XiaoDa comments

Results 7 comments of


                                            XiaoDa

Part segmentation for custom dataset

@thangvubk, I saw your config_explanation.md file. Thanks for your explanation. But I have some questions about setting configs. **Q1: If I only have 10 semantic classes and there is no...

result in ucf101

I also trained the model on ucf101 dataset. At first, I used the default hyperparameters which the author gave. Then I got the 73.50% of top 1 accuracy. Afterwards, I...

result in ucf101

@patykov Maybe there was no standard answer for hyperparameters. I often found the better hyperparameters by trial and error. On UCF101 dataset, I used learning rate=0.001, weight decay = 0.0005,...

Data Preprocessing

I have solved this problem. Afterwards, I found that I could use os.rename to change ".txt" format to ".pts" format. In addition, when I started to train a model, I...

Stack at Sampling phase.

+1 I also have the same problem.

There are some bugs

@zouwenqin I also found these bugs. Afterwards, I tried to fix these bugs by myself and I could run PVT for training, but I could not reproduce the results in...

Code for Part Segmentation (Tab. 3)

Hi @blacktime14, I also look forward to this code for part segmentation.