-
Hello, I would like to ask which GPU you are using. I use the 3090, but it takes a long time to train the openlane. and in addition, is there any multi-gpu training code.
-
### Description
The variable that governs how much an instance can be moved after global placement for legalization, `PL_MAX_DISPLACEMENT_{X,Y}`, is set atrociously high at `0.1mm` along the Y axis a…
-
我们在openlane公开数据集上进行训练，但是训练到一半出现了cuda error的问题。我们怀疑这是数据集车道线类别超出了21类的限制？但是在用openlane.py处理数据集的时候，我们看到有对于超出的类别进行了修改
```
if lane_results['category'] >= 21:
lane_resu…
-
### Description
To maintain backwards compatibility with OpenLane 1, OpenLane 2 does not (by default) currently emit errors when there are hold violations in corners other than `*tt*`.
### Propo…
-
hi, thanks for your great work, some questions about the generalization of the virtual camera and the STP,
1.did you test the model trained on openlane with other datasets which the camera extrins…
-
### Description
I am trying to add a verilog file to OpenLane. I followed the instructions in getting_started. Here I create a code counter file then run the following command ./flow.tcl -design . Ho…
-
I would like to train a model which achieves your SOTA result of 0.825 F1@0.5 on OpenLane-V dataset. Which model/folder should I use for doing this? I assume I should use this one `Modeling/OpenLane-V…
aj96 updated
6 months ago
-
thanks for your work！
How to quickly train on custom dataset which only has front view, such as openlane and some BEV lane detection task. Can you give some suggestions?
Do you think MapTR can perf…
-
### Description
Hi all,
I create this issues due to i'm working on a project with OpenRAM, i create a module that combine two SRAM macros to work as one, the problem comes when i update OpenLane l…
-
Installed via:
% curl -L -O https://github.com/proppy/conda-eda/releases/download/v0.0-1382-g0155826/mixed-signal.sky130a-0-Linux-x86_64.sh
% bash mixed-signal.sky130a-0-Linux-x86_64.sh -p silic…