robot-grasp-detection icon indicating copy to clipboard operation
robot-grasp-detection copied to clipboard
verified publisher icon tnikolla

About Regression + Classification and Pretraining

Open HEUzhouhanwen opened this issue 7 years ago • 3 comments

Hi！ In paper 'Real-Time Grasp Detection Using Convolutional Neural Networks'
part IV. GRASP DETECTION WITH NEURAL NETWORKS C. Regression + Classification D. MultiGrasp Detection Do you have a program? part V. EXPERIMENTS AND EVALUATION C. Pretraining Is models/imagenet/m2/m2.ckpt the weight of pre-training results saved？ or models/imagenet/m4/m4.ckpt Thank you！ Shu Guo！

HEUzhouhanwen avatar Jan 06 '18 15:01 HEUzhouhanwen

The loss is stable at 30000-40000，I think it is related to Pretraining！

HEUzhouhanwen avatar Jan 07 '18 09:01 HEUzhouhanwen

I don't have a program for Reg+Class or MultiGrasp. Fill free to contribute.

models/imagenet/... are the saved parameters for imagenet. models/grasp/... are the saved parameters for grasping dataset.

tnikolla avatar Jan 13 '18 13:01 tnikolla

ValueError: Tensor conversion requested dtype int32 for Tensor with dtype float64: 'Tensor("truediv:0", shape=(), dtype=float64, device=/device:CPU:0)' May I ask how to solve this problem? Thanks, I've been working on it for a long time!

zhoumo1121 avatar Jul 02 '21 04:07 zhoumo1121