Sử dụng keras để đọc captcha chữ đơn giản

import os
import numpy as np
import matplotlib.pyplot as plt

import tensorflow as tf
import keras
from keras import layers

path = "./captcha_images_v2/"
labels = []
images = []
for file in os.listdir(path):
  label = file.split(".png")[0]
  labels.append(label)
  full_file_path = os.path.join(path, file)
  images.append(full_file_path)

char_ = set(char for label in labels for char in label)

char_to_num = layers.experimental.preprocessing.StringLookup(
    vocabulary=list(char_), num_oov_indices=0
)
num_to_char = layers.experimental.preprocessing.StringLookup(
    vocabulary=char_to_num.get_vocabulary(), invert=True
)

def encode_single_sample(img_path, label):
    # 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])
    # 6. Map the characters in label to numbers
    label = char_to_num(tf.strings.unicode_split(label, input_encoding="UTF-8"))
    # 7. Return a dict as our model is expecting two inputs
    return {"image": img, "label": label}


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

#chia
x_train = images[:832]
y_train = labels[:832]

x_val = images[832:936]
y_val = labels[832:936]

x_test = images[936:]
y_test = labels[936:]


batch_size = 20
img_width = 200
img_height = 50
max_length = 5

train_dataset = tf.data.Dataset.from_tensor_slices((x_train, y_train))
train_dataset = (train_dataset.map(encode_single_sample).batch(batch_size))

val_dataset = tf.data.Dataset.from_tensor_slices((x_val, y_val))
val_dataset = (val_dataset.map(encode_single_sample).batch(batch_size))

test_dataset = tf.data.Dataset.from_tensor_slices((x_test, y_test))
test_dataset = (test_dataset.map(encode_single_sample).batch(batch_size))

class CTCLayer(layers.Layer):
    def __init__(self, name=None):
        super().__init__(name=name)
        self.loss_fn = keras.backend.ctc_batch_cost

    def call(self, y_true, y_pred):
        # Compute the training-time loss value and add it
        # to the layer using `self.add_loss()`.
        batch_len = tf.cast(tf.shape(y_true)[0], dtype="int64")
        input_length = tf.cast(tf.shape(y_pred)[1], dtype="int64")
        label_length = tf.cast(tf.shape(y_true)[1], dtype="int64")

        input_length = input_length * tf.ones(shape=(batch_len, 1), dtype="int64")
        label_length = label_length * tf.ones(shape=(batch_len, 1), dtype="int64")

        loss = self.loss_fn(y_true, y_pred, input_length, label_length)
        self.add_loss(loss)

        # At test time, just return the computed predictions
        return y_pred


def build_model():
    # Inputs to the model
    input_img = layers.Input(
        shape=(img_width, img_height, 1), name="image", dtype="float32"
    )
    labels = layers.Input(name="label", shape=(None,), dtype="float32")

    # First conv block
    x = layers.Conv2D(
        32,
        (3, 3),
        activation="relu",
        kernel_initializer="he_normal",
        padding="same",
        name="Conv1",
    )(input_img)
    x = layers.MaxPooling2D((2, 2), name="pool1")(x)

    # Second conv block
    x = layers.Conv2D(
        64,
        (3, 3),
        activation="relu",
        kernel_initializer="he_normal",
        padding="same",
        name="Conv2",
    )(x)
    x = layers.MaxPooling2D((2, 2), name="pool2")(x)

    new_shape = ((img_width // 4), (img_height // 4) * 64)
    x = layers.Reshape(target_shape=new_shape, name="reshape")(x)
    x = layers.Dense(64, activation="relu", name="dense1")(x)
    x = layers.Dropout(0.2)(x)

    # RNNs
    x = layers.Bidirectional(layers.LSTM(128, return_sequences=True, dropout=0.25))(x)
    x = layers.Bidirectional(layers.LSTM(64, return_sequences=True, dropout=0.25))(x)

    # Output layer
    x = layers.Dense(len(char_) + 1, activation="softmax", name="dense2")(x)

    # Add CTC layer for calculating CTC loss at each step
    output = CTCLayer(name="ctc_loss")(labels, x)

    # Define the model
    model = keras.models.Model(
        inputs=[input_img, labels], outputs=output, name="ocr_model_v1"
    )
    # Optimizer
    opt = keras.optimizers.Adam()
    # Compile the model and return
    model.compile(optimizer=opt)
    return model

model = build_model()
model.summary()

history = model.fit(
    train_dataset,
    validation_data=val_dataset,
    epochs=50
)

prediction_model = keras.models.Model(
    model.get_layer(name="image").input, model.get_layer(name="dense2").output
)
prediction_model.summary()

for batch in test_dataset.take(1):
    batch_images = batch["image"]
    batch_labels = batch["label"]

    preds = prediction_model.predict(batch_images)
    pred_texts = decode_batch_predictions(preds)

    orig_texts = []
    for label in batch_labels:
        label = tf.strings.reduce_join(num_to_char(label)).numpy().decode("utf-8")
        orig_texts.append(label)

    _, ax = plt.subplots(4, 4, figsize=(15, 5))
    for i in range(len(pred_texts)):
        img = (batch_images[i, :, :, 0] * 255).numpy().astype(np.uint8)
        img = img.T
        title = f"Prediction: {pred_texts[i]}"
        ax[i // 4, i % 4].imshow(img, cmap="gray")
        ax[i // 4, i % 4].set_title(title)
        ax[i // 4, i % 4].axis("off")
plt.show()