-
Notifications
You must be signed in to change notification settings - Fork 414
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
Quantization and scaling #53
Comments
Hi @pooyaww, |
For a 5 layer DS-CNN in the following structure: Why are there 12 act_max values required, and what do they related to? |
12 quantization ranges correspond to the 10 layers that you mentioned + 1 input layer + 1 average pooling layer prior to FINAL_FC. |
@ccnankai Please don't spam on Issues, instead spend your time on reading materials, codes, articles and other issues. Spamming does not work for open source society. |
@ccnankai Yes, you are right. A greedy approach would lead you to an acceptable result, try levels in the same range you mentioned for the first layer while assigning zeros for other layers then check the accuracy, fix a level for the current layer, then go on until the last layer. It is exactly what has already been mentioned in the quantization tutorial of this repo. |
Is this correct?--act_max 32 0 0 0 0 0 0 0 0 0 0 0, ds_cnn useing that --acc_max value. |
@navsuda
In case of DNN, --act_max should have 5 parameters such as --act_max 32 30 30 30 30, while the DNN structure is made of 4 layers
How should I use these 5 --act_max values to scale 4 arm_fully_connected_q7() functions?
The text was updated successfully, but these errors were encountered: