Spaces:
Runtime error
Runtime error
File size: 2,118 Bytes
ad11330 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 |
import gradio as gr
from PIL import Image
import numpy as np
from pickle import load
from tensorflow.keras.applications.xception import Xception
from tensorflow.keras.models import load_model
from tensorflow.keras.preprocessing.sequence import pad_sequences
from matplotlib import pyplot as plt
def extract_features(filename, model):
try:
image = Image.open(filename)
except:
print("ERROR: Couldn't open image! Make sure the image path and extension is correct")
image = image.resize((299,299))
image = np.array(image)
# for images that has 4 channels, we convert them into 3 channels
if image.shape[2] == 4:
image = image[..., :3]
image = np.expand_dims(image, axis=0)
image = image/127.5
image = image - 1.0
feature = model.predict(image)
return feature
def word_for_id(integer, tokenizer):
for word, index in tokenizer.word_index.items():
if index == integer:
return word
return None
def generate_desc(model, tokenizer, photo, max_length):
in_text = 'start'
for i in range(max_length):
sequence = tokenizer.texts_to_sequences([in_text])[0]
sequence = pad_sequences([sequence], maxlen=max_length)
pred = model.predict([photo,sequence], verbose=0)
pred = np.argmax(pred)
word = word_for_id(pred, tokenizer)
if word is None:
break
in_text += ' ' + word
if word == 'end':
break
return in_text.split()[1:-1]
max_length = 32
tokenizer = load(open("tokenizer.p","rb"))
model = load_model('models/model_9.h5')
xception_model = Xception(include_top=False, pooling="avg")
def caption_generator(img_path):
photo = extract_features(img_path, xception_model)
img = Image.open(img_path)
description = generate_desc(model, tokenizer, photo, max_length)
description = ' '.join(description)
return description
inputs = gr.inputs.File(label="Select an Image")
outputs = gr.outputs.Textbox(label="Description")
gr.Interface(fn=caption_generator , inputs=inputs, outputs=outputs, capture_session=True).launch()
|