Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
# -*- coding: utf-8 -*- | |
"""ocrforcaptcha.ipynb | |
Automatically generated by Colaboratory. | |
Original file is located at | |
https://colab.research.google.com/drive/161aX_CGT4Q3zAMkLeLSOZVDhMyMtsqPx | |
""" | |
# Commented out IPython magic to ensure Python compatibility. | |
# %%capture | |
# !pip install gradio | |
# !pip install huggingface-hub | |
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 | |
characters = {'d', 'w', 'y', '4', 'f', '6', 'g', 'e', '3', '5', 'p', 'x', '2', 'c', '7', 'n', 'b', '8', 'm'} | |
max_length = 5 | |
img_width = 200 | |
img_height = 50 | |
model = from_pretrained_keras("keras-io/ocr-for-captcha") | |
prediction_model = keras.models.Model( | |
model.get_layer(name="image").input, model.get_layer(name="dense2").output | |
) | |
# Mapping characters to integers | |
char_to_num = layers.StringLookup( | |
vocabulary=list(characters), mask_token=None | |
) | |
# Mapping integers back to original characters | |
num_to_char = layers.StringLookup( | |
vocabulary=char_to_num.get_vocabulary(), 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=False)[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 | |
image = gr.inputs.Image(type='filepath') | |
text = gr.outputs.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>" | |
) | |
iface.launch() | |