Spaces:
Runtime error
Runtime error
File size: 2,881 Bytes
f6a2955 a158ece f6a2955 a158ece f6a2955 5dae5d6 f6a2955 0155159 f6a2955 d84fc0b f6a2955 b1d2d4e f6a2955 1969b0a f6a2955 a940779 f6a2955 a940779 f6a2955 231bcfd 85d8257 f6a2955 |
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 70 71 72 |
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 = 55
img_width = 240
img_height = 50
model = from_pretrained_keras("napatswift/ocr-vl", compile=False)
prediction_model = keras.models.Model(
model.get_layer(name="image").input, model.get_layer(name="dense2").output
)
vocab = [' ', '(', ')', '+', '-', '.', '/', '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', ':', '=', '\xa0', 'ก', 'ข', 'ค', 'ฆ', 'ง', 'จ', 'ฉ', 'ช', 'ซ', 'ฌ', 'ญ',
'ฎ', 'ฏ', 'ฐ', 'ฑ', 'ฒ', 'ณ', 'ด', 'ต', 'ถ', 'ท', 'ธ', 'น', 'บ', 'ป', 'ผ', 'ฝ', 'พ', 'ฟ','ภ', 'ม', 'ย', 'ร', 'ฤ', 'ล', 'ฦ', 'ว', 'ศ', 'ษ', 'ส', 'ห', 'ฬ', 'อ', 'ฮ',
'ฯ', 'ะ', 'ั', 'า', 'ำ', 'ิ', 'ี', 'ึ', 'ื', 'ุ', 'ู', 'เ', 'แ', 'โ', 'ใ', 'ไ', 'ๅ', 'ๆ', '็', '่', '้', '๊', '๋', '์', '๐', '๑', '๒', '๓', '๔', '๕', '๖', '๗', '๘', '๙']
# Mapping integers back to original characters
num_to_char = layers.StringLookup(
vocabulary=vocab, 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_with_pad(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]
image = gr.Image(type='filepath')
text = gr.Textbox()
iface = gr.Interface(classify_image, image, text,
title="OCR for CAPTCHA",
description = "Keras Implementation of OCR model for reading captcha 🤖🦹🏻",
article = "Author: <a href=\"https://huggingface.co/anuragshas\">Anurag Singh</a>. Based on the keras example from <a href=\"https://keras.io/examples/vision/captcha_ocr/\">A_K_Nain</a>",
examples = ["dd764.png","3p4nn.png"]
)
iface.launch()
|