compute_val_loss parser action to store_true

Either the argument should be named "--no-val-loss" or something like this and have a store_false action, or be named "--compute-val-loss" and have a store_true action. Second option is more coherent with the fact that providing a validation set is optional.

keras_retinanet/bin/train.py

@@ -410,7 +410,7 @@ def csv_list(string):
     parser.add_argument('--image-max-side',   help='Rescale the image if the largest side is larger than max_side.', type=int, default=1333)
     parser.add_argument('--config',           help='Path to a configuration parameters .ini file.')
     parser.add_argument('--weighted-average', help='Compute the mAP using the weighted average of precisions among classes.', action='store_true')
-    parser.add_argument('--compute-val-loss', help='Compute validation loss during training', dest='compute_val_loss', action='store_false')
+    parser.add_argument('--compute-val-loss', help='Compute validation loss during training', dest='compute_val_loss', action='store_true')
 
     # Fit generator arguments
     parser.add_argument('--workers', help='Number of multiprocessing workers. To disable multiprocessing, set workers to 0', type=int, default=1)