[Bugfix][Relay] Fix softplus about the wrong calculation formula in Relay PyTorch frontend

[jikechao]

Due to lacking consider of the attribute threshold in Softplus, the inference results in TVM are different from PyTorch.
You can see the definition of Softplus in Pytorch documentation

Expected Behavior

The TVM gives the same inference results as PyTorch.

Actual Behavior

Steps for reproduce

import torch
from tvm import relay
import tvm
import numpy as np

m = torch.nn.Softplus(1, 2,)
input_data = torch.tensor([[1.0, 4.0]], dtype=torch.float32)

torch_outputs = m(input_data)

trace = torch.jit.trace(m, input_data)
input_shapes = [('input0', torch.Size([1, 2]))]

mod, params = relay.frontend.from_pytorch(trace, input_shapes)

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([[1.,  4.]], dtype='float32')}
tvm_outputs = exe(**input_tvm).asnumpy()

np.testing.assert_allclose(torch_outputs, tvm_outputs, rtol=1e-3, atol=1e-3)

cc @Hzfengsy @echuraev

[tvm-bot]

Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from Reviewers by @-ing them in a comment.

• cc @shingjan _{See #10317 for details}

_{Generated by tvm-bot}

[echuraev]

LGTM. Thanks

[echuraev]

@tvm-bot rerun

[jikechao]

The added test cases produce a wired flaky problem, I'll try to figure out it later.

[jikechao]

This problem has been solved. Waiting for the CI testing.