jikechao opened a new issue, #15005:
URL: https://github.com/apache/tvm/issues/15005
The Pytorch model with a `dropout` layer gave inconsistent inference results
between PyTorch and TVM.
The RelayIR arising from the PyTorch model is here:
```
def @main(%input0: Tensor[(5), float64] /*
span=aten::alpha_dropout_0.input0:0:0 */) {
%0 = nn.dropout(%input0, rate=0.2f) /* span=aten::alpha_dropout_0:0:0 */;
%0.0 /* span=aten::alpha_dropout_0:0:0 */
}
```
### Actual behavior
### Steps to reproduce
```
import torch
from tvm import relay
import tvm
import numpy as np
from torch.nn import Module
input_data = torch.randn([5], dtype=torch.float64)
class alpha_dropout(Module):
def forward(self, *args):
return torch.nn.functional.alpha_dropout(args[0], 0.2,True)
m = alpha_dropout().float().eval()
torch_outputs = m(input_data)
trace = torch.jit.trace(m, input_data)
input_shapes = [('input0', torch.Size([5]))]
mod, params = relay.frontend.from_pytorch(trace, input_shapes)
print(mod)
with tvm.transform.PassContext(opt_level=3):
exe = relay.create_executor('graph', mod=mod, params=params,
device=tvm.device('llvm', 0), target='llvm').evaluate()
input_tvm = {'input0': np.array(input_data, dtype='float64')}
tvm_outputs = exe(**input_tvm).asnumpy()
np.testing.assert_allclose(torch_outputs, tvm_outputs, rtol=1e-3, atol=1e-3)
```
### Triage
* needs-triage
* frontend::pytorch
cc @shingjan @echuraev @Hzfengsy
Could you help me review this exception?
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
