Add callbacks (#7315)

* Add `on_train_start()` callback

* Update

* Update

val.py

@@ -188,8 +188,10 @@ def run(
     dt, p, r, f1, mp, mr, map50, map = [0.0, 0.0, 0.0], 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0
     loss = torch.zeros(3, device=device)
     jdict, stats, ap, ap_class = [], [], [], []
+    callbacks.run('on_val_start')
     pbar = tqdm(dataloader, desc=s, bar_format='{l_bar}{bar:10}{r_bar}{bar:-10b}')  # progress bar
     for batch_i, (im, targets, paths, shapes) in enumerate(pbar):
+        callbacks.run('on_val_batch_start')
         t1 = time_sync()
         if cuda:
             im = im.to(device, non_blocking=True)
@@ -260,6 +262,8 @@ def run(
             f = save_dir / f'val_batch{batch_i}_pred.jpg'  # predictions
             Thread(target=plot_images, args=(im, output_to_target(out), paths, f, names), daemon=True).start()
 
+        callbacks.run('on_val_batch_end')
+
     # Compute metrics
     stats = [np.concatenate(x, 0) for x in zip(*stats)]  # to numpy
     if len(stats) and stats[0].any():