EfficientPose

EfficientPose copied to clipboard

Object detection is working well, but rotation error is very high

9

Hello, I'm having an issue with training on my custom dataset. It seems that the network is finding the images just fine, and this is reflected in the translation errors....

Jorisdehoog

Can't improve rotation error when training with my custom data

4

I'm having a problem with training on my custom dataset. I use the weight pretrained file efficientdet-d2.h5 It seems that the translation error has been improved very well. However, the...

CongDuy038

NAN loss using your conda env and data and command after 500 epochs

11

I am getting NAN loss, using your own processed data, conda env, and command. Is there a fix to it? ``` (EfficientPose) mona@mona-ThinkStation-P7:~/EfficientPose$ python train.py --phi 0 --weights weights/Weights/Linemod/object_8/phi_0_linemod_best_ADD.h5 linemod...

monajalal

Data projecion problem

3

Dear @ybkscht , I've generated some data in unity with the flip Y to make it equal to openCV. However, my rotations and translation when projected into the image does...

DavidJimenezS

Model not getting trained

1

Hi, Thanks for this wonderful repo. While training the model with this command 'python3 train.py --phi 0 --weights /home/priyalakshmip/pose_est_efficientpose/EfficientPose/COCO/efficientdet-d0.h5 linemod /home/priyalakshmip/pose_est_efficientpose/Linemod_preprocessed/ --object-id 4' I am receiving nan in loss and...

IAM-P-LP

Occlusion with multiple objects of the same type?

11

I currently have linemod working well detecting one of my custom objects. Thank you! I now would like to extend this to support multiple objects of the same type using...

pgaston1

Model not learning on custom data

5

Hello, Thanks for providing the implementation to your work. Motivated by your results, I started training on my custom collected dataset and also visualized the dataset using 'debug.py' script provided...

alishan2040

Hey, can you please provide a way and the python scripts that will be used in training the model on a custom dataset?

IAMHAADICOOL

ValueError: numpy.ndarray size changed, may indicate binary incompatibility. Expected 88 from C header, got 80 from PyObject

1

Hi, thank you your model I have followed all the steps accordingly as you mentioned in the readme file while inferencing that  the system is throwing the above-mentioned error....

Aryanjb

I have an x64 M1 Mac. Conda does not support python 3.7 so i had to use 3.9. While trying to run install -r requirements.txt, i run into the following...

JoshvirNarula