yang1332133

Results 15 comments of yang1332133

> Can you give me your contact information? We can discuss it.

> Can you give me your contact information? We can discuss it.

> > 我做了几乎相同的事情,我和你有同样的问题。代码似乎存在一些问题。 > > 我使用了[Wu的代码](https://github.com/ShunChengWu/3DSSG)并成功地复制了该模型。我用这项工作之一替换了吴的GCN,模型工作得很好。所以至少GCN部分是正确的。 Hello, how did you reproduce the model using wu's code?

> 你好,我下载了预训练模型,并用其中的config_CVPR21.json作为配置文件,修改其中的"MODEL": "SGPN";"label_file": "labels.instances.align.annotated.v2.ply";"dataset_type": "SGPN"但是会报错,请问你具体是如何修改的呢?

> > 你好,我下载了预训练模型,并用其中的config_CVPR21.json作为配置文件,修改其中的"MODEL": "SGPN";"label_file": "labels.instances.align.annotated.v2.ply";"dataset_type": "SGPN"但是会报错,请问你具体是如何修改的呢? > > Use SGFN and modify the network/config. I got problems on SGPN too. 我使用了SGFN,但是将"label_file"修改为"labels.instances.align.annotated.v2.ply"还是会报错

> > > > 你好,我下载了预训练模型,并用其中的config_CVPR21.json作为配置文件,修改其中的"MODEL": "SGPN";"label_file": "labels.instances.align.annotated.v2.ply";"dataset_type": "SGPN"但是会报错,请问你具体是如何修改的呢? > > > > > > > > > Use SGFN and modify the network/config. I got problems on SGPN too. >...

> 你好!但我使用"label_file":"inseg.ply"代码运行没有错误,请问你运行的结果是基于"inseg.ply"还是"labels.instances.align.annotated.v2.ply"呢?

> > > > > > > > > 你好!但我使用"label_file":"inseg.ply"代码运行没有错误,请问你运行的结果是基于"inseg.ply"还是"labels.instances.align.annotated.v2.ply"呢? > > Based on `labels.instances.align.annotated.v2.ply`. 我在data_processing阶段运行gen_data_gt.py ----type train/gen_data_gt.py ----type test/gen_data_gt.py/----type validation分别生成relationships_train.json/relationships_test.json/relationships_validation.json,然后在config_CVPR21.json将"label_file": "labels.instances.align.annotated.v2.ply","GCN_TYPE": "TRIP",请问这样的操作是正确的吗?

> > > > > > > > > > > > > > > > > 你好!但我使用"label_file":"inseg.ply"代码运行没有错误,请问你运行的结果是基于"inseg.ply"还是"labels.instances.align.annotated.v2.ply"呢? > > > > > > > > > Based on `labels.instances.align.annotated.v2.ply`....

> Difference from the paper: Learning rate: The default value is 0.0001, while this code uses 0.001 (the learning rate is quite sensitive in this task, and it has been...