gistfile1.txt

(fair_env) matthijs@devfair0144:~/src/low-shot-with-diffusion$ python logreg.py      --mode test --nlabeled 2 --seed 1      --maxiter 29500      --lr 0.001 --wd 0.01 --batchsize 128
nb of eval classes 311
/public/apps/anaconda2/5.0.1/envs/fair_env/lib/python2.7/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
  from ._conv import register_converters as _register_converters
open  /checkpoint/matthijs/low-shot/features/val.hdf5
read  /checkpoint/matthijs/low-shot/features/val_features.npy
   features loaded in 2.880 s
nb of eval classes 311
open  /checkpoint/matthijs/low-shot/features/train.hdf5
read  /checkpoint/matthijs/low-shot/features/train_features.npy
   features loaded in 68.417 s
selecting images, seed=1
dataset sizes: Xtr (250860, 2048) (250860 labeled), Xte (25350, 2048), 507 classes (eval on 25350 examples, 507 classes, 311 novel classes)
============== start logreg
logreg.py:107: UserWarning: Implicit dimension choice for log_softmax has been deprecated. Change the call to include dim=X as an argument.
  return F.log_softmax(self.l1(x))
0.025084982872
6.20095642092
6.06771154991
5.92883865873
5.79343245874
5.66283695742
5.5329569634
5.40713169171
5.28074271397
5.16166630091
5.03845827656
4.92353282533
4.80592244407
4.6860298699
4.5779072198
4.46372476223
4.3541482833
4.25072629431
4.1439837419
4.04272760276
3.94442317322
3.85027416224
3.75703827063
3.65755777724
3.56684669553
3.48459247511
3.3957052346
3.32090998366
3.23577628662
3.15135820504
3.08178561703
2.99940180194
2.93062312268
2.86213091482
2.79963234479
2.73306129462
2.6664646196
2.60899042426
2.55377942561
2.49447850049
2.43557271345
2.38170072621
2.32763882441
2.27615750877
2.23852747132
2.18326326763
2.14415860527
2.09311960936
2.05569484017
2.01933530192
1.98056203133
1.94637428153
1.90737477299
1.85906640226
1.83698344905
1.80718957187
1.76976152394
1.73807740991
1.71130809595
[92.456s] iteration 29500 top-5 accuracy: 0.700 (0.565 on novel)