Kaiwen Duan

i also met the same issue. Have you fixed it? @714586886 @duoyun1314 @gmayday1997 @xzy295461445 @Leerw

@Leerw Thank you very much!

Hi sulth, I met the same warning, for me, It’s because (1). the number of samples for “truck” and ”bus” are too few compared with “car” (2). There are many...

I met the same issue,how did you solved? Thanks very much!

@Nishith365 https://github.com/souryuu/FastMaskRCNN

Hello，HuangBo @HuangBo-Terraloupe ，I also have this problem，and I have changed the path in dataset_factory.py and in config_v1.py, but it still has same bugs. please help!

@HuangBo-Terraloupe ,sorry,the bug on my computer is RandomShuffleQueue '_2_random_shuffle_queue' is closed and has insufficient elements (requested 1, current size 0), but not "_1_random_shuffle_queue". I don't know what's the difference.Help please!

Thanks a lot! @HuangBo-Terraloupe The problem has been solved with your help! I made a mistake, I turned the relative path of tfrecords into an absolute path in both dataset_factory.py...

@lnuchiyo Don't change anything in the dataset_factory.py. Change the path in config_v1.py only. config_v1.py: tf.app.flags.DEFINE_string( 'train_dir', '/home/kwduan/FastMaskRCNN-master3/output/mask_rcnn/', 'Directory where checkpoints and event logs are written to.') ###################################################################### tf.app.flags.DEFINE_string( 'pretrained_model', '/ssd/kwduan/data/pretrained_models/resnet_v1_50.ckpt',...

I will suggest you uninstall tensorflow-cpu and install the tensorflow-gpu(1.0 or 1.1) only. Because by default, this code is run with gpu. If this does not work, I will suggest...