tianwei-yu
commented
2 years ago Dear ks2002ml,
I think it is a data format issue, as it is showing size 0. If you want, you can send me your data to take a look.
Best, Tianwei
Get Outlook for Androidhttps://aka.ms/AAb9ysg
From: ks2022ml @.> Sent: Friday, March 4, 2022 1:28:26 PM To: tianwei-yu/AIME @.> Cc: Subscribed @.***> Subject: [tianwei-yu/AIME] error in running AIME (Issue #1)
Hi Prof Yu
I was trying to run AIME using my own dataset but it seems to be running into some errors:
- if confounder matrix is provided but no out.layers, there is a bug in the decoder.layer.sizes as it produces numeric(0) instead.
- when it seems to be running, i run into this error:
any help would be greatly appreciated!
Thank you!
`> b <- aime(data.in=X, data.out=Y, confounder=C, in.layers=3, out.layers=3, max.dropout=0.25, max.epochs=100, importance.permutations=5, ncomp=3) Model: "model"
Layer (type) Output Shape Param # Connected to
input_1 (InputLayer) [(None, 1000)] 0
dropout_2 (Dropout) (None, 1000) 0 input_1[0][0]
dense_2 (Dense) (None, 234) 234234 dropout_2[0][0]
dropout_1 (Dropout) (None, 234) 0 dense_2[0][0]
dense_1 (Dense) (None, 55) 12925 dropout_1[0][0]
dropout (Dropout) (None, 55) 0 dense_1[0][0]
dense (Dense) (None, 13) 728 dropout[0][0]
dropout_3 (Dropout) (None, 13) 0 dense[0][0]
dense_3 (Dense) (None, 3) 42 dropout_3[0][0]
aux_input (InputLayer) [(None, 10)] 0
concatenate (Concatenate) (None, 13) 0 dense_3[0][0] aux_input[0][0]
dropout_7 (Dropout) (None, 13) 0 concatenate[0][0]
dense_7 (Dense) (None, 4) 56 dropout_7[0][0]
dropout_6 (Dropout) (None, 4) 0 dense_7[0][0]
dense_6 (Dense) (None, 5) 25 dropout_6[0][0]
dropout_5 (Dropout) (None, 5) 0 dense_6[0][0]
dense_5 (Dense) (None, 6) 36 dropout_5[0][0]
dropout_4 (Dropout) (None, 6) 0 dense_5[0][0]
dense_4 (Dense) (None, 7) 49 dropout_4[0][0]
Total params: 248,095 Trainable params: 248,095 Non-trainable params: 0
Error in py_call_impl(callable, dots$args, dots$keywords) : ValueError: in user code:
/home/ks/anaconda3/envs/r-reticulate/lib/python3.9/site-packages/tensorflow/python/keras/engine/training.py:855 train_function * return step_function(self, iterator) /home/ks/anaconda3/envs/r-reticulate/lib/python3.9/site-packages/tensorflow/python/keras/engine/training.py:845 step_function ** outputs = model.distribute_strategy.run(run_step, args=(data,)) /home/ks/anaconda3/envs/r-reticulate/lib/python3.9/site-packages/tensorflow/python/distribute/distribute_lib.py:1285 run return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs) /home/ks/anaconda3/envs/r-reticulate/lib/python3.9/site-packages/tensorflow/python/distribute/distribute_lib.py:2833 call_for_each_replica return self._call_for_each_replica(fn, args, kwargs) /home/ks/anaconda3/envs/r-reticulate/lib/python3.9/site-packages/tensorflow/python/distribute/distribute_lib.py:3608 _call_for_each_replica retur`
— Reply to this email directly, view it on GitHubhttps://nam12.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Ftianwei-yu%2FAIME%2Fissues%2F1&data=04%7C01%7C%7C56906102d2fc46e517e508d9fd9fcf65%7C84df9e7fe9f640afb435aaaaaaaaaaaa%7C1%7C0%7C637819685091855519%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=EKaJ7c0D%2FB8tBRGHoMxKFWohz%2Flm5QzjcxTpp3Y%2BSrc%3D&reserved=0, or unsubscribehttps://nam12.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Fnotifications%2Funsubscribe-auth%2FAPXE4FZ2WTYAXDGBE6YIFPLU6GNPVANCNFSM5P4SD4ZA&data=04%7C01%7C%7C56906102d2fc46e517e508d9fd9fcf65%7C84df9e7fe9f640afb435aaaaaaaaaaaa%7C1%7C0%7C637819685091855519%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=ee6wYFG1yV84z8rw7KNDDJbw%2F%2Fom6B0O45wrGhOsYYs%3D&reserved=0. Triage notifications on the go with GitHub Mobile for iOShttps://nam12.safelinks.protection.outlook.com/?url=https%3A%2F%2Fapps.apple.com%2Fapp%2Fapple-store%2Fid1477376905%3Fct%3Dnotification-email%26mt%3D8%26pt%3D524675&data=04%7C01%7C%7C56906102d2fc46e517e508d9fd9fcf65%7C84df9e7fe9f640afb435aaaaaaaaaaaa%7C1%7C0%7C637819685091855519%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=zJrdJNKtPKe42cMZIehmG0WdiDI%2F6P2%2BJYwEmhtVv4I%3D&reserved=0 or Androidhttps://nam12.safelinks.protection.outlook.com/?url=https%3A%2F%2Fplay.google.com%2Fstore%2Fapps%2Fdetails%3Fid%3Dcom.github.android%26referrer%3Dutm_campaign%253Dnotification-email%2526utm_medium%253Demail%2526utm_source%253Dgithub&data=04%7C01%7C%7C56906102d2fc46e517e508d9fd9fcf65%7C84df9e7fe9f640afb435aaaaaaaaaaaa%7C1%7C0%7C637819685091855519%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=m3vUVV4%2BGbehHdIi0277hB9VX%2BcGK%2BUdNyCyhOqJJtU%3D&reserved=0. You are receiving this because you are subscribed to this thread.Message ID: @.***>
ks2022ml
Hi Prof Yu
I was trying to run AIME using my own dataset but it seems to be running into some errors:
any help would be greatly appreciated!
Thank you!
`> b <- aime(data.in=X, data.out=Y, confounder=C, in.layers=3, out.layers=3, max.dropout=0.25, max.epochs=100, importance.permutations=5, ncomp=3) Model: "model"
Layer (type) Output Shape Param # Connected to
input_1 (InputLayer) [(None, 1000)] 0
dropout_2 (Dropout) (None, 1000) 0 input_1[0][0]
dense_2 (Dense) (None, 234) 234234 dropout_2[0][0]
dropout_1 (Dropout) (None, 234) 0 dense_2[0][0]
dense_1 (Dense) (None, 55) 12925 dropout_1[0][0]
dropout (Dropout) (None, 55) 0 dense_1[0][0]
dense (Dense) (None, 13) 728 dropout[0][0]
dropout_3 (Dropout) (None, 13) 0 dense[0][0]
dense_3 (Dense) (None, 3) 42 dropout_3[0][0]
aux_input (InputLayer) [(None, 10)] 0
concatenate (Concatenate) (None, 13) 0 dense_3[0][0]
aux_input[0][0]
dropout_7 (Dropout) (None, 13) 0 concatenate[0][0]
dense_7 (Dense) (None, 4) 56 dropout_7[0][0]
dropout_6 (Dropout) (None, 4) 0 dense_7[0][0]
dense_6 (Dense) (None, 5) 25 dropout_6[0][0]
dropout_5 (Dropout) (None, 5) 0 dense_6[0][0]
dense_5 (Dense) (None, 6) 36 dropout_5[0][0]
dropout_4 (Dropout) (None, 6) 0 dense_5[0][0]
dense_4 (Dense) (None, 7) 49 dropout_4[0][0]
Total params: 248,095 Trainable params: 248,095 Non-trainable params: 0
Error in py_call_impl(callable, dots$args, dots$keywords) : ValueError: in user code: