Dr Yifan Liu comments

Results 24 comments of


                                            Dr Yifan Liu

Hi~Have you used the moblie net which is pretrained on the ImageNet?

So you mean you just train from the scratch, and get the IoU of 70?

Hi~Have you used the moblie net which is pretrained on the ImageNet?

I loaded in your ImageNet pre-trained weight, but most of the weights are zeros or ones. It seemed the parameters had not been trained.

Batch inference?

AND! When will the model stop? What is the meaning of "coord.should_stop"? Are there any parts we can use to test? Hoping for your reply, thanks!

Batch inference?

Thanks a lot~ But it will be helpful if we have a test part~

Batch inference?

The datasets are divided into train set and test set. Do you use the test set? I guess the test set is design to test the effects of the model....

Batch inference?

Yes, I think an automatic script may be more effective to show the results. 在 2017-05-16 16:50:22，"Van Huy" 写道： Yes, I used the test set for that purpose too. The...

FileNotFoundError

Please read the README carefully. You also need to download the pretrain weight for vgg through following links: https://github.com/machrisaa/tensorflow-vgg

Pretrained model is not available

I have uploaded the link: https://cloudstor.aarnet.edu.au/plus/s/LvyREKsiaH47Aa6

The pre-trained model can't be loaded

The model I provided is a frozen one, which can only be used for demo evaluation. Sorry for the inconvenient. This project is opened two years ago, and it is...

More diversity in the dataset

Thank you for your advice~ If anyone is interested, he or she can use the training code I provided.