diff --git a/README.md b/README.md
index 5ca5e8eff2a0cb3362c4b6d48177043adfd263f9..1ed91e0e630228a038dc03e860160a7b473e67e2 100644
--- a/README.md
+++ b/README.md
@@ -467,6 +467,9 @@ Stage2 images already downloaded and cropped are available [here](https://mosqui
python train_bb_detector.py --config ./resources/yolov8n.json --images_path ./data/images --initial_cv ./resources/files_10k_bb_4folds.csv
+First, it will create a labels/ folder under images/ folder with Yolo expected format. Second it will create .yaml file for each Yolo fold training.
+
+
**3/ Run classifiers training scripts:**
You can remove --wandb_project if you don’t have a [wandb](https://wandb.ai/) account --full_train option if you want to train CV models to monitor F1/Precision/Recall score.
diff --git a/mqt/training/train_bb_detector.py b/mqt/training/train_bb_detector.py
index 76a3872e39385443a0ccdb42d53c82ed882e41c8..1ab977fb4fbdcb3a9d3d83d828690e66d98f526d 100644
--- a/mqt/training/train_bb_detector.py
+++ b/mqt/training/train_bb_detector.py
@@ -78,23 +78,23 @@ def generate_yolo_labels(train_pd, data_home):
if xmin_ < 0:
xmin_ = 0
if xmin_ > w:
- print("w", row["uid"])
+ # print("w", row["uid"])
xmin_ = 0 # w
if ymin_ < 0:
ymin_ = 0
if ymin_ > h:
- print("h", row["uid"])
+ # print("h", row["uid"])
ymin_ = 0 # h
if xmax_ < 0:
xmax_ = 0
if xmax_ > w:
- print("w", row["uid"])
+ # print("w", row["uid"])
xmax_ = w
if ymax_ < 0:
ymax_ = 0
if ymax_ > h:
- print("h", row["uid"])
+ # print("h", row["uid"])
ymax_ = h
filename = row["img_fName"].replace(".jpeg", ".txt")
@@ -110,11 +110,15 @@ def generate_yolo_labels(train_pd, data_home):
bbx = ((xmax_ + xmin_) / 2.0) / w
bby = ((ymax_ + ymin_) / 2.0) / h
+ labels_path = os.path.join(data_home, "labels")
+ if not os.path.exists(labels_path):
+ os.makedirs(labels_path)
+
with open(os.path.join(data_home, "labels", filename), "w") as f:
f.write(str(label) + " " + str(bbx) + " " + str(bby) + " " + str(bbw) + " " + str(bbh))
-def generate_yolo_list(train_home, train_pd, seed=SEEDS[0], exclude_noisy=NOISY, folds=FOLDS, single_class=SINGLE_CLASS):
+def generate_yolo_list(train_pd, train_home, seed=SEEDS[0], exclude_noisy=NOISY, folds=FOLDS, single_class=SINGLE_CLASS):
# Generate YOLO lists
for fold_ in range(folds):
@@ -190,9 +194,8 @@ def get_model(architecture, weights):
def train_yolo(config, architecture="YOLO", model_backbone="yolov8n", image_size=IMAGE_SIZE,
- models_folder="mosquito_yolo_models", seed=SEEDS[0]):
+ models_folder="mosquito_yolo_models", seed=SEEDS[0], resume_fold=0):
- resume_fold = 0
for fold_ in range(FOLDS):
torch.cuda.empty_cache()
if fold_ < resume_fold:
diff --git a/mqt/training/train_classifier.py b/mqt/training/train_classifier.py
index 31fb3247432144e013d91fe76888a90d71c392b0..4afb5352db09de8d817b4d2e3a0f74bbe5250126 100644
--- a/mqt/training/train_classifier.py
+++ b/mqt/training/train_classifier.py
@@ -192,7 +192,7 @@ BAD_YOLO8N_768_OOF = [
def train_cls(train_boxes_home, config, train_pd, train_background_pd=None, external_pd=None,
wandb_project=None, models_home="./mosquito_models", full_train=False,
- exclude_noisy=BAD_YOLO8N_768_OOF):
+ exclude_noisy=BAD_YOLO8N_768_OOF, resume_fold=0):
seed_everything(config.seed, workers=True)
@@ -279,7 +279,7 @@ def train_cls(train_boxes_home, config, train_pd, train_background_pd=None, exte
wandb.finish()
else:
- resume_fold = 0
+ # resume_fold = 0
for fold_ in range(config.folds):
if fold_ < resume_fold:
continue
diff --git a/train_bb_detector.py b/train_bb_detector.py
index 62aab4b454cda7a4bf68c3cf49c85da34aa56bf0..72c152a1ebe092da0465ba409adeb75f3102d371 100644
--- a/train_bb_detector.py
+++ b/train_bb_detector.py
@@ -3,8 +3,8 @@ import pandas as pd
import os
import argparse
-from mqt.training.train_bb_detector import train_yolo
-from my_models.utils.torch import Config
+from mqt.training.train_bb_detector import train_yolo, generate_yolo_labels, generate_yolo_list
+from my_models.utils.torch import Config, SEEDS
def check_path(path):
@@ -22,17 +22,35 @@ if __name__ == '__main__':
parser.add_argument('--config', type=str, default='./resources/yolov8n.json', help='Path to yolo configuration file')
parser.add_argument('--images_path', type=str, default="./data/images", help='Path to images folder')
parser.add_argument('--initial_cv', type=str, default="./resources/files_10k_bb_4folds.csv", help='Path to initial files with CV split')
- parser.add_argument('--models_home', type=str, default="./mosquito_yolo_models", help='Yolo model home')
+ parser.add_argument('--models_home', type=str, default="mosquito_yolo_models", help='Yolo model home')
parser.add_argument('--image_size', type=int, default=768, help='Image size')
parser.add_argument('--epochs', type=int, default=128, help='Epochs')
+ parser.add_argument('--resume_fold', type=int, default=0, help='Resume training from a given fold')
args = parser.parse_args()
train_file = args.initial_cv
train_home = args.images_path
check_path(train_home)
+ config_path = args.config
+ resume_fold = args.resume_fold
+ image_size = args.image_size
+ models_home = args.models_home
check_path(train_file)
train_pd = pd.read_csv(train_file)
- print("Initial available:", train_pd.shape)
+ print("Initial data available:", train_pd.shape)
+
+ check_path(config_path)
+ config = Config(json.load(open(config_path, "r")))
+ print("Config loaded:", config.__dict__)
+
+ print("Preparing Yolo bounding boxes labels...")
+ generate_yolo_labels(train_pd, train_home)
+
+ print("Preparing Yolo training...")
+ generate_yolo_list(train_pd, train_home)
+
+ train_yolo(config, architecture="YOLO", model_backbone="yolov8n", image_size=image_size,
+ models_folder=models_home, seed=SEEDS[0], resume_fold=0)
diff --git a/train_classifier.py b/train_classifier.py
index 093a513d4f4e44ccd8f3b2d37069e2b1b7e8ac10..62ee72310c159ff90cc3ef3342cb57bc3edd5646 100644
--- a/train_classifier.py
+++ b/train_classifier.py
@@ -31,6 +31,7 @@ if __name__ == '__main__':
parser.add_argument('--epochs', type=int, default=96, help='Epochs')
parser.add_argument('--batch_size', type=int, default=32, help='Batch size')
parser.add_argument('--num_workers', type=int, default=8, help='CPU workers')
+ parser.add_argument('--resume_fold', type=int, default=0, help='Resume training from a given fold')
args = parser.parse_args()
@@ -44,6 +45,7 @@ if __name__ == '__main__':
config_path = args.config
full_train = args.full_train
wandb_project = args.wandb_project
+ resume_fold = args.resume_fold
if wandb_project is not None:
print("Wandb project:", wandb_project)
@@ -77,4 +79,5 @@ if __name__ == '__main__':
print()
train_cls(train_boxes_home, config, train_pd, train_background_pd=train_background_pd, external_pd=external_pd,
- wandb_project=wandb_project, models_home=args.models_home, full_train=full_train)
+ wandb_project=wandb_project, models_home=args.models_home, full_train=full_train,
+ resume_fold=resume_fold)