Classify image client script

README.md

@@ -10,39 +10,51 @@ For problem description and requirements, see [Project Statement](project-statem
 
 ```
 .
+├── font/
 ├── notebooks/
 │   ├── images/
 │   ├── Step1.EDA.ipynb
 │   ├── Step2.DataPrep.ipynb
 │   └── Step3.Classifier-BaselineModel.ipynb
 ├── scraping/
 │   └── scrape.py
+├── classify.py
+├── recommend.py
 ├── requirements.txt
 ├── .gitignore
 ├── project-statement.md
 ├── README.md
 └── LICENSE
 ```
 
-1. `notebooks/`: This folder contains all Jupyter Notebooks for this project and their exported plots in `notebooks/images/`.
-2. `scrape/`: This folder contains a scraping script to get more images from the internet for our dataset. All downloaded images will also be in this folder.
-3. `requirements.txt`: Text file for `pip` installation of necessary packages for development environment.
-4. `.gitignore`: This file contains ignore VCS ignore rules.
-5. `README.md`: A text file containing useful reference information about this project, including how to run the algorithm.
-6. `LICENSE`: MIT
+1. `font/`: This folder contains the fonts used in our client script's GUI mode.
+2. `notebooks/`: This folder contains all Jupyter Notebooks for this project and their exported plots in `notebooks/images/`.
+3. `scrape/`: This folder contains a scraping script to get more images from the internet for our dataset. All downloaded images will also be in this folder.
+4. `classify.py`: Client script for classifying flower images using trained models.
+5. `recommend.py`: Client script for recommending flower images using trained models.
+6. `requirements.txt`: Text file for `pip` installation of necessary packages for development environment.
+7. `.gitignore`: This file contains ignore VCS ignore rules.
+8. `README.md`: A text file containing useful reference information about this project, including how to run the algorithm.
+9. `LICENSE`: MIT
 
 
 Additionally, these folders will be created during dataset fetching and model training:
 
 1. `data/`: This folder contains out datasets.
-2. `logs/`: This folder contains training logs exported from training our models.
+2. `log/`: This folder contains training logs exported from training our models.
 3. `models/`: This folder contains trained models exported after training.
 
 ---
 
 
 ## Getting Started 🚀
 
+Clone this repository:
+
+```bash
+git clone https://github.com/miketvo/rmit2023a-cosc2753-assignment2.git
+```
+
 
 ### Development Environment
 
@@ -54,6 +66,8 @@ pip install -r requirements.txt
 
 Refer to [requirements.txt](requirements.txt) for package dependencies and their versions.
 
+<span style="color:gold">**NOTE:**</span> It is recommended that you use a Python virtual environment to avoid conflict with your global packages, and to keep your global Python installation clean. This is because we require specific versions of Numpy, Tensorflow and Keras in our code to maintain backward compatibility and compatibility between trained models and client code.
+
 
 ### Download Dataset
 
@@ -91,10 +105,68 @@ Skip this step if you just want to use the pre-trained model packages available
 
 If you are using one of our pre-trained model packages, download your desired version from [Packages](https://github.com/miketvo?tab=packages&repo_name=rmit2023a-cosc2753-assignment2) (.zip archives) and extract its contents into this project's root directory using your preferred zip program.
 
+On your terminal, make sure that you have the environment activated for the client script to have access to all required packages:
+
+- Python Virtualenv:
+
+   ```bash
+   ./venv/Scripts/activate
+   ```
+
+- Conda:
+
+   ```bash
+   conda activate ./envs
+   ```
+
 #### Classifying Flower Images
 
-To be written.
+Use the `classify.py` client script. Its syntax is as follows:
+
+```text
+python ./classify.py [-h] -f FILE -m MODEL [-g] [-v {0,1,2}]
+
+options:
+  -h, --help                                show this help message and exit
+  -f FILE, --file FILE                      the image to be classified
+  -c CLASSIFIER, --classifier CLASSIFIER    the machine learning model used for classification
+  -g, --gui                                 show classification result using GUI
+  -v {0,1,2}, --verbose-level {0,1,2}       verbose level, default: 0
+```
+
+Example use:
+
+```text
+$ python ./classify.py -f path/to/your/your/image.png -m ./models/clf-baseline -v=1
+Image image.png is classified as "Chrysanthemum" (model: "clf-baseline")
+```
+
+It also has a rudimentary GUI mode using your system's default GUI image viewer, which will display the image with a caption of what flower type it is classified as:
+
+```bash
+python ./classify.py --gui -f path/to/your/your/image.png -m ./models/clf-baseline
+```
+
 
 #### Recommending Flower Images
 
-To be written.
+Use the `recommend.py` client script. Its syntax is as follows:
+
+```text
+python ./recommend.py [-h] -f FILE -r RECOMMENDER -c CLASSIFIER [-n NUM]
+
+options:
+  -h, --help                                    show this help message and exit
+  -f FILE, --file FILE                          reference image
+  -r RECOMMENDER, --recommender RECOMMENDER     the machine learning model used for recommendation
+  -c CLASSIFIER, --classifier CLASSIFIER        the machine learning model used for classification
+  -n NUM, --num NUM                             number of recommendations, default: 10
+```
+
+Example:
+
+```bash
+python ./recommend.py --gui -f path/to/your/your/image.png -r ./models/recommender -c ./models/clf-baseline
+```
+
+When executed, the code above will display (using your system's default GUI image viewer) 10 similar flower images of the same type, based on your reference image.

classify.py

@@ -0,0 +1,56 @@
+import os
+import argparse
+from PIL import Image, ImageDraw, ImageFont
+import tensorflow as tf
+from keras.engine.training import Model
+
+from utils.glob import TARGET_IMG_SIZE
+from utils.glob import CLASS_LABELS
+import utils.data_manip as manip
+
+
+def classify(image_path: str, model_path: str, verbose: bool = False) -> tuple:
+    im_original = Image.open(image_path)
+    im_processed = manip.remove_transparency(im_original)
+    im_processed = manip.resize_crop(im_processed, TARGET_IMG_SIZE, TARGET_IMG_SIZE)
+    im_processed = manip.normalize_pixels(im_processed)
+    im_processed = tf.expand_dims(im_processed, axis=0)
+
+    model: Model = tf.keras.models.load_model(model_path)
+    pred = model.predict(im_processed, verbose=1 if verbose else 0)
+
+    pred_class_idx = tf.argmax(pred, axis=1).numpy()[0]
+    pred_class_label = CLASS_LABELS[pred_class_idx]
+
+    return im_original, pred_class_label
+
+
+if __name__ == '__main__':
+    ap = argparse.ArgumentParser()
+    ap.add_argument('-f', '--file', required=True, help='the image to be classified')
+    ap.add_argument('-c', '--classifier', required=True, help='the machine learning model used for classification')
+    ap.add_argument('-g', '--gui', action='store_true', help='show classification result using GUI')
+    ap.add_argument('-v', '--verbose-level', required=False, choices=['0', '1', '2'], default='0', help="verbose level, default: 0")
+    args = vars(ap.parse_args())
+    verbose_level = int(args['verbose_level'])
+
+    img = os.path.abspath(args['file'])
+    clf = os.path.abspath(args['classifier'])
+    image, predicted_label = classify(img, clf, False if verbose_level < 1 else True)
+
+    if args['gui']:
+        canvas = ImageDraw.Draw(image)
+        canvas.text(
+            (10, 10),
+            predicted_label,
+            fill=(255, 0, 0),
+            stroke_fill=(0, 0, 0),
+            stroke_width=2,
+            font=ImageFont.truetype(os.path.abspath('font/OpenSans-Regular.ttf'), size=24)
+        )
+        image.show()
+    else:
+        if verbose_level == 0:
+            print(predicted_label)
+        else:
+            print(f'Image {os.path.basename(img)} is classified as "{predicted_label}" (model: "{os.path.basename(clf)}")')

font/OFL.txt

@@ -0,0 +1,93 @@
+Copyright 2020 The Open Sans Project Authors (https://github.com/googlefonts/opensans)
+
+This Font Software is licensed under the SIL Open Font License, Version 1.1.
+This license is copied below, and is also available with a FAQ at:
+http://scripts.sil.org/OFL
+
+
+-----------------------------------------------------------
+SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007
+-----------------------------------------------------------
+
+PREAMBLE
+The goals of the Open Font License (OFL) are to stimulate worldwide
+development of collaborative font projects, to support the font creation
+efforts of academic and linguistic communities, and to provide a free and
+open framework in which fonts may be shared and improved in partnership
+with others.
+
+The OFL allows the licensed fonts to be used, studied, modified and
+redistributed freely as long as they are not sold by themselves. The
+fonts, including any derivative works, can be bundled, embedded, 
+redistributed and/or sold with any software provided that any reserved
+names are not used by derivative works. The fonts and derivatives,
+however, cannot be released under any other type of license. The
+requirement for fonts to remain under this license does not apply
+to any document created using the fonts or their derivatives.
+
+DEFINITIONS
+"Font Software" refers to the set of files released by the Copyright
+Holder(s) under this license and clearly marked as such. This may
+include source files, build scripts and documentation.
+
+"Reserved Font Name" refers to any names specified as such after the
+copyright statement(s).
+
+"Original Version" refers to the collection of Font Software components as
+distributed by the Copyright Holder(s).
+
+"Modified Version" refers to any derivative made by adding to, deleting,
+or substituting -- in part or in whole -- any of the components of the
+Original Version, by changing formats or by porting the Font Software to a
+new environment.
+
+"Author" refers to any designer, engineer, programmer, technical
+writer or other person who contributed to the Font Software.
+
+PERMISSION & CONDITIONS
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of the Font Software, to use, study, copy, merge, embed, modify,
+redistribute, and sell modified and unmodified copies of the Font
+Software, subject to the following conditions:
+
+1) Neither the Font Software nor any of its individual components,
+in Original or Modified Versions, may be sold by itself.
+
+2) Original or Modified Versions of the Font Software may be bundled,
+redistributed and/or sold with any software, provided that each copy
+contains the above copyright notice and this license. These can be
+included either as stand-alone text files, human-readable headers or
+in the appropriate machine-readable metadata fields within text or
+binary files as long as those fields can be easily viewed by the user.
+
+3) No Modified Version of the Font Software may use the Reserved Font
+Name(s) unless explicit written permission is granted by the corresponding
+Copyright Holder. This restriction only applies to the primary font name as
+presented to the users.
+
+4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font
+Software shall not be used to promote, endorse or advertise any
+Modified Version, except to acknowledge the contribution(s) of the
+Copyright Holder(s) and the Author(s) or with their explicit written
+permission.
+
+5) The Font Software, modified or unmodified, in part or in whole,
+must be distributed entirely under this license, and must not be
+distributed under any other license. The requirement for fonts to
+remain under this license does not apply to any document created
+using the Font Software.
+
+TERMINATION
+This license becomes null and void if any of the above conditions are
+not met.
+
+DISCLAIMER
+THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT
+OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE
+COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL
+DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM
+OTHER DEALINGS IN THE FONT SOFTWARE.