ValueError: '['train']' split is not provided by this dataset. Available splits are (u'test', u'train').

[tongmuyuan]

Hi, I just setup the environment, and got a issue in my first running. Could you please show me how to solve this problem, many thanks!!!

$ python run.py train --encoder-layers 1000-500-250-250-250-10 --decoder-spec gauss --denoising-cost-x 2000,20,0.1,0.1,0.1,0.1,0.1 --labeled-samples 50 --unlabeled-samples 60000 --seed 1 -- mnist_50_full

INFO:main:Logging into results/mnist_50_full6/log.txt INFO:main:== COMMAND LINE == INFO:main:run.py train --encoder-layers 1000-500-250-250-250-10 --decoder-spec gauss --denoising-cost-x 2000,20,0.1,0.1,0.1,0.1,0.1 --labeled-samples 50 --unlabeled-samples 60000 --seed 1 -- mnist_50_full INFO:main:== PARAMETERS == INFO:main: zestbn : bugfix
INFO:main: dseed : 1
INFO:main: top_c : 1
INFO:main: super_noise_std : 0.3
INFO:main: batch_size : 100
INFO:main: dataset : mnist
INFO:main: valid_set_size : 10000
INFO:main: num_epochs : 150
INFO:main: whiten_zca : 0
INFO:main: unlabeled_samples : 60000
INFO:main: decoder_spec : ('gauss',)
INFO:main: valid_batch_size : 100
INFO:main: denoising_cost_x : (2000.0, 20.0, 0.1, 0.1, 0.1, 0.1, 0.1) INFO:main: f_local_noise_std : 0.3
INFO:main: cmd : train
INFO:main: act : relu
INFO:main: lrate_decay : 0.67
INFO:main: seed : 1
INFO:main: lr : 0.002
INFO:main: save_to : mnist_50_full
INFO:main: save_dir : results/mnist_50_full6 INFO:main: commit : 5a8daa1760535ec4aa25c20c531e1cc31c76d911 INFO:main: contrast_norm : 0
INFO:main: encoder_layers : ('1000', '500', '250', '250', '250', '10') INFO:main: labeled_samples : 50
Traceback (most recent call last): File "run.py", line 656, in if train(d) is None: File "run.py", line 410, in train in_dim, data, whiten, cnorm = setup_data(p, test_set=False) File "run.py", line 245, in setup_data train_set = dataset_class(["train"]) File "/usr/local/lib/python2.7/dist-packages/fuel/datasets/mnist.py", line 36, in init super(MNIST, self).init(self.data_path, which_set, kwargs) File "/usr/local/lib/python2.7/dist-packages/fuel/datasets/hdf5.py", line 146, in init** "{}.".format(self.available_splits)) ValueError: '['train']' split is not provided by this dataset. Available splits are (u'test', u'train').

[hotloo]

Thanks for the interest in our work! Could you post your python dependency here? We are using Fuel 0.2 and it could be that the version did not match. Cheers!

[tongmuyuan]

@hotloo thanks for reply, I just solve this problem by: replace " train_set = dataset_class("[train]") " in run.py to "train_set = dataset_class("train")"

but I still got another question: when I finished install anaconda, and type: "julian@PremilabServer02:~/myproject/ladder$ conda env create -f environment.yml " to command window, it shows that: "conda: command not found" what should I do? really thanks appreciate for your help, many thanks!!

[hotloo]

@tongmuyuan OK. The best place to check the latest installation of Anaconda is at https://www.continuum.io/downloads

However, it looks like that your conda is not added the $PATH. A simple search on Google gave me this. Could you try this out?

http://stackoverflow.com/questions/35246386/conda-command-not-found

[tongmuyuan]

@hotloo Thank you very much, it helps me to added conda to $PATH. funny things is that, the iron-wall in my country blocked the second webside you gave to me, and I had to use a VPN for connection. anyway, you solved my question, thank you.

[hotloo]

Good that we did solve the immediate issue. I will close this one now.