Merge branch 'main' into pytest, resolved conflicts

.gitignore

@@ -1,6 +1,7 @@
 docs/site/
 data/raw/
 lightning_logs/
+
 # test cache
 manual_test/
 
@@ -175,7 +176,7 @@ cython_debug/
 #  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/
+.idea/
 
 # DVC
 /data

LICENSE

@@ -1,14 +1,14 @@
 {% if cookiecutter.open_source_license == 'MIT' %}
 The MIT License (MIT)
-Copyright (c) {% now 'utc', '%Y' %}, {{ cookiecutter.author_name }}
+Copyright (c) {% now 'utc', '%Y' %}, JonatanRasmussen
 
 Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
 
 The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
 
 THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 {% elif cookiecutter.open_source_license == 'BSD-3-Clause' %}
-Copyright (c) {% now 'utc', '%Y' %}, {{ cookiecutter.author_name }}
+Copyright (c) {% now 'utc', '%Y' %}, JonatanRasmussen
 All rights reserved.
 
 Redistribution and use in source and binary forms, with or without modification,
@@ -21,7 +21,7 @@ are permitted provided that the following conditions are met:
   list of conditions and the following disclaimer in the documentation and/or
   other materials provided with the distribution.
 
-* Neither the name of {{ cookiecutter.project_name }} nor the names of its
+* Neither the name of project_winegrape nor the names of its
   contributors may be used to endorse or promote products derived from this
   software without specific prior written permission.
 

Makefile

@@ -4,8 +4,8 @@
 # GLOBALS                                                                       #
 #################################################################################
 
-PROJECT_NAME = {{ cookiecutter.project_name }}
-PYTHON_VERSION = {{ cookiecutter.python_version_number }}
+PROJECT_NAME = project_winegrape_src_files
+PYTHON_VERSION = 3.11
 PYTHON_INTERPRETER = python
 
 #################################################################################

data.dvc

@@ -1,6 +1,6 @@
 outs:
-- md5: 9d61ac5c5b1aeb3f1ab5cde649e04ea9.dir
-  size: 0
-  nfiles: 2
+- md5: 8d058593ff5033ab4f934ba52d092839.dir
+  size: 114539947
+  nfiles: 503
   hash: md5
   path: data

docs/mkdocs.yaml

@@ -1,5 +1,5 @@
-site_name: {{ cookiecutter.project_name }}
-site_author: {{ cookiecutter.author_name }}
+site_name: project_winegrape
+site_author: JonatanRasmussen
 docs_dir: source
 
 theme:

docs/source/index.md

@@ -1,4 +1,4 @@
 ## Documentation
 
-Documentation for {{ cookiecutter.project_name }}
+Documentation for project_winegrape
 

project_structure.md

@@ -33,7 +33,7 @@ The directory structure of the project looks like this:
 │
 ├── tests                <- Test files
 │
-├── {{cookiecutter.project_name}}  <- Source code for use in this project.
+├── project_winegrape_src_files  <- Source code for use in this project.
 │   │
 │   ├── __init__.py      <- Makes folder a Python module
 │   │

project_winegrape_src_files/conf/config.yaml → project_winegrape_src_files/conf/config1.yaml

@@ -6,21 +6,23 @@ data:
   transform_level: "light"
   batch_size: 32
   val_split: 0.2
+  num_workers: 6
 
 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
+  max_epochs: 20
 
 logging:  
-  log_every_n_steps: 40
+  log_every_n_steps: 5

project_winegrape_src_files/conf/config2.yaml

@@ -0,0 +1,29 @@
+reproducibility:
+  seed: 123
+
+data:
+  dir: "data/raw/grapevine-leaves-image-dataset/Grapevine_Leaves_Image_Dataset"
+  transform_level: "light"
+  batch_size: 32
+  val_split: 0.2
+  num_workers: 6
+
+model:
+  #model_name: "efficientnet_b0" # or resnetv2_50t
+  model_name: "CNN"
+  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: 20
+
+logging:  
+  log_every_n_steps: 5

project_winegrape_src_files/data/data.py

@@ -13,20 +13,25 @@ def __init__(
             self,
             data_dir="data/raw/grapevine-leaves-image-dataset/Grapevine_Leaves_Image_Dataset",
             transform_level=None,
-            batch_size=32,
-            val_split = 0.2
+            img_size = 224,
+            batch_size=8,
+            val_split = 0.2,
+            num_workers = 0
         ):
         super().__init__()
         self.root_dir = Path(data_dir)
         self.transform_level = transform_level
+        self.img_size = img_size
         self.batch_size = batch_size
         self.val_split = val_split
+        self.num_workers = num_workers
 
         self.transform_val,self.transform_train = self.which_transform()
 
     def which_transform(self):
 
         basic_transformation = [
+            transforms.Resize(self.img_size),
             transforms.ToTensor(),
             transforms.Normalize([0.485, 0.456, 0.406],[0.229, 0.224, 0.225])
         ]
@@ -67,9 +72,9 @@ def setup(self, stage=None):
         val_dataset = Subset(val_dataset, indices[:split_idx]) 
         val_dataset, test_dataset = torch.utils.data.random_split(val_dataset, [0.9, 0.1])
 
-        self.train_dataset = DataLoader(train_dataset, batch_size=self.batch_size, shuffle=True, num_workers = 31)
-        self.val_dataset = DataLoader(val_dataset, batch_size=self.batch_size, shuffle = False, num_workers = 31)
-        self.test_dataset = DataLoader(test_dataset, batch_size=len(test_dataset), shuffle = False, num_workers = 31)
+        self.train_dataset = DataLoader(train_dataset, batch_size=self.batch_size, shuffle=True, num_workers = self.num_workers)
+        self.val_dataset = DataLoader(val_dataset, batch_size=self.batch_size, shuffle = False, num_workers = self.num_workers)
+        self.test_dataset = DataLoader(test_dataset, batch_size=len(test_dataset), shuffle = False, num_workers = self.num_workers)
 
     def train_dataloader(self):
         return self.train_dataset