Skip to content

X
X2Paddle

PaddlePaddle / X2Paddle
大约 1 年 前同步成功

通知 328
Star 698
Fork 167
X
X2Paddle

体验新版 GitCode，发现更多精彩内容 >>

提交 ba85e189 编写于 作者: S SunAhong1993
浏览文件
操作

fix the bug

上级 3c80edf9
隐藏空白更改
内联 并排
Showing with 8 addition and 8 deletion
x2paddle/decoder/pytorch_decoder.py
浏览文件 @ ba85e189
......@@ -21,14 +21,14 @@ import numpy as np
class Decoder(object):
def _optimize_graph(self, graph):
torch._C._jit_pass_constant_propagation(graph)
# torch._C._jit_pass_dce(graph)
# torch._C._jit_pass_lint(graph)
# torch._C._jit_pass_peephole(graph)
# torch._C._jit_pass_lint(graph)
# torch._C._jit_pass_dce(graph)
# torch._C._jit_pass_lint(graph)
# torch._C._jit_pass_canonicalize(graph)
# torch._C._jit_pass_lint(graph)
torch._C._jit_pass_dce(graph)
torch._C._jit_pass_lint(graph)
torch._C._jit_pass_peephole(graph)
torch._C._jit_pass_lint(graph)
torch._C._jit_pass_dce(graph)
torch._C._jit_pass_lint(graph)
torch._C._jit_pass_canonicalize(graph)
torch._C._jit_pass_lint(graph)
torch._C._jit_pass_constant_propagation(graph)
return graph
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或