refactoring

src/captcha/CaptchaReader.py

@@ -7,6 +7,7 @@ from captcha.DatasetFactory import DatasetFactory
 import numpy as np
 from tensorflow import keras
 
+
 class CaptchaReader:
 
     def __init__(self, modelFilepath, captchaShape):
@@ -14,19 +15,17 @@ class CaptchaReader:
         self.captchaShape = captchaShape
 
     def getTextInCaptchaImage(self, captchaImageFile):
-        # FK-TODO: refactor
-        modelDAO = ModelDAO(inColab = False)
-        model = modelDAO.loadModel(self.modelFilepath)
-        prediction_model = ModelFactory.createPredictionModel(model)
-        charNumConverter = CharNumConverter(CaptchaGenerator.characters)
-        datasetFactory = DatasetFactory(self.captchaShape,charNumConverter.char_to_num, batch_size = 64)
-        batchImages = self._asSingleSampleBatch(datasetFactory._encode_single_sample(captchaImageFile, 'dummy')['image'])
-        preds = prediction_model.predict(batchImages)
-        predictionsDecoder = PredictionsDecoder(CaptchaGenerator.captchaLength, charNumConverter.num_to_char)
-        pred_texts = predictionsDecoder.decode_batch_predictions(preds)
-        return pred_texts[0]
+        return self._getTextsInCaptchaImage(self._getCaptchaImage(captchaImageFile))[0]
+
+    def _getCaptchaImage(self, captchaImageFile):
+        return self._asSingleSampleBatch(DatasetFactory.encodeImage(captchaImageFile, self.captchaShape))
 
     def _asSingleSampleBatch(self, img):
-        array = keras.utils.img_to_array(img)
-        array = np.expand_dims(array, axis=0)
-        return array
+        return np.expand_dims(keras.utils.img_to_array(img), axis=0)
+
+    def _getTextsInCaptchaImage(self, captchaImage):
+        preds = self._createPredictionModel().predict(captchaImage)
+        return PredictionsDecoder(CaptchaGenerator.captchaLength, CharNumConverter(CaptchaGenerator.characters).num_to_char).decode_batch_predictions(preds)
+
+    def _createPredictionModel(self):
+        return ModelFactory.createPredictionModel(ModelDAO(inColab=False).loadModel(self.modelFilepath))

src/captcha/DatasetFactory.py

@@ -10,15 +10,18 @@ class DatasetFactory:
 
     def createDataset(self, x, y):
         dataset = tf.data.Dataset.from_tensor_slices((x, y))
-        dataset = dataset.map(self._encode_single_sample, num_parallel_calls=tf.data.AUTOTUNE)
+        dataset = dataset.map(self._encodeImageAndLabel, num_parallel_calls=tf.data.AUTOTUNE)
         dataset = dataset.batch(self.batch_size).prefetch(buffer_size=tf.data.AUTOTUNE)
         return dataset
 
-    def _encode_single_sample(self, img_path, label):
-        img = tf.io.read_file(img_path)
+    def _encodeImageAndLabel(self, imageFilename, label):
+        return {
+            "image": DatasetFactory.encodeImage(imageFilename, self.captchaShape),
+            "label": self.char_to_num(tf.strings.unicode_split(label, input_encoding="UTF-8"))}
+    
+    @staticmethod
+    def encodeImage(imageFilename, captchaShape):
+        img = tf.io.read_file(imageFilename)
         img = tf.io.decode_jpeg(img, channels=3)
-        img = tf.image.resize(img, [self.captchaShape.height, self.captchaShape.width])
-        # Map the characters in label to numbers
-        label = self.char_to_num(tf.strings.unicode_split(label, input_encoding="UTF-8"))
-        # Return a dict as our model is expecting two inputs
-        return {"image": img, "label": label}
+        img = tf.image.resize(img, [captchaShape.height, captchaShape.width])
+        return img