Created
April 4, 2020 01:59
-
-
Save thejefflarson/d8e2a65f37a37d39309058d23f6a71f1 to your computer and use it in GitHub Desktop.
Captcha solver
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from tensorflow.keras import Input, Model | |
from tensorflow.keras.models import load_model | |
from tensorflow.keras.layers import ( | |
Conv2D, | |
Activation, | |
MaxPooling2D, | |
Dropout, | |
Flatten, | |
Dense, | |
) | |
from tensorflow.keras.applications import MobileNetV2 | |
from tensorflow.keras.optimizers import RMSprop | |
from tensorflow.keras.metrics import top_k_categorical_accuracy | |
from PIL import Image | |
from tensorflow.keras.preprocessing.image import img_to_array | |
import numpy as np | |
from tensorflow.keras.callbacks import ( | |
ModelCheckpoint, | |
TensorBoard, | |
LambdaCallback, | |
TerminateOnNaN, | |
) | |
from os.path import isfile | |
from subprocess import Popen, PIPE, DEVNULL | |
from urllib.request import urlopen | |
from urllib.error import URLError | |
from time import sleep | |
from base64 import b64decode | |
from json import loads | |
from io import BytesIO | |
import backoff | |
from hashlib import blake2b | |
import tensorflow as tf | |
import matplotlib.pyplot as plt | |
alphabet = "abcdefghijklmnopqrstuvwxyz0123456789".upper() | |
char_size = len(alphabet) | |
categories = 6 | |
model_path = "./checkpoints/model.hdf5" | |
def text2vec(label): | |
vecs = [] | |
for i, char in enumerate(label): | |
vector = np.zeros(char_size) | |
vector[alphabet.index(char)] = 1 | |
vecs.append(vector) | |
return np.array(vecs) | |
@backoff.on_exception(backoff.expo, URLError) | |
def get(): | |
return urlopen( | |
"http://0.0.0.0:3000/botdetect.php?get=image&c=DemoCaptcha&t=239c90fd000cfe78d241c9d2f7743188" | |
) | |
def generator(port=3000): | |
while True: | |
x = [] | |
y = [] | |
proc = Popen( | |
["php", "-S", f"0.0.0.0:{port}"], | |
cwd="./bdc-php-free/v4.2.5/examples/t_api-captcha~demo", | |
stderr=PIPE, | |
stdout=DEVNULL, | |
) | |
sleep(0.05) | |
while len(x) < 32: | |
r = get() | |
resp = loads(r.read()) | |
img = BytesIO(b64decode(resp["image"])) | |
img = img_to_array(Image.open(img).convert("L")).reshape((50, 250, 1)) | |
img /= 127.5 | |
img -= 1.0 | |
code = resp["code"] | |
x.append(img) | |
y.append(text2vec(code)) | |
proc.kill() | |
x = np.array(x) | |
y = np.array(y).reshape((32, -1)) | |
if np.any(np.isnan(x)) or np.any(np.isnan(y)): | |
print("OPOO got NAN") | |
continue | |
yield (x, y) | |
def vec2text(label): | |
arr = [l.argmax().tolist() for l in label.reshape((categories, char_size))] | |
ret = [alphabet[l] for l in arr] | |
return ret | |
class CaptchaModel: | |
# ref: https://github.com/yeguixin/captcha_solver/tree/master/src/models | |
def __init__(self): | |
self.filewriter = tf.summary.create_file_writer("./logs/") | |
if isfile(model_path): | |
self.model = load_model(model_path) | |
return | |
inp = Input(shape=(50, 250, 1)) | |
x = Conv2D(32, (3, 3), strides=(1, 1), padding="same")(inp) | |
x = Activation("relu")(x) | |
x = MaxPooling2D(pool_size=(2, 2), padding="same")(x) | |
x = Dropout(0.5)(x) | |
x = Conv2D(64, (3, 3), strides=(1, 1), padding="same")(x) | |
x = Activation("relu")(x) | |
x = MaxPooling2D(pool_size=(2, 2), padding="same")(x) | |
x = Dropout(0.5)(x) | |
x = Conv2D(128, (3, 3), strides=(1, 1), padding="same")(x) | |
x = Activation("relu")(x) | |
x = MaxPooling2D(pool_size=(2, 2), padding="same")(x) | |
x = Dropout(0.5)(x) | |
x = Conv2D(256, (3, 3), strides=(1, 1), padding="same")(x) | |
x = Activation("relu")(x) | |
x = MaxPooling2D(pool_size=(2, 2), padding="same")(x) | |
x = Dropout(0.5)(x) | |
x = Conv2D(512, (3, 3), strides=(1, 1), padding="same")(x) | |
x = Activation("relu")(x) | |
x = MaxPooling2D(pool_size=(2, 2), padding="same")(x) | |
x = Dropout(0.5)(x) | |
x = Flatten()(x) | |
x = Dense(1024)(x) | |
x = Activation("relu")(x) | |
x = Dropout(0.5)(x) | |
x = Dense(char_size * categories, activation="softmax")(x) | |
model = Model(inp, x) | |
model.compile( | |
optimizer=RMSprop(learning_rate=0.0001, clipvalue=0.5), | |
loss=["categorical_crossentropy"], | |
metrics=[self.accuracy], | |
) | |
self.model = model | |
def accuracy(self, y_true, y_pred): | |
return top_k_categorical_accuracy(y_true, y_pred, k=categories) | |
def test(self, batch, logs=None): | |
print("") | |
(images, labels) = next(generator(port="9000")) | |
for i, image in enumerate(images[:5]): | |
label = "".join(vec2text(labels[i].reshape((1, -1)))) | |
predicted = self.model.predict(image.reshape((1, 50, 250, 1))) | |
predicted_label = "".join(vec2text(predicted)) | |
print( | |
blake2b(image.tobytes()).hexdigest()[:5], | |
predicted[0][:5], | |
vec2text(predicted), | |
vec2text(labels[i].reshape((1, -1))), | |
) | |
with self.filewriter.as_default(): | |
tf.summary.image( | |
f"{label} {predicted_label}", image.reshape((1, 50, 250, 1)), step=0 | |
) | |
def train(self): | |
checkpoint = ModelCheckpoint( | |
model_path, save_best_only=True, monitor="accuracy", mode="max" | |
) | |
board = TensorBoard(log_dir="./logs", write_images=True) | |
log = LambdaCallback(on_epoch_end=self.test) | |
term = TerminateOnNaN() | |
self.model.fit_generator( | |
generator(), | |
steps_per_epoch=20, | |
epochs=100000, | |
callbacks=[checkpoint, board, log, term], | |
) | |
if __name__ == "__main__": | |
model = CaptchaModel() | |
model.train() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment