Dinar Sharafutdinov

I have the same problem with Openvslam not in ROS, but just in docker. I tried to run Kaist dataset in monocular mode using run_image_slam and seems it works fine,...

I think the reason for such a behavior is that option `_C.TRAIN.DRIVABLE_ONLY = True` does not include encoder training.

> > How to change it to 13 which BDD100K has? > > Thanks, > > 1. search `nc=1`, and change it to `nc=13`; > 2. search `single_cls = True`,...

> @dinarkino What mAP did you get for multiple classes? My mAP after making the changes @thinkthinking mentioned is 0.25 I'm training the model on my own data, but I...

Hey @ankur219 I got training results. After 70 epochs I have such metrics (I did not train lane line segmentation task). Epoch: [79] Loss(0.329) Driving area Segment: Acc(0.964) IOU (0.816)...

Yeah, it seems so. I started an experiment just for one raw car class on bdd data and got 60% of map after 30 epochs which is higher than for...

Yes, you can do that, but you should change the code. You can find similar functionality in YOLOv5 repository. You need to drop the last layer of the detection head,...

@LuthraBhomik yes, that is exactly what I said. If you want to reuse weights with different number of classes, you should change the code. Or you can train the network...

I can confirm that using specific VAE solves the problem. For example, for [SG161222/Realistic_Vision_V6.0_B1_noVAE](https://huggingface.co/SG161222/Realistic_Vision_V6.0_B1_noVAE) model the [stabilityai/sd-vae-ft-mse-original](https://huggingface.co/stabilityai/sd-vae-ft-mse-original) should be used