您好，请问我使用cuda11以上的版本可以训练吗，因为我只有A6000和A100的显卡，它们不兼容cuda11以下的版本。我用cuda11.1和torch1.8或者1.9训练时，都会报double free or corruption (!prev)、RuntimeError: DataLoader worker (pid(s) xxxxx) exited unexpectedly。

Hello! I find this work really interesting. After successfully testing inference (LMO and YCB) I was just interested in plotting the inference results as 3D bounding boxes on RGB images and by inspecting the code I bumped into:

https://github.com/THU-DA-6D-Pose-Group/GDR-Net/blob/5fb30c3dc53f46bac24a8a83a373eac7a8038556/core/gdrn_modeling/gdrn_evaluator.py#L516

it is the function used for inference, which seems to show the results in terms of the different metrics, but not showing graphical results as I am looking for

In the same file I noticed the function: https://github.com/THU-DA-6D-Pose-Group/GDR-Net/blob/5fb30c3dc53f46bac24a8a83a373eac7a8038556/core/gdrn_modeling/gdrn_evaluator.py#L634

which seems structurally similar but with some input differences, in particular I would like to ask if the input dataloader can be be computed for gdrn_inference_on_dataset as for save_result_of_dataset as in

https://github.com/THU-DA-6D-Pose-Group/GDR-Net/blob/5fb30c3dc53f46bac24a8a83a373eac7a8038556/core/gdrn_modeling/engine.py#L135-L137

Since from preliminar debugging it seems it is not possible to access to the "image" field of the input sample in

https://github.com/THU-DA-6D-Pose-Group/GDR-Net/blob/5fb30c3dc53f46bac24a8a83a373eac7a8038556/core/gdrn_modeling/gdrn_evaluator.py#L678

Possibly related issue: https://github.com/THU-DA-6D-Pose-Group/GDR-Net/issues/56

你好，论文里关于MXYZ到M2D-3D的转化是这样说的。"$M_{2D-3D}$ can then be derived by stacking $M_{XYZ}$onto the corresponding 2D pixel coordinates". 但是我还是不太清楚为什么从$3\times64\times64$维度的$M_{XYZ}$转变成了$2\times64\times64$维度的$M_{2D-3D}$。以及为什么要做这样一个转化呢，直接将预测的XYZ归一化之后和MSRA Concatenation不行吗？

王博，您好！ 您的工作对我的帮助很大，非常感谢您提供的开源项目。现在我想使用自己的数据在您的模型上训练，之前的一些issue里您只提到了应该如何处理和组织自己的数据，但并没有提及如果要使用自己的数据，应该修改哪些部分的代码。因为之前在lm数据集上训练时需要先生成一些文件，所以我猜测如果要将模型应用在自己的数据上，可能需要修改的地方有很多，可以请您具体讲讲吗？ 期待您的回复，再次致谢！

Hi! thanks for your great work. I execute the following command to get the evaluation results of LM-O as follows, ‘GDR-Net-DATA‘ is the folder where I put the trained models. ./core/gdrn_modeling/test_gdrn.sh configs/gdrn/lmo/a6_cPnP_AugAAETrunc_BG0.5_lmo_real_pbr0.1_40e.py 1 GDR-Net-DATA/gdrn/lmo/a6_cPnP_AugAAETrunc_BG0.5_lmo_real_pbr0.1_40e/gdrn_lmo_real_pbr.pth Is ‘ad_10’ the ‘Average Recall (%) of ADD(-S)’ mentioned in Table 2 in the paper?

Hello @wangg12

I tried to evaluate the GDR-Net model on LMO dataset using the pretrained models you shared on OneDrive. I used following command to run the valuation:

python core/gdrn_modeling/main_gdrn.py --config-file configs/gdrn/lmo/a6_cPnP_AugAAETrunc_BG0.5_lmo_real_pbr0.1_40e.py \
 --num-gpus 1 \
--eval-only  \
--opts MODEL.WEIGHTS=output/gdrn/lmo/a6_cPnP_AugAAETrunc_BG0.5_lmo_real_pbr0.1_40e/gdrn_lmo_real_pbr.pth

However, it is showing zero recall values. Please see the screenshot below. Could you please help?

Thank you, Supriya

Hi,

When I train GDR-Net on ape of LMO dataset by

./core/gdrn_modeling/train_gdrn.sh configs/gdrn/lmoSO/a6_cPnP_AugAAETrunc_BG0.5_lmo_real_pbr0.1_80e_SO/a6_cPnP_AugAAETrunc_BG0.5_lmo_real_pbr0.1_80e_ape.py 1

I get the unexpected output at the end of log.txt:

core.gdrn_modeling.test_utils [email protected]: evaluation failed.
core.gdrn_modeling.test_utils [email protected]: =====================================================================
core.gdrn_modeling.test_utils [email protected]: output/gdrn/lmoSO/a6_cPnP_AugAAETrunc_lmo_real_pbr0.1_80e_SO/ape/inference_model_final/lmo_test/a6-cPnP-AugAAETrunc-BG0.5-lmo-real-pbr0.1-80e-ape-test-iter0_lmo-test-bb8/error:ad_ntop:1 does not exist.

Could you suggest how to fix it? Thanks!

Hi, unfortunately the One-Drive link of pretrained model seems to provide the following error on different browsers, do you have any insight about this?

Thanks in advance,

Alberto

王博你好，我在使用tools/lm/lm_pbr_1_gen_xyz_crop.py生成xyz_crop文件的过程中遇到了这个问题。

Traceback (most recent call last): File "tools/lm/lmo_pbr_1_gen_xyz_crop.py", line 228, in xyz_gen.main() File "tools/lm/lmo_pbr_1_gen_xyz_crop.py", line 137, in main bgr_gl, depth_gl = self.get_renderer().render(render_obj_id, IM_W, IM_H, K, R, t, near, far) File "tools/lm/lmo_pbr_1_gen_xyz_crop.py", line 98, in get_renderer self.renderer = Renderer( File "/data/hsm/gdr/tools/lm/../../lib/meshrenderer/meshrenderer_phong.py", line 26, in init self._fbo = gu.Framebuffer( File "/data/hsm/gdr/tools/lm/../../lib/meshrenderer/gl_utils/fbo.py", line 22, in init glNamedFramebufferTexture(self.__id, k, attachement.id, 0) File "/data/hsm/env/gdrn2/lib/python3.8/site-packages/OpenGL/platform/baseplatform.py", line 415, in call return self( *args, **named ) ctypes.ArgumentError: argument 1: <class 'TypeError'>: wrong type

我认为可能是在 https://github.com/THU-DA-6D-Pose-Group/GDR-Net/blob/main/lib/meshrenderer/gl_utils/fbo.py#L19 中传入的k类型不匹配所以出错。图片为debug中显示的glNamedFramebufferTexture函数要求传入的数据类型。 在issue中没有找到与我类似的问题，请问有人有任何解决这个问题的相关建议吗？

We implement the training process with pbr rendered data on eight GPU parallel computing (NIVDIA 2080 Ti with graphic memory of 12 G) , it barely starts training in batchsize 8 (original is 24). But when we resume the training process, CUDA will be out of memory.

We'd like to know the author's training configuration...

Other Loss has significant decline， but Loss_region‘s drop is very weak. My training use config : configs/gdrn/lm/a6_cPnP_lm13.py Region area choose 4, 16, 64 can not make any improve.

Hello @wangg12,

Sorry to bother you again.

Could you please tell me how to generate faster_R50_FPN_AugCosyAAE_HalfAnchor_lmo_pbr_lmo_fuse_real_all_8e_test_480x640.json in lmo/test/test_bboxes folder?

Which code did you run to obtain this file?

Thank you, Supriya