BeyondVE

Results 8 comments of BeyondVE

Excuse me, how is your AP performance

> ![image](https://private-user-images.githubusercontent.com/32351961/317266948-4c95c9a7-b764-4aa6-b722-2ae730b56665.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.oEWnC3KACeuNuNDRwRHE9C7lnsWXPsSlTwwOtJyzzhQ) This is my replicate results, the problem is same with u. We also look forward a reasonable explain. Excuse me, is this the model of the original paper,...

> > @Vipermdl @BeyondVE I used the pre-trained weights he published. According to my understanding, the results in KITTI test set are obtained by model training in the whole trainval...

> > It seems to me that what the author released is a pre-trained weight that is only trained on the training set. The performance of their published weights on...

> > > > It seems to me that what the author released is a pre-trained weight that is only trained on the training set. The performance of their published...

> > > > > > It seems to me that what the author released is a pre-trained weight that is only trained on the training set. The performance of...

> 我跑出来只有这个指标。 Car (3D Detection) | 19.51 % | 12.70 % | 10.75 % Car (Bird's Eye View) | 29.81 % | 19.31 % | 15.98 % 我跑出来的测试集是这样 没达到论文指标 Car...

same question.