Bug description:
when I use compile a keras model, It crashed. The crash message is shown as followsing:
Conditions(triggering this bug)
- target= ‘cuda’
- opt_level = 1
- use
relay.vm.compile()
to compile rather thanrelay.build_module.build()
Only when these three conditions are met at the same time, the bug will be triggered.
The Reproducible script
import keras
import tvm
import tvm.relay as relay
model_path = './xception-imagenet_origin.h5'
predict_model = keras.models.load_model(model_path)
print(predict_model.input)
shape_dict = {'input_7': (1, 3, 299, 299)}
irmod, params = relay.frontend.from_keras(predict_model, shape_dict)
target = 'cuda'
ctx = tvm.gpu(0)
with tvm.transform.PassContext(opt_level=1):
# graph, lib, params = relay.build_module.build(irmod, target, params=params)
vm_exec = relay.vm.compile(irmod, target, params=params)
Environment
TVM : 0.8.dev0
OS: Ubuntu 16.04
Anyone can download this Keras model from the below link: