You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello, after reading the Question 1 about initial set of placement locations (from physical synthesis) affect the (relative) quality of the CT. I am curious how the vacuous placements file was generated.
Are they generated directly by changing the coordinate information in these documents?(circuit_training/environment/test_data/ariane) Or generated in some other unmentioned way?
The text was updated successfully, but these errors were encountered:
I believe the method used to change coordinate does not matter as the resulted plc will be similar.
Either 1 or 2 should end up with the same plc that later consumes by CT.
Use physical design tool to relocate all blocks and feed to FormatTranslator to generate plc file
As a student in internship, I still have doubts about pre-trained model. When I finish training the Ariane model from physical synthesis, I get the output folder. If I want to use the pre-trained model at this point, can I just keep the policies file and change the input file?
Also in my programme, only the checkpoints in the policies folder are updated multiple times. Does this contain the information I need for the pre-trained model?
Hello, after reading the Question 1 about initial set of placement locations (from physical synthesis) affect the (relative) quality of the CT. I am curious how the vacuous placements file was generated.
Are they generated directly by changing the coordinate information in these documents?(circuit_training/environment/test_data/ariane) Or generated in some other unmentioned way?
The text was updated successfully, but these errors were encountered: