W&B: More improvements and refactoring (#4205)

* Improve docstrings and run names

* default wandb login prompt with timeout

* return key

* Update api_key check logic

* Properly support zipped dataset feature

* update docstring

* Revert tuorial change

* extend changes to log_dataset

* add run name

* bug fix

* bug fix

* Update comment

* fix import check

* remove unused import

* Hardcore .yaml file extension

* reduce code

* Reformat using pycharm

* Remove redundant try catch

* More refactoring and bug fixes

* retry

* Reformat using pycharm

* respect LOGGERS include list

Co-authored-by: Glenn Jocher <[email protected]>

utils/loggers/__init__.py

@@ -48,12 +48,12 @@ class Loggers():
             self.tb = SummaryWriter(str(s))
 
         # W&B
-        try:
-            assert 'wandb' in self.include and wandb
-            run_id = torch.load(self.weights).get('wandb_id') if self.opt.resume else None
+        if wandb and 'wandb' in self.include:
+            wandb_artifact_resume = isinstance(self.opt.resume, str) and self.opt.resume.startswith('wandb-artifact://')
+            run_id = torch.load(self.weights).get('wandb_id') if self.opt.resume and not wandb_artifact_resume else None
             self.opt.hyp = self.hyp  # add hyperparameters
             self.wandb = WandbLogger(self.opt, run_id)
-        except:
+        else:
             self.wandb = None
 
         return self

utils/loggers/wandb/wandb_utils.py

@@ -158,11 +158,12 @@ class WandbLogger():
                         self.data_dict = check_dataset(opt.data)
 
                 self.setup_training(opt)
-                # write data_dict to config. useful for resuming from artifacts
                 if not self.wandb_artifact_data_dict:
                     self.wandb_artifact_data_dict = self.data_dict
-                self.wandb_run.config.update({'data_dict': self.wandb_artifact_data_dict},
-                                             allow_val_change=True)
+                # write data_dict to config. useful for resuming from artifacts. Do this only when not resuming.
+                if not opt.resume:
+                    self.wandb_run.config.update({'data_dict': self.wandb_artifact_data_dict},
+                                                 allow_val_change=True)
 
             if self.job_type == 'Dataset Creation':
                 self.data_dict = self.check_and_upload_dataset(opt)