Qiuxiaqing comments

Results 8 comments of


                                            Qiuxiaqing

Sorry But I don't know what exactly mean 'delete the checkpoint directory to train a new model'

I meet the same problem. How do you solve this problem？

NotFoundError (see above for traceback): Key discriminator/d_bn0/beta not found in checkpoint

Have you solved the problem? I have the same problem

Train my own data

I also want to know how to generate the new caffemodle with my own database. Have you solved this problem? if yes, would you like to give me some suggestion?...

Train my own data

yes thank you. you are right! now, I have do this ,but i want to know what's your mean_value in train.prototxt. (shicai's mean_value: [103.94, 116.78, 123.68]......then, must I compute my...

Train my own data

OK， That may not be what I want . Thank you all the same

train.py stopped in epoch[0],[49/63], when it training

I know the reason now. The option "--sample_steps" constrain the training numbers. In the process, I set the sample_steps=50, thus it stop in 49...But, i don't know what it actually...

IOError: [Errno 2] No such file or directory: 'dir/0_0000.jpg'

In the options, there are a '--sample_dir=dir'. That is mean, you must mkdir a directory, which named "dir".

error run create_data.sh , only generate the Soft connection，the size is 57 bytes , but did not genereate the actual lmdb

I have recently encountered the same problem. Have you solved it? If you solve this problem, can you share the method? Thank you