Threaded TensorBoard graph logging (#9070)

* Log TensorBoard graph on pretrain_routine_end

* fix

train.py

@@ -219,7 +219,7 @@ def train(hyp, opt, device, callbacks):  # hyp is path/to/hyp.yaml or hyp dictio
                 check_anchors(dataset, model=model, thr=hyp['anchor_t'], imgsz=imgsz)  # run AutoAnchor
             model.half().float()  # pre-reduce anchor precision
 
-        callbacks.run('on_pretrain_routine_end', labels, names, plots)
+        callbacks.run('on_pretrain_routine_end', labels, names)
 
     # DDP mode
     if cuda and RANK != -1:
@@ -328,7 +328,7 @@ def train(hyp, opt, device, callbacks):  # hyp is path/to/hyp.yaml or hyp dictio
                 mem = f'{torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0:.3g}G'  # (GB)
                 pbar.set_description(('%11s' * 2 + '%11.4g' * 5) %
                                      (f'{epoch}/{epochs - 1}', mem, *mloss, targets.shape[0], imgs.shape[-1]))
-                callbacks.run('on_train_batch_end', ni, model, imgs, targets, paths, plots)
+                callbacks.run('on_train_batch_end', model, ni, imgs, targets, paths)
                 if callbacks.stop_training:
                     return
             # end batch ------------------------------------------------------------------------------------------------
@@ -420,7 +420,7 @@ def train(hyp, opt, device, callbacks):  # hyp is path/to/hyp.yaml or hyp dictio
                     if is_coco:
                         callbacks.run('on_fit_epoch_end', list(mloss) + list(results) + lr, epoch, best_fitness, fi)
 
-        callbacks.run('on_train_end', last, best, plots, epoch, results)
+        callbacks.run('on_train_end', last, best, epoch, results)
 
     torch.cuda.empty_cache()
     return results