Revert "Revert "add 'find_unused_parameters' in dist train""

This reverts commit eda7242b.

mmdet/apis/train.py

@@ -206,9 +206,14 @@ def _dist_train(model,
     ]
     # put model on gpus
     # model = MMDistributedDataParallel(model.cuda())
-    model = MMDistributedDataParallel(model.cuda(), 
-                                      device_ids=[torch.cuda.current_device()], 
-                                      broadcast_buffers=False)
+    find_unused_parameters = True
+    # Sets the `find_unused_parameters` parameter in
+    # torch.nn.parallel.DistributedDataParallel
+    model = MMDistributedDataParallel(
+        model.cuda(),
+        device_ids=[torch.cuda.current_device()],
+        broadcast_buffers=False,
+        find_unused_parameters=find_unused_parameters)
 
     # build runner
     optimizer = build_optimizer(model, cfg.optimizer)

tools/test.py

@@ -240,7 +240,11 @@ def main():
         model = MMDataParallel(model, device_ids=[0])
         outputs = single_gpu_test(model, data_loader, args.show)
     else:
-        model = MMDistributedDataParallel(model.cuda())
+        # model = MMDistributedDataParallel(model.cuda())
+        model = MMDistributedDataParallel(
+            model.cuda(),
+            device_ids=[torch.cuda.current_device()],
+            broadcast_buffers=False)
         outputs = multi_gpu_test(model, data_loader, args.tmpdir,
                                  args.gpu_collect)
 

tools/test_robustness.py

@@ -375,7 +375,11 @@ def main():
                 model = MMDataParallel(model, device_ids=[0])
                 outputs = single_gpu_test(model, data_loader, args.show)
             else:
-                model = MMDistributedDataParallel(model.cuda())
+                # model = MMDistributedDataParallel(model.cuda())
+                model = MMDistributedDataParallel(
+                    model.cuda(),
+                    device_ids=[torch.cuda.current_device()],
+                    broadcast_buffers=False)
                 outputs = multi_gpu_test(model, data_loader, args.tmpdir)
 
             rank, _ = get_dist_info()