新增功能
- 添加enable_code_optim开关,解决部分场景下代码优化可能导致转换出错的问题 https://github.com/PaddlePaddle/X2Paddle/pull/696
新增模型支持
PyTorch->Paddle
- 首次支持声音克隆模型:MockingBird
- 轻量级检测算法:YOLOX
新增op
- 新增PyTorch op(5个):aten::repeat_interleave、aten::maxpool1d、aten::frobenius_norm、aten::silu、aten::format https://github.com/PaddlePaddle/X2Paddle/pull/691 https://github.com/PaddlePaddle/X2Paddle/pull/696
- 新增ONNX op(1个):GatherND https://github.com/PaddlePaddle/X2Paddle/pull/645
修复op
- 修复PyTorch op(5个):aten::div、aten::index_select、aten::select、aten::upsample_nearest2d、aten::_convolution https://github.com/PaddlePaddle/X2Paddle/pull/691 https://github.com/PaddlePaddle/X2Paddle/pull/689
- 修复ONNX op(3个):Split、Conv、Pad https://github.com/PaddlePaddle/X2Paddle/pull/645 https://github.com/PaddlePaddle/X2Paddle/pull/707 https://github.com/PaddlePaddle/X2Paddle/pull/687
- 修复PyTorch训练代码转换(2个):ToPILImage、Split https://github.com/PaddlePaddle/X2Paddle/pull/690 https://github.com/PaddlePaddle/X2Paddle/pull/694
修复功能
- Windows环境生成代码问题 https://github.com/PaddlePaddle/X2Paddle/pull/706
- 修复ONNX和PyTorch版本问题 https://github.com/PaddlePaddle/X2Paddle/pull/708
- 去除代码优化部分to_tensor操作,优化预测速度 https://github.com/PaddlePaddle/X2Paddle/pull/696
Contributors
- Thanks to external developers for their contributions to open source projects!@littletomatodonkey @zhoucz97 @firedent @dawn1206