The training model download link is invalid。

maudzung / YOLO3D-YOLOv4-PyTorch

YOLO3D: End-to-end real-time 3D Oriented Object Bounding Box Detection from LiDAR Point Cloud (ECCV 2018)

https://arxiv.org/pdf/1808.02350v1.pdf

GNU General Public License v3.0

289 stars 44 forks source link

The training model download link is invalid。 #1

Open tianyuluan opened 3 years ago

tianyuluan commented 3 years ago

The training model download link is invalid，Could you please upload it again，thank for your great works!!!

zhanghanbin3159 commented 3 years ago

The training model download link is invalid，Could you please upload it again，thank for your great works!!!

https://drive.google.com/drive/folders/1RHD9PBvk-9SjbKwoi_Q1kl9-UGFo2Pth

streamB commented 3 years ago

It seems that the trained model provided by @zhanghanbin3159 mismatches the config file ''yolo3d_yolov4.cfg". The differences are the number of convolutional kernels (36 in ''yolo3d_yolov4.cfg" but 30 in "complex_yolov4_mse_loss.pth") before each [yolo] layer. Could you please provide the corresponding config file? Thanks a lot!!!