Merge pull request #7 from JonatanRasmussen/pytest

added unit tests and coverage reports to project

.coveragerc

@@ -0,0 +1,4 @@
+[run]
+omit =
+    *__init__*
+    */tests/*

.github/workflows/python-app.yml

@@ -0,0 +1,34 @@
+name: Python application
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: '3.10'
+        cache: 'pip'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -r requirements.txt
+    - name: Test with pytest
+      run: |
+        coverage run -m pytest tests/
+        coverage html --title="DTU 02476 Group 100 Project Coverage Report"
+    - name: Upload pytest test results
+      uses: actions/upload-artifact@v4
+      with:
+        name: coverage-report
+        path: htmlcov/
+      # Use always() to always run this step to publish test results when there are test failures
+      if: ${{ always() }}

project_winegrape_src_files/__init__.py

@@ -1,2 +1,2 @@
-from project_winegrape_src_files.models.model import MyNeuralNet
+from project_winegrape_src_files.models.model import ImageClassifier
 from project_winegrape_src_files.predict_model import predict

project_winegrape_src_files/conf/test_config.yaml

@@ -0,0 +1,26 @@
+reproducibility:
+  seed: 123
+
+data:
+  dir: "tests/test_data/raw/grapevine-leaves-image-dataset/Grapevine_Leaves_Image_Dataset"
+  transform_level: "light"
+  batch_size: 32
+  val_split: 0.2
+
+model:
+  model_name: "efficientnet_b0" # or resnetv2_50t
+  num_classes: 5
+  drop_rate: 0.3
+  pretrained: true
+
+optimization:
+  lr_pretrained: 1e-5
+  lr_final: 1e-4
+  optimizer: "AdamW"
+  criterion: "cross_entropy"
+
+training:
+  max_epochs: 40
+
+logging:  
+  log_every_n_steps: 40

project_winegrape_src_files/data/data.py

@@ -19,7 +19,7 @@ def __init__(
             num_workers = 0
         ):
         super().__init__()
-        self.root_dir = Path(os.getcwd(), data_dir)
+        self.root_dir = Path(data_dir)
         self.transform_level = transform_level
         self.img_size = img_size
         self.batch_size = batch_size

pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
 [project]
 name = "project_winegrape_src_files"
 version = "0.0.1"
-description = "Your project description"
+description = ""
 authors = [
   { name = "Your Name", email = "[email protected]" },
 ]

requirements.txt

@@ -1,9 +1,16 @@
-torch >= 2.1.0
-timm >= 0.9.12
-pytorch-lightning >= 2.1.3
-torchvision >= 0.16.0
-torchmetrics >= 1.2.1
-numpy >= 1.26.0
-opendatasets >= 0.1.22
-hydra-core >= 1.3.2
-omegaconf >= 2.3.0
+click==8.1.7
+coverage==7.4.0
+dvc==3.39.0
+dvc-gdrive==3.0.1
+hydra-core==1.3.2
+kaggle==1.6.2
+Markdown==3.5.2
+numpy==1.26.3
+omegaconf==2.3.0
+opendatasets==0.1.22
+pytest==7.4.4
+pytorch_lightning==2.1.3
+timm==0.9.12
+torch==2.1.2
+torchmetrics==1.3.0
+torchvision==0.16.2

tests/test_config.py

@@ -0,0 +1,15 @@
+from hydra import initialize, compose
+import os
+
+def test_config() -> None:
+    with initialize(version_base=None, config_path="../project_winegrape_src_files/conf"):
+        test_cfg = compose(config_name="test_config")
+        # assert top level keys
+        assert "reproducibility" in test_cfg.keys()
+        assert "data" in test_cfg.keys()
+        assert "model" in test_cfg.keys()
+        assert "optimization" in test_cfg.keys()
+        assert "training" in test_cfg.keys()
+        assert "logging" in test_cfg.keys()
+        # assert data exists
+        assert os.path.exists(os.path.dirname(test_cfg.data.dir))

tests/test_data.py

@@ -0,0 +1,19 @@
+from project_winegrape_src_files.data.data import DataModule
+from hydra import initialize, compose
+
+def test_data():
+    with initialize(version_base=None, config_path="../project_winegrape_src_files/conf"):
+        test_cfg = compose(config_name="test_config")
+        data_module = DataModule(
+            data_dir=test_cfg.data.dir,
+            transform_level=test_cfg.data.transform_level,
+            batch_size=test_cfg.data.batch_size,
+            val_split=test_cfg.data.val_split,
+        )
+        data_module.setup()
+        training_dataset = data_module.train_dataloader()
+        val_dataset = data_module.val_dataloader()
+        test_dataset = data_module.test_dataloader()
+        assert len(training_dataset) == 2
+        assert len(val_dataset) == 1
+        assert len(test_dataset) == 1

tests/test_data/raw/grapevine-leaves-image-dataset/Grapevine_Leaves_Image_Dataset/Grapevine_Leaves_Image_Dataset_Citation_Request.txt

@@ -0,0 +1,24 @@
+DATASET: https://www.muratkoklu.com/datasets/
+
+KOKLU Murat (a), UNLERSEN M. Fahri (b), OZKAN Ilker Ali (a), ASLAN M. Fatih(c), SABANCI Kadir (c)
+
+(a) Department of Computer Engineering, Selcuk University, Turkey, Konya, Turkey
+(b) Department of Electrical and Electronics Engineering, Necmettin Erbakan University, Konya, Turkey
+(c) Department of Electrical-Electronic Engineering, Karamanoglu Mehmetbey University, Karaman, Turkey
+
+Citation Request :
+Koklu, M., Unlersen, M. F., Ozkan, I. A., Aslan, M. F., & Sabanci, K. (2022). A CNN-SVM study based on selected deep features for grapevine leaves classification. Measurement, 188, 110425. Doi:https://doi.org/10.1016/j.measurement.2021.110425
+
+Link: https://doi.org/10.1016/j.measurement.2021.110425
+
+DATASET: https://www.muratkoklu.com/datasets/
+
+Highlights
+• Classification of five classes of grapevine leaves by MobileNetv2 CNN Model.
+• Classification of features using SVMs with different kernel functions.
+• Implementing a feature selection algorithm for high classification percentage.
+• Classification with highest accuracy using CNN-SVM Cubic model.
+
+Abstract: The main product of grapevines is grapes that are consumed fresh or processed. In addition, grapevine leaves are harvested once a year as a by-product. The species of grapevine leaves are important in terms of price and taste. In this study, deep learning-based classification is conducted by using images of grapevine leaves. For this purpose, images of 500 vine leaves belonging to 5 species were taken with a special self-illuminating system. Later, this number was increased to 2500 with data augmentation methods. The classification was conducted with a state-of-art CNN model fine-tuned MobileNetv2. As the second approach, features were extracted from pre-trained MobileNetv2′s Logits layer and classification was made using various SVM kernels. As the third approach, 1000 features extracted from MobileNetv2′s Logits layer were selected by the Chi-Squares method and reduced to 250. Then, classification was made with various SVM kernels using the selected features. The most successful method was obtained by extracting features from the Logits layer and reducing the feature with the Chi-Squares method. The most successful SVM kernel was Cubic. The classification success of the system has been determined as 97.60%. It was observed that feature selection increased the classification success although the number of features used in classification decreased.
+
+Keywords: Deep learningTransfer learningSVMGrapevine leavesLeaf identification