[GitHub] [incubator-tvm] trevor-m commented on issue #4534: [Relay] Dead code elimination pass blows up call stack

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

trevor-m commented on issue #4534: [Relay] Dead code elimination pass blows up call stack
URL: https://github.com/apache/incubator-tvm/issues/4534#issuecomment-571817854
 
 
   I was getting a segfault just trying to run resnet152_v1 with the script below. Smaller models worked fine. Once I increased the stack limit using `ulimit -s unlimited`, the segfaults stopped.
   
   ```
   import numpy as np
   import time
   
   import tvm
   from tvm import relay
   import tvm.relay.testing
   import tvm.relay.transform
   from tvm.contrib import graph_runtime
   import mxnet
   from mxnet.gluon.model_zoo.vision import get_model
   dtype = 'float32'
   input_shape = (1, 3, 224, 224)
   i_data = np.random.uniform(0, 1, input_shape).astype(dtype)
   block = get_model('resnet152_v1', pretrained=True)
   mod, params = relay.frontend.from_mxnet(block, shape={'data': input_shape}, dtype=dtype)
   with relay.build_config(opt_level=3):
       graph, lib, params = relay.build(mod, "cuda", params=params)
   mod = graph_runtime.create(graph, lib, ctx=tvm.gpu(0))
   mod.set_input(**params)
   for i in range(10):
       mod.run(data=i_data)
   ```

----------------------------------------------------------------
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


With regards,
Apache Git Services