train from checpoints

[QueenJuliaZxx]

Hi,I want to train after 160000 iters,how should I use the order?thank you very much!
Mine:
python ./faster_rcnn/train_net.py
--gpu 1
--weights ./output/faster_rcnn_end2end_pva_kitti1/kittivoc_train/PVAnet_iter_160000.ckpt
--imdb kittivoc_train
--iters 160000
--cfg ./experiments/cfgs/faster_rcnn_end2end_pva_kitti1.yml
--network PVAnet_train
--restore 0
but it cause error:
Loading pretrained model weights from ./output/faster_rcnn_end2end_pva_kitti1/kittivoc_train/PVAnet_iter_160000.ckpt
Traceback (most recent call last):
File "./faster_rcnn/train_net.py", line 118, in
restore=bool(int(args.restore))) #1
File "./faster_rcnn/../lib/fast_rcnn/train.py", line 405, in train_net
sw.train_model(sess, max_iters, restore=restore) #restore=true
File "./faster_rcnn/../lib/fast_rcnn/train.py", line 163, in train_model
raise 'Check your pretrained model {:s}'.format(self.pretrained_model)
TypeError: exceptions must be old-style classes or derived from BaseException, not str

[HaoWangDL]

@QueenJuliaZxx Hello ,

I also met this problem. How do you solve it

[chiyandetaotie]

@QueenJuliaZxx @HaoWangDL
Hello,
I have a problem,could you help me?
I interrupted a training (and saved the fixed step model). After two days, I want to continue training in the place where I last interrupted. How to do it?I am a newbie, I hope to answer with the most specific examples, instead of applying the official function.Thanks.

[pale1018]

I have the same problem,could you tell me how to fix it? thanks!!@HaoWangDL @chiyandetaotie @CharlesShang @QueenJuliaZxx