You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@xiechunhong First, you have to convert your own dataset into tfrecord by utils/dataset_util.py. You can simply modify def make_***_tfrecord function in dataset_util.py to convert your dataset into tfrecord. And then, change model_dir, train_data, test_data in __init__.py and run. You can change other variables to train your network like batch_size, max_iter, etc.
@Tamuel By the way, can you explain the process of BDD100k lane vertices to lane mask? Or it's not dense lane mask while training ? I am confused of sparse lane segmentation.
Sparse lane segmentation is train only via the lane vertices during loss build?
tensorflow.python.framework.errors_impl.InvalidArgumentError: Unsuccessful TensorSliceReader constructor: Failed to get matching files on ./init_checkpoints/resnet_v2_50/resnet_v2_50.ckpt: Not found: FindFirstFile failed for: ./init_checkpoints/resnet_v2_50 : ϵͳ�Ҳ���ָ����·����
; No such process
Activity
Tamuel commentedon Apr 9, 2019
@xiechunhong First, you have to convert your own dataset into tfrecord by
utils/dataset_util.py. You can simply modifydef make_***_tfrecordfunction indataset_util.pyto convert your dataset into tfrecord. And then, changemodel_dir,train_data,test_datain__init__.pyand run. You can change other variables to train your network likebatch_size,max_iter, etc.xiechunhong commentedon Apr 13, 2019
@Tamuel Thank you for your reply, Tamuel! Your work is great!
nieyan commentedon Jun 18, 2019
@Tamuel Great work! And can you tell me what dataset do you use to train? And the lane in demo has been postprocess or the raw model output?
Tamuel commentedon Jun 18, 2019
@nieyan Thank you for your comment. In demo, I just overlapped raw model output on original image. There are no other postprocessing conducted. And I pretrain network by BDD100k dataset (https://bair.berkeley.edu/blog/2018/05/30/bdd/) which have information of lane by vertices. So, I make sparse lane segmentation dataset from those vertices by OpenCV and pretrain with it. And then, fine-tune network by KAIST dataset (https://sites.google.com/site/highwaydrivingdataset/) which finely labeled. If you want to increase performance of network more than this, you can use other huge dataset like Mapillary dataset (https://www.mapillary.com/dataset/vistas?pKey=H1P0sKnFsYu1MkfcjGUZTg).
nieyan commentedon Jun 19, 2019
@Tamuel Many thanks for the prompt reply!
nieyan commentedon Jun 19, 2019
@Tamuel By the way, can you explain the process of BDD100k lane vertices to lane mask? Or it's not dense lane mask while training ? I am confused of sparse lane segmentation.
Sparse lane segmentation is train only via the lane vertices during loss build?
uzair-mehmood commentedon Nov 22, 2019
@Tamuel, did you apply augmentations, other than those applied in init?
xuxiuzhi2627 commentedon Nov 25, 2019
Hi，Have you implemented this code yet?
xiechunhong commentedon Dec 26, 2019
@xxzcpsmemeda Just follow Tamuel's comments, the training can be done.
fsxy1063200037 commentedon May 28, 2020
Hi！I get this problem, how did you solve it
tensorflow.python.framework.errors_impl.InvalidArgumentError: Unsuccessful TensorSliceReader constructor: Failed to get matching files on ./init_checkpoints/resnet_v2_50/resnet_v2_50.ckpt: Not found: FindFirstFile failed for: ./init_checkpoints/resnet_v2_50 : ϵͳ�Ҳ���ָ����·����
; No such process