[GitHub] [incubator-tvm] MeioJane opened a new issue #5446: [NMS] nms operation cost too mush time

[GitBox <gi...@apache.org>]

MeioJane opened a new issue #5446:
URL: https://github.com/apache/incubator-tvm/issues/5446


   Hi: I create a network using relay.build. Now I need to add the nms(relya.vision.non_max_suppression) after the network, and then get a new network, But I find only the nms operation cost about 30ms time. It is too strange to cost so much time. I want to know if there is any wrong with nms using or add the nms layer. There are part code as follows:
   ```
   relay_mod, relay_params = relay.frontend.from_mxnet(
           mx_sym,
           shape=input_shapes,
           dtype={'data': 'float32'},
           arg_params=arg_params,
           aux_params=aux_params
       )
   func = relay_mod["main"]
   valid_count = relay.var('valid_count', relay.TensorType((1,), 'int32'),)
   out = relay.vision.non_max_suppression(func.body, valid_count, max_output_size=100, top_k=400, iou_threshold=0.45, return_indices=False)
   func = relay.Function(func.params, out, None, func.type_params, func.attrs)
   target = tvm.target.create('cuda')
   with autotvm.apply_history_best(log_file):
       print('Compile with relay ...')
       with relay.build_config(opt_level=3):
           graph, lib, params = relay.build(
               func,
               # relay_mod,
               target,
               params=relay_params
           )
   ```


----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org

[GitHub] [incubator-tvm] tqchen commented on issue #5446: [NMS] nms operation cost too mush time

[GitBox <gi...@apache.org>]

tqchen commented on issue #5446:
URL: https://github.com/apache/incubator-tvm/issues/5446#issuecomment-621241256


   Thanks for start the discussion, Please open a new discussion thread on https://discuss.tvm.ai/


----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org