Paddle2ONNX不支持导出半精度ONNX模型

[tiandou-tangdou]

Describe the bug

paddle框架提供的paddle.onnx.export 不支持导出半精度ONNX模型，会直接报错[ERROR] Float16 is not supported.
同paddle2onnx也不支持导出半精度ONNX模型，期望提供方法能够支持这个需求。

related issue: PaddlePaddle/Paddle#57194

最小的实现示例：

import paddle
from paddlenlp.transformers import UIEX # 从模型代码中导入模型
model = UIEX.from_pretrained("uie-x-base") # 实例化模型
model.to(dtype="float16") # 加载预训练模型参数
model.eval() # 将模型设置为评估状态

input_spec = [
paddle.static.InputSpec(shape=[None, None], dtype="int64", name="input_ids"),
paddle.static.InputSpec(shape=[None, None], dtype="int64", name="token_type_ids"),
paddle.static.InputSpec(shape=[None, None], dtype="int64", name="position_ids"),
paddle.static.InputSpec(shape=[None, None], dtype="int64", name="attention_mask"),
paddle.static.InputSpec(shape=[None, None, 4], dtype="int64", name="bbox"),
paddle.static.InputSpec(shape=[None, 3, 224, 224], dtype="float16", name="image"),
] # # 定义输入数据

print("Exporting ONNX model to %s" % "./uiex_fp16.onnx")
paddle.onnx.export(model, "./uiex_fp16", input_spec=input_spec) # ONNX模型导出
print("ONNX model exported.")

另，网上提供的工具https://zenn.dev/pinto0309/scraps/588ed8342e2182 将FP32的onnx模型转为FP16后，此FP16的onnx模型存在问题不能在onnxruntime上使用。

Informations (please complete the following information):

[hl-gl]

请问解决了吗？

[Zheng-Bicheng]

会在下面的PR中修复Paddle2ONNX 无法原生导出FP16模型的Bug

• [Hackathon No.82] Support fp16 #1151

[github-actions]

This issue is stale because it has been open for 30 days with no activity.

[github-actions]

This issue was closed because it has been inactive for 14 days since being marked as stale.