Thrsu opened a new issue, #15759:
URL: https://github.com/apache/tvm/issues/15759
I encountered an assertion error while attempting to convert a torch.fx
model with interpolation using TVM.
### Actual behavior
```
Traceback (most recent call last):
...
mod = from_fx(fx_model, input_info)
File
"/workplace/software/tvm/tvm/python/tvm/relax/frontend/torch/fx_translator.py",
line 1475, in from_fx
return TorchFXImporter().from_fx(
File
"/workplace/software/tvm/tvm/python/tvm/relax/frontend/torch/fx_translator.py",
line 1362, in from_fx
self.env[node] = self.convert_map[func_name](node)
File
"/workplace/software/tvm/tvm/python/tvm/relax/frontend/torch/fx_translator.py",
line 1008, in _interpolate
assert recompute_scale_factor is None
AssertionError
```
### Environment
- branch: unity
- tvm: v0.14.dev0-595-gfa0d35b
- torch: 2.0.1
### Steps to reproduce
```python
import torch
from torch import fx
from torch.nn import Module
import tvm
from tvm import relax
from tvm.relax.frontend.torch import from_fx
input_data = torch.randn([5, 5, 10, 10], dtype=torch.float32)
para_1 = 4
para_2 = None
para_3 = 'bicubic'
para_4 = None
para_5 = False
class interpolate(Module):
def forward(self, input):
return torch.nn.functional.interpolate(input,
para_1,para_2,para_3,para_4,para_5,)
model = interpolate().float()
input_info = list(zip([list(inp.shape) for inp in input_data],
[str(inp.dtype) for inp in input_data]))
fx_model : torch.fx.GraphModule = fx.symbolic_trace(model)
with torch.no_grad():
mod = from_fx(fx_model, input_info)
```
### Triage
* needs-triage
--
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]
