fix: read the docs build error

.readthedocs.yml

@@ -9,7 +9,7 @@ build:
   os: ubuntu-22.04
   tools:
     python: "3.11"
-    
+
 # Build documentation in the docs/ directory with Sphinx
 sphinx:
   configuration: docs/conf.py

Benchmark/distort_images.py

@@ -9,14 +9,15 @@
 
 
 def distort_image(input_image_path: str, output_image_path: str) -> None:
-    """
-    This function takes the path of an input image and the desired output image path (both str).
-    It rotates the input image randomly (-5° or +5°) and applies shearing (in x or y-direction with an
-    angle of -9° or 9°) as described by Clevert et al (Img2Mol (preprint)).
-    I was a bit confused about the "shearing factor" of +/- 0.1 described by Clevert et al. Normally the transformation
-    is done with a shearing angle. I assume here that the correponding angle is 0.1*90° = 9° as 90° is the extreme case
-    where the image turns into a horizontal or vertical line.
-    This seems reasonable as it results in a mild distortion as described by the authors.
+    """This function takes the path of an input image and the desired output
+    image path (both str). It rotates the input image randomly (-5° or +5°) and
+    applies shearing (in x or y-direction with an angle of -9° or 9°) as
+    described by Clevert et al (Img2Mol (preprint)). I was a bit confused about
+    the "shearing factor" of +/- 0.1 described by Clevert et al. Normally the
+    transformation is done with a shearing angle. I assume here that the
+    correponding angle is 0.1*90° = 9° as 90° is the extreme case where the
+    image turns into a horizontal or vertical line. This seems reasonable as it
+    results in a mild distortion as described by the authors.
 
     Args:
             input_image_path (str): Path of input image
@@ -43,9 +44,12 @@ def distort_image(input_image_path: str, output_image_path: str) -> None:
 
 
 def main():
-    """This script takes an input directory with images of chemical structure depictions, applies a random
-    rotation (-5° or +5°) as well as shearing (angle drawn from [-0.1, 0.1]) to every input image. These
-    distortions are supposed to imitate the image modifications described by Clevert et al (Img2Mol (preprint))
+    """This script takes an input directory with images of chemical structure
+    depictions, applies a random rotation (-5° or +5°) as well as shearing
+    (angle drawn from [-0.1, 0.1]) to every input image.
+
+    These distortions are supposed to imitate the image modifications
+    described by Clevert et al (Img2Mol (preprint))
     """
     input_dir = os.path.abspath(sys.argv[1])
     output_dir = os.path.abspath(sys.argv[2])

Benchmark/evaluate_benchmarks.py

@@ -8,9 +8,8 @@
 def compare_molecules_inchi_match(
     input_file_path: str, reference_directory: str
 ) -> None:
-    """
-    This function checks if the molecules in the DECIMER results to a set of reference
-    mol-files using Standard InChI.
+    """This function checks if the molecules in the DECIMER results to a set of
+    reference mol-files using Standard InChI.
 
     Args:
             input_file (str): Path of file that contains image names and SMILES as created by run_decimer_save_results.py

Benchmark/run_decimer_save_results.py

@@ -5,10 +5,9 @@
 
 
 def main():
-    """
-    This script runs Decimer on every image in a given directory (first argument) and saves the
-    results in a text file with a given ID (second argument).
-    """
+    """This script runs Decimer on every image in a given directory (first
+    argument) and saves the results in a text file with a given ID (second
+    argument)."""
     im_path = sys.argv[1]
     save_ID = sys.argv[2]
 

DECIMER/DECIMER_EfficinetNetV2_Transfomer_Trainer.py

@@ -76,8 +76,8 @@
 
 
 def decode_image(image_data):
-    """Preprocess the input image for Efficient-Net and
-    returned the preprocessed image
+    """Preprocess the input image for Efficient-Net and returned the
+    preprocessed image.
 
     Args:
         image_data (int array): Decoded image in 2D array
@@ -98,8 +98,8 @@ def decode_image(image_data):
 
 
 def read_tfrecord(example):
-    """Read a tf record file and decodes the image and text data
-    back into original form.
+    """Read a tf record file and decodes the image and text data back into
+    original form.
 
     Args:
         example (tf.record): single entry from tf record file
@@ -124,7 +124,7 @@ def read_tfrecord(example):
 
 
 def numericalSort(value):
-    """Sorts the filenames numerically
+    """Sorts the filenames numerically.
 
     Args:
         value (int): numerical value of the file name
@@ -138,7 +138,7 @@ def numericalSort(value):
 
 
 def get_dataset(batch_size=BATCH_SIZE, buffered_size=BUFFER_SIZE, path=""):
-    """Creates a batch of data rom a given dataset
+    """Creates a batch of data rom a given dataset.
 
     Args:
         batch_size (int, optional): number of datapoints per batch. Defaults to BATCH_SIZE.
@@ -207,8 +207,8 @@ def get_dataset(batch_size=BATCH_SIZE, buffered_size=BUFFER_SIZE, path=""):
 
 
 def prepare_for_training(lr_config, encoder_config, transformer_config, verbose=0):
-    """Preparte the model for training. initiate the learning rate, loss object, metrics
-    and optimizer
+    """Preparte the model for training. initiate the learning rate, loss
+    object, metrics and optimizer.
 
     Args:
         lr_config (int): values for learning rate configuration
@@ -239,13 +239,11 @@ def loss_fn(real, pred):
         train_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(
             name="train_accuracy", dtype=tf.float32
         )
-        """
-        validation_loss = tf.keras.metrics.Mean(
-            name="validation_loss", dtype=tf.float32
-        )
-        validation_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(
-            name="validation_accuracy", dtype=tf.float32
-        )
+        """validation_loss = tf.keras.metrics.Mean(
+
+        name="validation_loss", dtype=tf.float32 ) validation_accuracy =
+        tf.keras.metrics.SparseCategoricalAccuracy(
+        name="validation_accuracy", dtype=tf.float32 )
         """
         # Declare the learning rate schedule (try this as actual lr schedule and list...)
         lr_scheduler = config.CustomSchedule(
@@ -327,7 +325,7 @@ def loss_fn(real, pred):
 
 # Main training step fucntion
 def train_step(image_batch, selfies_batch):
-    """Main training step function
+    """Main training step function.
 
     Args:
         image_batch (float array): Input image batch

DECIMER/Predictor_usingCheckpoints.py

@@ -130,9 +130,8 @@ def __init__(self, encoder, tokenizer, transformer, max_length):
         self.max_length = max_length
 
     def __call__(self, Decoded_image):
-        """
-        Run the DECIMER predictor model when called.
-        Usage of predict_SMILES or predict_SMILES_with_confidence is recommended instead
+        """Run the DECIMER predictor model when called. Usage of predict_SMILES
+        or predict_SMILES_with_confidence is recommended instead.
 
         Args:
             Decoded_image (_type_): output of config.decode_image
@@ -180,9 +179,8 @@ def __call__(self, Decoded_image):
 
 
 def detokenize_output(predicted_array: tf.Tensor) -> str:
-    """
-    This function takes the predicted array of tokens and returns the predicted SMILES
-    string.
+    """This function takes the predicted array of tokens and returns the
+    predicted SMILES string.
 
     Args:
         predicted_array (tf.Tensor): Transformer Decoder output array (predicted tokens)
@@ -203,11 +201,10 @@ def detokenize_output_add_confidence(
     predicted_array: tf.Tensor,
     confidence_array: tf.Tensor,
 ) -> List[Tuple[str, float]]:
-    """
-    This function takes the predicted array of tokens as well as the confidence values
-    returned by the Transformer Decoder and returns a list of tuples
-    that contain each token of the predicted SMILES string and the confidence
-    value.
+    """This function takes the predicted array of tokens as well as the
+    confidence values returned by the Transformer Decoder and returns a list of
+    tuples that contain each token of the predicted SMILES string and the
+    confidence value.
 
     Args:
         predicted_array (tf.Tensor): Transformer Decoder output array (predicted tokens)
@@ -234,8 +231,7 @@ def detokenize_output_add_confidence(
 
 
 def predict_SMILES_with_confidence(image_path: str) -> List[Tuple[str, float]]:
-    """
-    This function takes an image path (str) and returns a list of tuples
+    """This function takes an image path (str) and returns a list of tuples
     that contain each token of the predicted SMILES string and the confidence
     level from the last layer of the Transformer decoder.
 
@@ -255,8 +251,7 @@ def predict_SMILES_with_confidence(image_path: str) -> List[Tuple[str, float]]:
 
 
 def predict_SMILES(image_path: str) -> str:
-    """
-    This function takes an image path (str) and returns the SMILES
+    """This function takes an image path (str) and returns the SMILES
     representation of the depicted molecule (str).
 
     Args:

DECIMER/Repack_model.py

@@ -87,9 +87,8 @@
 
 
 def detokenize_output(predicted_array: tf.Tensor) -> str:
-    """
-    This function takes the predicted array of tokens and returns the predicted SMILES
-    string.
+    """This function takes the predicted array of tokens and returns the
+    predicted SMILES string.
 
     Args:
         predicted_array (tf.Tensor): Transformer Decoder output array (predicted tokens)
@@ -110,11 +109,10 @@ def detokenize_output_add_confidence(
     predicted_array: tf.Tensor,
     confidence_array: tf.Tensor,
 ) -> List[Tuple[str, float]]:
-    """
-    This function takes the predicted array of tokens as well as the confidence values
-    returned by the Transformer Decoder and returns a list of tuples
-    that contain each token of the predicted SMILES string and the confidence
-    value.
+    """This function takes the predicted array of tokens as well as the
+    confidence values returned by the Transformer Decoder and returns a list of
+    tuples that contain each token of the predicted SMILES string and the
+    confidence value.
 
     Args:
         predicted_array (tf.Tensor): Transformer Decoder output array (predicted tokens)
@@ -137,14 +135,18 @@ def detokenize_output_add_confidence(
 
 
 class DECIMER_Predictor(tf.Module):
-    """This is a class which takes care of inference. It loads the saved checkpoint and the necessary
-    tokenizers. The inference begins with the start token (<start>) and ends when the end token(<end>)
-    is met. This class can only work with tf.Tensor objects. The strings shoul gets transformed into np.arrays
-    before feeding them into this class.
+    """This is a class which takes care of inference.
+
+    It loads the saved checkpoint and the necessary tokenizers. The
+    inference begins with the start token (<start>) and ends when the
+    end token(<end>) is met. This class can only work with tf.Tensor
+    objects. The strings shoul gets transformed into np.arrays before
+    feeding them into this class.
     """
 
     def __init__(self, encoder, tokenizer, transformer, max_length):
-        """Load the tokenizers, the maximum input and output length and the model.
+        """Load the tokenizers, the maximum input and output length and the
+        model.
 
         Args:
             encoder (tf.keras.model):  The encoder model
@@ -158,8 +160,8 @@ def __init__(self, encoder, tokenizer, transformer, max_length):
         self.max_length = max_length
 
     def __call__(self, Decoded_image):
-        """This fuction takes in the Decoded image as input and
-        makes the predicted list of tokens and return the tokens as tf.Tensor array.
+        """This fuction takes in the Decoded image as input and makes the
+        predicted list of tokens and return the tokens as tf.Tensor array.
         Before feeding the input array we must define start and the end tokens.
 
         Args:
@@ -211,7 +213,9 @@ def __call__(self, Decoded_image):
 
 
 class ExportDECIMERPredictor(tf.Module):
-    """This class wraps the inference class into a module into tf.Module sub-class, with a tf.function on the __call__ method.
+    """This class wraps the inference class into a module into tf.Module sub-
+    class, with a tf.function on the __call__ method.
+
     So we could export the model as a tf.saved_model.
     """
 
@@ -222,8 +226,9 @@ def __init__(self, DECIMER):
     @tf.function
     def __call__(self, Decoded_Image):
         """This fucntion calls the __call__function from the translator class.
-        In the tf.function only the output sentence is returned.
-        Thanks to the non-strict execution in tf.function any unnecessary values are never computed.
+        In the tf.function only the output sentence is returned. Thanks to the
+        non-strict execution in tf.function any unnecessary values are never
+        computed.
 
         Args:
             sentence (tf.Tensor[tf.int32]): Input array in tf.Easgertensor format.

DECIMER/__init__.py

@@ -1,7 +1,5 @@
 # -*- coding: utf-8 -*-
-"""
-DECIMER V2.4.0 Python Package.
-============================
+"""DECIMER V2.4.0 Python Package. ============================
 
 This repository contains DECIMER-V2,Deep lEarning for Chemical ImagE Recognition) project
 was launched to address the OCSR problem with the latest computational intelligence methods
@@ -19,7 +17,6 @@
 
 For comments, bug reports or feature ideas,
 please raise a issue on the Github repository.
-
 """
 
 __version__ = "2.4.0"