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
flops, params = get_model_complexity_info(net, input_res=(3, 256, 512), input_constructor=prepare_input, as_strings=True, print_per_layer_stat=True)
input_res的格式是什么?channel,row,col?还是channel,col,row?
The text was updated successfully, but these errors were encountered:
Pytorch uses the NCHW data layout and the input res parameter follows this practice. So in your terms the order is channel, row, col.
input res
Sorry, something went wrong.
Pytorch 使用 NCHW 数据布局,input res参数也遵循这种做法。所以用你的话来说,顺序是通道、行、列。
Hi, if my model input is dict, and the dict have many keys, how can I set the input_res? Can you tell me an example code? Thank you very much!
Pytorch 使用 NCHW 数据布局,input res参数也遵循这种做法。所以用你的话来说,顺序是通道、行、列。 Hi, if my model input is dict, and the dict have many keys, how can I set the input_res? Can you tell me an example code? Thank you very much!
Using input_constructor functionality you can shape any input dict, see #14
input_constructor
No branches or pull requests
flops, params = get_model_complexity_info(net, input_res=(3, 256, 512), input_constructor=prepare_input, as_strings=True, print_per_layer_stat=True)
input_res的格式是什么?channel,row,col?还是channel,col,row?
The text was updated successfully, but these errors were encountered: