We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
测试发现,转换Pytorch的normalize函数存在问题: y=torch.nn.functional.normalize(x, p=1, dim=1) 转换ONNX,opset_version=9,可以正常转换,但在推理时出现异常:
normalize
y=torch.nn.functional.normalize(x, p=1, dim=1)
#pragma OPENCL EXTENSION cl_khr_fp16 : enable ^ <kernel>:73:18: error: use of undeclared identifier 'inff' FLOAT4 out = OPERATOR; ^ <built-in>:28:59: note: expanded from here #define OPERATOR clamp(in,(FLOAT4)(1.00000e-12f),(FLOAT4)(inff))
从问题看,是未能识别字符inff导致的异常,而正常情况下,无穷大应该表示为:inf,而不是inff 于是尝试改动tnnproto文件,将normalize层inf改为in,推理则正常了 我怀疑,TNN源码是不多加了f导致出现inff异常
inff
inf
The text was updated successfully, but these errors were encountered:
No branches or pull requests
测试发现,转换Pytorch的
normalize
函数存在问题:y=torch.nn.functional.normalize(x, p=1, dim=1)
转换ONNX,opset_version=9,可以正常转换,但在推理时出现异常:
#pragma OPENCL EXTENSION cl_khr_fp16 : enable ^ <kernel>:73:18: error: use of undeclared identifier 'inff' FLOAT4 out = OPERATOR; ^ <built-in>:28:59: note: expanded from here #define OPERATOR clamp(in,(FLOAT4)(1.00000e-12f),(FLOAT4)(inff))
从问题看,是未能识别字符
inff
导致的异常,而正常情况下,无穷大应该表示为:inf
,而不是inff
于是尝试改动tnnproto文件,将normalize层inf改为in,推理则正常了
我怀疑,TNN源码是不多加了f导致出现
inff
异常The text was updated successfully, but these errors were encountered: