-
Notifications
You must be signed in to change notification settings - Fork 31
New issue
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
add trt args and trt infer #180
base: master
Are you sure you want to change the base?
Conversation
|
||
|
||
if args.use_int8_online: | ||
for j in range(10): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
校准数据集的batch数可以用一个参数来控制,--calibration_batch_num
InferenceNet().get() | ||
flow.tensorrt.cache_int8_calibration() | ||
|
||
warmup = 2 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
warmup也需要用一个参数来控制
help='Whether to use online int8 calibration' | ||
) | ||
parser.add_argument( | ||
'--use_int8_offline', |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
这里缩进和其他地方不一样
No description provided.