ruishu / dirt-t Goto Github PK

Hello,
The paper refers to a test using Wifi data. I assume that this Wifi data appears like a 1 dimensional feature vector and I want to ask if there is some runtime flags that one can raise in order for the code to accept image features rather than full images as train/test data?

Thanks
Mattias

Hi,
I got a vanilla copy of the master branch and downloaded the data using the 2 scripts in the repo.
Then I ran VADA, but got an error while executing DIRT-T following that.

The logs says the following. What do they tell me?

Model name: model=dirtt_src=mnist_trg=svhn_nn=small_trim=5_dw=1e-02_bw=1e-02_sw=1e+00_tw=1e-02_dirt=05000_run=0000
Traceback (most recent call last):
  File "run_dirtt.py", line 77, in <module>
    saver.restore(M.sess, path)
  File "/dccstor/mattiasm_dl/Anaconda3_x86_64/envs/mattiasm-dev-p2/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1796, in restore
    raise ValueError("Can't load save_path when it is None.")

The folder 'checkpoints' only contain one folder 'model=dirtt_src=mnist_trg=svhn_nn=small_trim=5_dw=1e-02_bw=0e+00_sw=1e+00_tw=1e-02_dirt=00000_run=0000' and its empty. My guess is that VADA failed to complete. Am I right?

Hi,

Is there a Pytorch implementation of the Dirt-t framework?

Thanks.

Thanks for making the code publically available.

I have trained the model and now I want to use the saved model to make predictions on some hand-picked test examples. I have restored the saved model but not sure which tensor operation to evaluate in order to get predictions?

Can you please help me with that?