- predictions = predict(image)
83
-
84
- st.write(f"Top Caption:{predictions}")
85
-
86
- # Run the app
87
- if __name__ == "__main__":
88
- main()