Shirley4042 opened a new issue, #19977:
URL: https://github.com/apache/tvm/issues/19977
### Expected behavior
The ONNX model should be imported successfully by the Relax ONNX frontend.
### Actual behavior
`from_onnx` fails while converting the `BatchNormalization` node because
`relax.nn.batch_norm` requires all inputs to have the same dtype.
```text
tvm.error.InternalError:
relax.nn.batch_norm requires all the input tensors to have the same dtype.
However, the gamma has dtype float32, which is different from the input
data's dtype float16.
```
### Environment
```text
TVM: 0.25.dev0, built from source
Python: 3.10
OS: Ubuntu 22.04
Target: llvm (CPU)
ONNX frontend: tvm.relax.frontend.onnx.from_onnx
```
### Steps to reproduce
```python
import numpy as np
import onnx
from onnx import TensorProto, helper, numpy_helper
from tvm.relax.frontend.onnx import from_onnx
data = helper.make_tensor_value_info(
"data",
TensorProto.FLOAT16,
[1, 3, 2, 2],
)
output = helper.make_tensor_value_info(
"output",
TensorProto.FLOAT16,
[1, 3, 2, 2],
)
params = [
numpy_helper.from_array(
np.array([1.0, 1.5, 2.0], dtype=np.float32),
name="gamma",
),
numpy_helper.from_array(
np.array([0.0, 0.1, -0.1], dtype=np.float32),
name="beta",
),
numpy_helper.from_array(
np.array([0.2, -0.3, 0.4], dtype=np.float32),
name="mean",
),
numpy_helper.from_array(
np.array([1.0, 1.5, 2.0], dtype=np.float32),
name="var",
),
]
node = helper.make_node(
"BatchNormalization",
inputs=["data", "gamma", "beta", "mean", "var"],
outputs=["output"],
epsilon=1e-5,
momentum=0.9,
training_mode=0,
)
graph = helper.make_graph(
[node],
"mixed_dtype_batchnorm",
[data],
[output],
initializer=params,
)
model = helper.make_model(
graph,
opset_imports=[helper.make_opsetid("", 15)],
)
onnx.checker.check_model(model, full_check=True)
mod = from_onnx(
model,
keep_params_in_input=False,
)
```
### Analysis
The Relax ONNX frontend directly converts the ONNX `BatchNormalization` node
into `relax.nn.batch_norm`.
The ONNX model contains mixed floating-point dtypes:
```text
data:float16, gamma:float32, beta:float32, moving_mean: float32, moving_var:
float32
```
The Relax `batch_norm` operator currently requires all five inputs to have
the same dtype. Therefore, the generated Relax expression fails during
`BlockBuilder.normalize()` before the ONNX model can be imported.
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
