W&B refactor, handle exceptions, CI example (ultralytics#5618)

* handle exceptions| attempt CI

* update

* Pre-commit manual run

* yaml one-liner

* Update ci-testing.yml

* Comment W&B CI

Leave as example for future separate CI

* Update ci-testing.yml

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

.github/workflows/ci-testing.yml

@@ -51,12 +51,15 @@ jobs:
         run: |
           python -m pip install --upgrade pip
           pip install -qr requirements.txt -f https://download.pytorch.org/whl/cpu/torch_stable.html
-          pip install -q onnx tensorflow-cpu keras==2.6.0  # for export
+          pip install -q onnx tensorflow-cpu keras==2.6.0  # wandb  # extras
           python --version
           pip --version
           pip list
         shell: bash
 
+      # - name: W&B login
+      #   run: wandb login 345011b3fb26dc8337fd9b20e53857c1d403f2aa
+
       - name: Download data
         run: |
           # curl -L -o tmp.zip https://github.com/ultralytics/yolov5/releases/download/v1.0/coco128.zip

utils/loggers/wandb/log_dataset.py

@@ -2,11 +2,15 @@
 
 from wandb_utils import WandbLogger
 
+from utils.general import LOGGER
+
 WANDB_ARTIFACT_PREFIX = 'wandb-artifact://'
 
 
 def create_dataset_artifact(opt):
     logger = WandbLogger(opt, None, job_type='Dataset Creation')  # TODO: return value unused
+    if not logger.wandb:
+        LOGGER.info("install wandb using `pip install wandb` to log the dataset")
 
 
 if __name__ == '__main__':

utils/loggers/wandb/wandb_utils.py

@@ -17,7 +17,7 @@
     sys.path.append(str(ROOT))  # add ROOT to PATH
 
 from utils.datasets import LoadImagesAndLabels, img2label_paths
-from utils.general import check_dataset, check_file
+from utils.general import LOGGER, check_dataset, check_file
 
 try:
     import wandb
@@ -203,7 +203,7 @@ def check_and_upload_dataset(self, opt):
         config_path = self.log_dataset_artifact(opt.data,
                                                 opt.single_cls,
                                                 'YOLOv5' if opt.project == 'runs/train' else Path(opt.project).stem)
-        print("Created dataset config file ", config_path)
+        LOGGER.info(f"Created dataset config file {config_path}")
         with open(config_path, errors='ignore') as f:
             wandb_data_dict = yaml.safe_load(f)
         return wandb_data_dict
@@ -316,7 +316,7 @@ def log_model(self, path, opt, epoch, fitness_score, best_model=False):
         model_artifact.add_file(str(path / 'last.pt'), name='last.pt')
         wandb.log_artifact(model_artifact,
                            aliases=['latest', 'last', 'epoch ' + str(self.current_epoch), 'best' if best_model else ''])
-        print("Saving model artifact on epoch ", epoch + 1)
+        LOGGER.info(f"Saving model artifact on epoch {epoch + 1}")
 
     def log_dataset_artifact(self, data_file, single_cls, project, overwrite_config=False):
         """
@@ -368,7 +368,7 @@ def map_val_table_path(self):
         Useful for - referencing artifacts for evaluation.
         """
         self.val_table_path_map = {}
-        print("Mapping dataset")
+        LOGGER.info("Mapping dataset")
         for i, data in enumerate(tqdm(self.val_table.data)):
             self.val_table_path_map[data[3]] = data[0]
 
@@ -488,7 +488,13 @@ def end_epoch(self, best_result=False):
             with all_logging_disabled():
                 if self.bbox_media_panel_images:
                     self.log_dict["BoundingBoxDebugger"] = self.bbox_media_panel_images
-                wandb.log(self.log_dict)
+                try:
+                    wandb.log(self.log_dict)
+                except BaseException as e:
+                    LOGGER.info(f"An error occurred in wandb logger. The training will proceed without interruption. More info\n{e}")
+                    self.wandb_run.finish()
+                    self.wandb_run = None
+
                 self.log_dict = {}
                 self.bbox_media_panel_images = []
             if self.result_artifact: