Vladimir Iglovikov
Vladimir Iglovikov
https://www.kaggle.com/c/3d-object-detection-for-autonomous-vehicles/discussion/108758626702 1. it seems that we can switch to LyftDataset().get simply by token, without specifying the type of table - tokens are still unique. 2. there is a bug in...
- [ ] No function to merge the data from 3 lidars. - [ ] We load huge json which takes a while. It is not always needed.
Would be nice to have a function, that for a given sample gets all LIdar points + annotation in the same coordinates. Figuring out what should be mapped where is...
I am decoding a list of videos with: ``` video = VideoReader(str(video_path), ctx=gpu(0)) frame_ids = list(range(300)) frames = video.get_batch(frame_ids).asnumpy() ``` on every iteration, GPU Ram consumption goes up till I...
``` from torchlars import LARS File "/home/vladimir/anaconda3/lib/python3.7/site-packages/torchlars/__init__.py", line 2, in from torchlars.lars import LARS File "/home/vladimir/anaconda3/lib/python3.7/site-packages/torchlars/lars.py", line 6, in from torchlars._adaptive_lr import compute_adaptive_lr ImportError: /home/vladimir/anaconda3/lib/python3.7/site-packages/torchlars/_adaptive_lr.cpython-37m-x86_64-linux-gnu.so: undefined symbol: THPVariableClass ```
Is there a way to convert the model into the `jit` format?
Could you please add license file?
It would be nice to add DPN as a feture extractor. Based on https://github.com/cypw/DPNs it may happen that it will work even better than DenseNet
`python3 volta_accelerate.py --onnx_trt=trtpython3 volta_accelerate.py --onnx_trt=trt` GPU: GTX 2080Ti Running from the docker image: `voltaml/volta_diffusion:v0.2 ` ``` [12/10/2022-22:18:01] [TRT] [E] 10: [optimizer.cpp::computeCosts::3728] Error Code 10: Internal Error (Could not find any...