bfortuner / pytorch_tiramisu

FC-DenseNet in PyTorch for Semantic Segmentation
MIT License
306 stars 66 forks source link

Is there any details for how to train a model? #3

Closed csjfwang closed 6 years ago

csjfwang commented 7 years ago

hi @bfortuner , Is there any details for how to train a model? I tried but there is following error ,

python train_densenet_pytorch.py
Traceback (most recent call last):
  File "train_densenet_pytorch.py", line 25, in <module>
    import utils.training as train_utils
  File "/pytorch_tiramisu-master/utils/training.py", line 47, in <module>
    def train(epoch, net, trainLoader, optimizer, trainF, sessionName=get_rand_str(5)):
  File "/pytorch_tiramisu-master/utils/training.py", line 21, in get_rand_str
    return ''.join(random.choices(string.ascii_uppercase + string.digits, k=n))
AttributeError: 'module' object has no attribute 'choices'

Hope for your help. Thanks a ton!

raghavab1992 commented 7 years ago

hi @wlwsea please checkout the other open issues! this issue has already been created.

csjfwang commented 7 years ago

hi @raghavab1992 , Thanks a lot! It really works. I want to train and test this network on camvid dataset, but i don't know how to use it. So , can you give me some advice or some details about my target?

Thx again!

raghavab1992 commented 7 years ago

@wlwsea im not really sure wht u mean by 'how to use it' but im gonna take a shot at it anyway. Please try to run the tiramisu-pytorch.ipynb notebook. Need to download camvid dataset and place it in the data folder(please look at the various folders present in github implementation and try to get an intuitive understanding of wht each folder might be for). It should be pretty straight forward from there.

csjfwang commented 7 years ago

@raghavab1992
OK, i will try it. Thanks a lot !

bfortuner commented 6 years ago

Updated the train.ipynb file with simpler interface. Hopefully that helps.