nolanliou edited a comment on issue #6268:
URL: https://github.com/apache/incubator-tvm/issues/6268#issuecomment-675457643
The above problem solved by modifying the model code.
However, another problem occurred when inferring the type of intermediate
tensor and there is a `type cast` operator.
sample code to reproduce the error.
```
import torch
import tvm
from tvm import relay
import tvm.contrib.graph_runtime as runtime
def fn(x):
y = (x != 0).long()
y = y.to(dtype=torch.float32)
y = y[:, 0]
return y
jit = torch.jit.trace(fn, (torch.ones(4, 5, dtype=torch.int64),))
torch.jit.save(jit, "test.jit")
jit = torch.jit.load("test.jit", map_location=torch.device('cpu'))
jit.eval()
print(jit(torch.ones(4, 5, dtype=torch.int64)))
batch = 1
seq_length = 43
shape_list = [('input', [4, 5])]
input_types = [('input', 'torch.int64')]
print("==========relay=======")
#print(jit.code)
mod, params = relay.frontend.pytorch.from_pytorch(jit,
shape_list,
input_types=input_types,
// Add input types, otherwise input type only could be float32
default_dtype="float32")
```
----------------------------------------------------------------
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:
[email protected]
