Filip Drapejkowski
Filip Drapejkowski
I am struggling to understand it based on provided readme and provided examples - does this project support retraining of the face detector? Or does it only provide fine-tuning script...
Click to expand! ### Issue Type Bug ### Have you reproduced the bug with TF nightly? Yes ### Tensorflow Version v2.12.0-rc1-12-g0db597d0d75 2.12.0 ### Custom Code No ### OS Platform and...
### Prerequisite - [X] I have searched [Issues](https://github.com/open-mmlab/mmdetection3d/issues) and [Discussions](https://github.com/open-mmlab/mmdetection3d/discussions) but cannot get the expected help. - [X] I have read the [FAQ documentation](https://github.com/open-mmlab/mmdetection3d/blob/1.1/docs/en/notes/faq.md) but cannot get the expected help....
When running `python kitti_dataloader.py --output-width 608` I get ``` Traceback (most recent call last): File "kitti_dataloader.py", line 163, in bev_utils.drawRotatedBox(img_bev, x, y, w, l, yaw, cnf.colors[int(c)]) File "/home/user/Complex-YOLOv4-Pytorch/src/data_process/../data_process/kitti_bev_utils.py", line 171,...
When I run `python tf_gen_12net_hard_example.py`, mtcnn dependency you don't mention in readme is missing. I tried my luck with "pip install mtcnn" and it works, but then I will get:...
### Add Link https://pytorch.org/tutorials/intermediate/realtime_rpi.html ### Describe the bug I am getting 25-30fps on my rpi4 with provided snippet. However, after finetuning mobilenet_v2 and applying: ``` # Quantize the model quantized_model...
Hey, I am trying to download weights for TransFusion model L, but the links are dead: https://github.com/XuyangBai/TransFusion/blob/master/docs/model_zoo.md I.e. https://github.com/XuyangBai/TransFusion/blob/master/configs/configs/transfusion_nusc_pillar_L.py https://github.com/XuyangBai/TransFusion/blob/master/configs/configs/transfusion_nusc_voxel_L.py result in 404 error
https://huggingface.co/datasets/OpenAssistant/oasst1 has a lot of columns (most important: "parent_id" and "role" - assistant or prompter). However you only seem to use "text" column, input stays empty (L624, https://github.com/artidoro/qlora/blob/main/qlora.py#L624 ) ```...
Hey! I've been trying square resolutions divisible by 64x64 (divisibility by 32 was not always enough for error-free conversion). I'm doing this **both for maskrcnn with coco weights, as well...