decimer 2.6.0__tar.gz → 2.7.1__tar.gz

{decimer-2.6.0 → decimer-2.7.1}/DECIMER/DECIMER_EfficinetNetV2_Transfomer_Trainer.py

@@ -250,7 +250,7 @@ def prepare_for_training(lr_config, encoder_config, transformer_config, verbose=
             transformer_config["d_model"], lr_config["warm_steps"]
         )
 
-        # Instiate an optimizer
+        # Instantiate an optimizer
         optimizer = tf.keras.optimizers.Adam(
             lr_scheduler, beta_1=0.9, beta_2=0.98, epsilon=1e-9
         )
@@ -323,7 +323,7 @@ if ckpt_manager.latest_checkpoint:
     start_epoch = int(ckpt_manager.latest_checkpoint.split("-")[-1])
 
 
-# Main training step fucntion
+# Main training step function
 def train_step(image_batch, selfies_batch):
     """Main training step function.
 
@@ -376,7 +376,7 @@ def dist_train_step(image_batch, selfies_batch):
 
 
 """
-# Main validation step fucntion
+# Main validation step function
 def validation_step(image_batch, selfies_batch):
 
     selfies_batch_input = selfies_batch[:, :-1]

{decimer-2.6.0 → decimer-2.7.1}/DECIMER/Predictor_usingCheckpoints.py

@@ -45,7 +45,7 @@ tokenizer = pickle.load(
 
 max_length = 302
 
-# Image partameters
+# Image parameters
 IMG_EMB_DIM = (16, 16, 512)
 IMG_EMB_DIM = (IMG_EMB_DIM[0] * IMG_EMB_DIM[1], IMG_EMB_DIM[2])
 IMG_SHAPE = (512, 512, 3)

{decimer-2.6.0 → decimer-2.7.1}/DECIMER/Repack_model.py

@@ -140,7 +140,7 @@ class DECIMER_Predictor(tf.Module):
     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
+    objects. The strings should get transformed into np.arrays before
     feeding them into this class.
     """
 
@@ -150,7 +150,7 @@ class DECIMER_Predictor(tf.Module):
 
         Args:
             encoder (tf.keras.model):  The encoder model
-            tokenizer (tf.keras.tokenizer): Output tokenizer, defines which charater is assigned to what token
+            tokenizer (tf.keras.tokenizer): Output tokenizer, defines which character is assigned to what token
             transformer (tf.keras.model):  The transformer model
             max_length (int): Maximum length of a string which can get predicted
         """
@@ -160,7 +160,7 @@ class DECIMER_Predictor(tf.Module):
         self.max_length = max_length
 
     def __call__(self, Decoded_image):
-        """This fuction takes in the Decoded image as input and makes the
+        """This function 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.
 
@@ -225,7 +225,7 @@ class ExportDECIMERPredictor(tf.Module):
 
     @tf.function
     def __call__(self, Decoded_Image):
-        """This fucntion calls the __call__function from the translator class.
+        """This function 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.

{decimer-2.6.0 → decimer-2.7.1}/DECIMER/Utils/Create_image_tokenizer.py

@@ -70,7 +70,7 @@ def data_loader(Smiles_Path):
     all_img_name = []
 
     for line in smiles.split("\n"):
-        # Split the ID and SMILES to seperate tokens
+        # Split the ID and SMILES to separate tokens
         tokens = line.split(",")
 
         image_id = str(tokens[0]) + ".png"

{decimer-2.6.0 → decimer-2.7.1}/DECIMER/__init__.py

@@ -1,29 +1,29 @@
-# -*- coding: utf-8 -*-
-"""DECIMER V2.6.0 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
-to provide an automated open-source software solution.
-
-
-Typical usage example:
-
-from decimer import predict_SMILES
-
-# Chemical depiction to SMILES translation
-image_path = "path/to/imagefile"
-SMILES = predict_SMILES(image_path)
-print(SMILES)
-
-For comments, bug reports or feature ideas,
-please raise a issue on the Github repository.
-"""
-
-__version__ = "2.6.0"
-
-__all__ = [
-    "DECIMER",
-]
-
-
-from .decimer import predict_SMILES
+# -*- coding: utf-8 -*-
+"""DECIMER V2.6.0 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
+to provide an automated open-source software solution.
+
+
+Typical usage example:
+
+from decimer import predict_SMILES
+
+# Chemical depiction to SMILES translation
+image_path = "path/to/imagefile"
+SMILES = predict_SMILES(image_path)
+print(SMILES)
+
+For comments, bug reports or feature ideas,
+please raise a issue on the Github repository.
+"""
+
+__version__ = "2.6.0"
+
+__all__ = [
+    "DECIMER",
+]
+
+
+from .decimer import predict_SMILES

{decimer-2.6.0 → decimer-2.7.1}/DECIMER/config.py

@@ -11,6 +11,7 @@ import tensorflow as tf
 from PIL import Image
 from PIL import ImageEnhance
 from pillow_heif import register_heif_opener
+from typing import Union
 
 import DECIMER.Efficient_Net_encoder as Efficient_Net_encoder
 import DECIMER.Transformer_decoder as Transformer_decoder
@@ -95,26 +96,68 @@ def HEIF_to_pillow(image_path: str):
     return heif_file
 
 
-def remove_transparent(image_path: str):
+def remove_transparent(image: Union[str, np.ndarray]) -> Image.Image:
     """
-    Removes the transparent layer from a PNG image with an alpha channel
-    Args: image_path (str): path of input image
-    Returns: PIL.Image
+    Removes the transparent layer from a PNG image with an alpha channel.
+
+    Args:
+        image (Union[str, np.ndarray]): Path of the input image or a numpy array representing the image.
+
+    Returns:
+        PIL.Image.Image: The image with transparency removed.
     """
-    try:
-        png = Image.open(image_path).convert("RGBA")
-    except Exception as e:
-        if type(e).__name__ == "UnidentifiedImageError":
-            png = HEIF_to_pillow(image_path)
-        else:
-            print(e)
-            raise Exception
+    def process_image(png: Image.Image) -> Image.Image:
+        """
+        Helper function to remove transparency from a single image.
+
+        Args:
+            png (PIL.Image.Image): The input PIL image with transparency.
+
+        Returns:
+            PIL.Image.Image: The image with transparency removed.
+        """
+        background = Image.new("RGBA", png.size, (255, 255, 255))
+        alpha_composite = Image.alpha_composite(background, png)
+        return alpha_composite
 
-    background = Image.new("RGBA", png.size, (255, 255, 255))
+    def handle_image_path(image_path: str) -> Image.Image:
+        """
+        Helper function to handle image paths.
+
+        Args:
+            image_path (str): The path to the input image.
+
+        Returns:
+            PIL.Image.Image: The image with transparency removed.
+        """
+        try:
+            png = Image.open(image_path).convert("RGBA")
+        except Exception as e:
+            if type(e).__name__ == "UnidentifiedImageError":
+                png = HEIF_to_pillow(image_path)
+            else:
+                print(e)
+                raise Exception
+        return process_image(png)
+
+    def handle_numpy_array(array: np.ndarray) -> Image.Image:
+        """
+        Helper function to handle a numpy array.
+
+        Args:
+            array (np.ndarray): The numpy array representing the image.
+
+        Returns:
+            PIL.Image.Image: The image with transparency removed.
+        """
+        png = Image.fromarray(array).convert("RGBA")
+        return process_image(png)
 
-    alpha_composite = Image.alpha_composite(background, png)
+    # Check if input is a numpy array
+    if isinstance(image, np.ndarray):
+        return handle_numpy_array(array=image)
 
-    return alpha_composite
+    return handle_image_path(image_path=image)
 
 
 def get_bnw_image(image):
@@ -185,12 +228,12 @@ def increase_brightness(image):
     return image
 
 
-def decode_image(image_path: str):
+def decode_image(image_path: Union[str, np.ndarray]):
     """Loads an image and preprocesses the input image in several steps to get
     the image ready for DECIMER input.
 
     Args:
-        image_path (str): path of input image
+        image_path (Union[str, np.ndarray]): path of input image or numpy array representing the image.
 
     Returns:
         Processed image
@@ -232,12 +275,12 @@ class Config:
         defined configurations.
 
         Args:
-            image_embedding_dim (int): Embedding dimention of the input image
+            image_embedding_dim (int): Embedding dimension of the input image
             preprocessing_fn (method): Efficient Net preprocessing function for input image
             backbone_fn (method): Calls Efficient-Net V2 as backbone for encoder
             image_shape (int): Shape of the input image
             do_permute (bool, optional): . Defaults to False.
-            pretrained_weights (keras weights, optional): Use pretrainined efficient net weights or not. Defaults to None.
+            pretrained_weights (keras weights, optional): Use pretrained efficient net weights or not. Defaults to None.
         """
         self.encoder_config = dict(
             image_embedding_dim=image_embedding_dim,
@@ -267,7 +310,7 @@ class Config:
             n_transformer_layers (int): Number of layers present in the transformer model
             transformer_d_dff (int): Transformer feed forward upwards projection size
             transformer_n_heads (int): Number of heads present in the transformer model
-            image_embedding_dim (int): Total number of dimension the image gets embeddeded
+            image_embedding_dim (int): Total number of dimension the image gets embedded
             dropout_rate (float, optional): Fraction of the input units to drop. Defaults to 0.1.
         """
         self.transformer_config = dict(
@@ -330,7 +373,7 @@ def prepare_models(encoder_config, transformer_config, replica_batch_size, verbo
         [type]: Optimizer, Encoder model and the Transformer
     """
 
-    # Instiate an optimizer
+    # Instantiate an optimizer
     optimizer = tf.keras.optimizers.Adam(learning_rate=0.00051)
 
     # Instantiate the encoder model

{decimer-2.6.0 → decimer-2.7.1}/DECIMER/decimer.py

@@ -5,6 +5,7 @@ import sys
 from typing import List
 from typing import Tuple
 
+import numpy as np
 import pystow
 import tensorflow as tf
 
@@ -71,7 +72,7 @@ tokenizer, DECIMER_V2, DECIMER_Hand_drawn = get_models(model_urls)
 
 
 def detokenize_output(predicted_array: int) -> str:
-    """This function takes the predited tokens from the DECIMER model and
+    """This function takes the predicted tokens from the DECIMER model and
     returns the decoded SMILES string.
 
     Args:
@@ -117,24 +118,24 @@ def detokenize_output_add_confidence(
     decoded_prediction_with_confidence = list(
         [(utils.decoder(tok), conf) for tok, conf in prediction_with_confidence_]
     )
-    decoded_prediction_with_confidence.append(prediction_with_confidence_[-1])
+
     return decoded_prediction_with_confidence
 
 
 def predict_SMILES(
-    image_path: str, confidence: bool = False, hand_drawn: bool = False
+        image_input: [str, np.ndarray], confidence: bool = False, hand_drawn: bool = False
 ) -> str:
     """Predicts SMILES representation of a molecule depicted in the given image.
 
     Args:
-        image_path (str): Path of chemical structure depiction image
-        confidence (bool): Flag to indicate whether to return confidence values along with SMILES prediction
-        hand_drawn (bool): Flag to indicate whether the molecule in the image is hand-drawn
+        image_input (str or np.ndarray): Path of chemical structure depiction image or a numpy array representing the image.
+        confidence (bool): Flag to indicate whether to return confidence values along with SMILES prediction.
+        hand_drawn (bool): Flag to indicate whether the molecule in the image is hand-drawn.
 
     Returns:
-        str: SMILES representation of the molecule in the input image, optionally with confidence values
+        str: SMILES representation of the molecule in the input image, optionally with confidence values.
     """
-    chemical_structure = config.decode_image(image_path)
+    chemical_structure = config.decode_image(image_input)
 
     model = DECIMER_Hand_drawn if hand_drawn else DECIMER_V2
     predicted_tokens, confidence_values = model(tf.constant(chemical_structure))

{decimer-2.6.0 → decimer-2.7.1}/DECIMER/efficientnetv2/effnetv2_model.py

@@ -180,7 +180,7 @@ class MBConvBlock(tf.keras.layers.Layer):
 
         self.endpoints = None
 
-        # Builds the block accordings to arguments.
+        # Builds the block according to arguments.
         self._build()
 
     @property

{decimer-2.6.0 → decimer-2.7.1}/DECIMER/utils.py

@@ -76,13 +76,17 @@ def ensure_models(default_path: str, model_urls: dict) -> dict:
         dict: A dictionary containing model names as keys and their local paths as values
     """
     model_paths = {}
-
+    # Store st_size of each model
+    model_sizes = {
+        "DECIMER": 28080309,
+        "DECIMER_HandDrawn": 28080328,
+    }
     for model_name, model_url in model_urls.items():
         model_path = os.path.join(default_path, f"{model_name}_model")
-        if (
-            os.path.exists(model_path)
-            and os.stat(os.path.join(model_path, "saved_model.pb")).st_size != 28080309
-        ):
+        if os.path.exists(model_path) and os.stat(
+            os.path.join(model_path, "saved_model.pb")
+        ).st_size != model_sizes.get(model_name):
+            print(f"Working with model {model_name}")
             shutil.rmtree(model_path)
             config.download_trained_weights(model_url, default_path)
         elif not os.path.exists(model_path):
@@ -90,5 +94,4 @@ def ensure_models(default_path: str, model_urls: dict) -> dict:
 
         # Store the model path
         model_paths[model_name] = model_path
-
     return model_paths

decimer-2.7.1/PKG-INFO

@@ -0,0 +1,195 @@
+Metadata-Version: 2.1
+Name: decimer
+Version: 2.7.1
+Summary: DECIMER 2.6.0: Deep Learning for Chemical Image Recognition using Efficient-Net V2 + Transformer
+Home-page: https://github.com/Kohulan/DECIMER-Image_Transformer
+Author: Kohulan Rajan
+Author-email: kohulan.rajan@uni-jena.de
+Maintainer: Kohulan Rajan, Otto Brinkhaus 
+Maintainer-email: kohulan.rajan@uni-jena.de, otto.brinkhaus@uni-jena.de
+License: MIT
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.5
+Classifier: Programming Language :: Python :: 3.6
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.5
+Description-Content-Type: text/markdown
+License-File: LICENSE
+
+<div align="center">
+
+# 🧪 DECIMER Image Transformer 🖼️
+
+### Deep Learning for Chemical Image Recognition using Efficient-Net V2 + Transformer
+
+<p align="center">
+  <img src="https://github.com/Kohulan/DECIMER-Image_Transformer/blob/master/DECIMER_V2.png?raw=true" alt="DECIMER Logo" width="600">
+</p>
+
+[![License](https://img.shields.io/badge/License-MIT%202.0-blue.svg?style=for-the-badge)](https://opensource.org/licenses/MIT)
+[![Maintenance](https://img.shields.io/badge/Maintained%3F-yes-green.svg?style=for-the-badge)](https://GitHub.com/Kohulan/DECIMER-Image_Transformer/graphs/commit-activity)
+[![GitHub issues](https://img.shields.io/github/issues/Kohulan/DECIMER-Image_Transformer.svg?style=for-the-badge)](https://GitHub.com/Kohulan/DECIMER-Image_Transformer/issues/)
+[![GitHub contributors](https://img.shields.io/github/contributors/Kohulan/DECIMER-Image_Transformer.svg?style=for-the-badge)](https://GitHub.com/Kohulan/DECIMER-Image_Transformer/graphs/contributors/)
+[![tensorflow](https://img.shields.io/badge/TensorFlow-2.10.1-FF6F00.svg?style=for-the-badge&logo=tensorflow)](https://www.tensorflow.org)
+[![DOI](https://zenodo.org/badge/293572361.svg)](https://zenodo.org/badge/latestdoi/293572361)
+[![Documentation Status](https://readthedocs.org/projects/decimer-image-transformer/badge/?version=latest&style=for-the-badge)](https://decimer-image-transformer.readthedocs.io/en/latest/?badge=latest)
+[![GitHub release](https://img.shields.io/github/release/Kohulan/DECIMER-Image_Transformer.svg?style=for-the-badge)](https://GitHub.com/Kohulan/DECIMER-Image_Transformer/releases/)
+[![PyPI version fury.io](https://badge.fury.io/py/decimer.svg?style=for-the-badge)](https://pypi.python.org/pypi/decimer/)
+
+</div>
+
+---
+
+## 📚 Table of Contents
+
+- [Abstract](#-abstract)
+- [Method and Model Changes](#-method-and-model-changes)
+- [Installation](#-installation)
+- [Usage](#-usage)
+- [Hand-drawn Model](#-decimer---hand-drawn-model)
+- [Citation](#-citation)
+- [Acknowledgements](#-acknowledgements)
+- [Author](#-author-kohulan)
+- [Project Website](#-project-website)
+- [Research Group](#-research-group)
+
+---
+
+## 🔬 Abstract
+
+<div style="background-color: #f0f0f0; padding: 15px; border-radius: 10px;">
+
+The DECIMER 2.2 project tackles the OCSR (Optical Chemical Structure Recognition) challenge using cutting-edge computational intelligence methods. Our goal? To provide an automated, open-source software solution for chemical image recognition.
+
+We've supercharged DECIMER with Google's TPU (Tensor Processing Unit) to handle datasets of over 1 million images with lightning speed!
+
+</div>
+
+---
+
+## 🧠 Method and Model Changes
+
+<table>
+  <tr>
+    <td width="50%">
+      <h3>🖼️ Image Feature Extraction</h3>
+      <p>Now utilizing EfficientNet-V2 for superior image analysis</p>
+    </td>
+    <td width="50%">
+      <h3>🔮 SMILES Prediction</h3>
+      <p>Employing a state-of-the-art transformer model</p>
+    </td>
+  </tr>
+</table>
+
+### 🚀 Training Enhancements
+
+1. **TFRecord Files**: Lightning-fast data reading
+2. **Google Cloud Buckets**: Efficient cloud storage solution
+3. **TensorFlow Data Pipeline**: Optimized data loading
+4. **TPU Strategy**: Harnessing the power of Google's TPUs
+
+---
+
+## 💻 Installation
+
+```bash
+# Create a conda wonderland
+conda create --name DECIMER python=3.10.0 -y
+conda activate DECIMER
+
+# Equip yourself with DECIMER
+pip install decimer
+```
+
+---
+
+## 🎮 Usage
+
+```python
+from DECIMER import predict_SMILES
+
+# Unleash the power of DECIMER
+image_path = "path/to/your/chemical/masterpiece.jpg"
+SMILES = predict_SMILES(image_path)
+print(f"🎉 Decoded SMILES: {SMILES}")
+```
+
+---
+
+## ✍️ DECIMER - Hand-drawn Model
+
+<div style="background-color: #e6f7ff; padding: 15px; border-radius: 10px;">
+
+🌟 **New Feature Alert!** 🌟
+
+Our latest model brings the magic of AI to hand-drawn chemical structures!
+
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.10781330.svg)](https://doi.org/10.5281/zenodo.10781330)
+
+</div>
+
+---
+
+## 📜 Citation
+
+<div style="background-color: #f9f9f9; padding: 15px; border-radius: 10px;">
+
+If DECIMER helps your research, please cite:
+
+1. Rajan K, et al. "DECIMER.ai - An open platform for automated optical chemical structure identification, segmentation and recognition in scientific publications." *Nat. Commun.* 14, 5045 (2023).
+2. Rajan, K., et al. "DECIMER 1.0: deep learning for chemical image recognition using transformers." *J Cheminform* 13, 61 (2021).
+3. Rajan, K., et al. "Advancements in hand-drawn chemical structure recognition through an enhanced DECIMER architecture," *J Cheminform* 16, 78 (2024).
+
+</div>
+
+---
+
+## 🙏 Acknowledgements
+
+- A big thank you to [Charles Tapley Hoyt](https://github.com/cthoyt) for his invaluable contributions!
+- Powered by Google's TPU Research Cloud (TRC)
+
+<p align="center">
+  <img src="https://user-images.githubusercontent.com/30716951/220350828-913e6645-6a0a-403c-bcb8-160d061d4606.png" width="300">
+</p>
+
+---
+
+## 👨‍🔬 Author: [Kohulan](https://kohulanr.com)
+
+<p align="center">
+  <img src="https://github.com/Kohulan/DECIMER-Image-to-SMILES/raw/master/assets/DECIMER.gif" width="300">
+</p>
+
+---
+
+## 🌐 Project Website
+
+Experience DECIMER in action at [decimer.ai](https://decimer.ai), brilliantly implemented by [Otto Brinkhaus](https://github.com/OBrink)!
+
+---
+
+## 🏫 Research Group
+
+<p align="center">
+  <a href="https://cheminf.uni-jena.de">
+    <img src="https://github.com/Kohulan/DECIMER-Image-to-SMILES/blob/master/assets/CheminfGit.png" width="300">
+  </a>
+</p>
+
+---
+
+<div align="center">
+
+### 📊 Project Analytics
+
+![Repobeats](https://repobeats.axiom.co/api/embed/bf532b7ac0d34137bdea8fbb82986828f86de065.svg "Repobeats analytics image")
+
+</div>