correcting nn_ops_converter.py

Author: apbose

py/torch_tensorrt/fx/converters/nn_ops_converters.py

@@ -30,7 +30,7 @@ def hardtanh(network, submod, args, kwargs, layer_name):
     # args/kwargs should have already been normalized to kwargs
     assert len(args) == 0
 
-    activation.hardtanh(
+    return activation.hardtanh(
         network=network,
         target="torch.nn.modules.activation.Hardtanh",
         source_ir=SourceIR.NN,