Spaces:
Running
Running
File size: 2,062 Bytes
f6a2955 a4f0c21 f6a2955 5648a79 f6a2955 645bae9 f6a2955 d84fc0b f6a2955 645bae9 f6a2955 1969b0a f6a2955 645bae9 f6a2955 645bae9 |
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 64 65 66 67 68 69 |
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
from huggingface_hub import from_pretrained_keras
import numpy as np
import gradio as gr
max_length = 5
img_width = 200
img_height = 50
model = from_pretrained_keras("keras-io/ocr-for-captcha", compile=False)
prediction_model = keras.models.Model(
model.get_layer(name="image").input, model.get_layer(name="dense2").output
)
with open("vocab.txt", "r") as f:
vocab = f.read().splitlines()
# Mapping integers back to original characters
num_to_char = layers.StringLookup(vocabulary=vocab, mask_token=None, invert=True)
def decode_batch_predictions(pred):
input_len = np.ones(pred.shape[0]) * pred.shape[1]
# Use greedy search. For complex tasks, you can use beam search
results = keras.backend.ctc_decode(pred, input_length=input_len, greedy=True)[0][0][
:, :max_length
]
# Iterate over the results and get back the text
output_text = []
for res in results:
res = tf.strings.reduce_join(num_to_char(res)).numpy().decode("utf-8")
output_text.append(res)
return output_text
def classify_image(img_path):
# 1. Read image
img = tf.io.read_file(img_path)
# 2. Decode and convert to grayscale
img = tf.io.decode_png(img, channels=1)
# 3. Convert to float32 in [0, 1] range
img = tf.image.convert_image_dtype(img, tf.float32)
# 4. Resize to the desired size
img = tf.image.resize(img, [img_height, img_width])
# 5. Transpose the image because we want the time
# dimension to correspond to the width of the image.
img = tf.transpose(img, perm=[1, 0, 2])
img = tf.expand_dims(img, axis=0)
preds = prediction_model.predict(img)
pred_text = decode_batch_predictions(preds)
return pred_text[0]
demo = gr.Interface(
fn=classify_image,
inputs=gr.Image(type="filepath"),
outputs=gr.Textbox(),
title="CAPTCHA OCR",
description="Upload a CAPTCHA image to recognize the text",
)
if __name__ == "__main__":
demo.launch(share=True)
|