Skip to content
This repository has been archived by the owner on Jun 20, 2020. It is now read-only.

Training error #22

Open
balintzkacsoh opened this issue Aug 6, 2019 · 0 comments
Open

Training error #22

balintzkacsoh opened this issue Aug 6, 2019 · 0 comments

Comments

@balintzkacsoh
Copy link

Hi Talmo,

We are having trouble initializing the training. See error below:

I = h5readframes('tyson.h5','/box',1);
Found 11/250 labeled frames.
Loaded 11 images [0.01s]
Generated confidence maps [0.07s]
9.281 MB
Symmetric channels:
earL (5) <-> earR (6)
Saved:
/private/var/folders/sq/qflygrvs7bxfmh698b3mntzx6yxtgs/T/tp71e705c4_a342_467a_ad6b_2d4725ad3290.h5 [0.17s]
tp71e705c4_a342_467a_ad6b_2d4725ad3290.h5: 21.7 MB
Finished generating training set. [0.36s]
session timestamp message
_______ ____________________ ________________________

   1       06-Aug-2019 17:05:34    "Fast training (n = 11)"

python "/Users/kacsoh/Desktop/LEAP/leap/leap/training.py" "/private/var/folders/sq/qflygrvs7bxfmh698b3mntzx6yxtgs/T/tp71e705c4_a342_467a_ad6b_2d4725ad3290.h5" --base-output-path="/Users/kacsoh/Desktop/LEAP/models" --run-name="190806_170523-n=11" --net-name="leap_cnn" --filters=32 --rotate-angle=5 --val-size=0.10000 --epochs=15 --batch-size=50 --batches-per-epoch=50 --val-batches-per-epoch=10 --reduce-lr-factor=0.1000000000 --reduce-lr-patience=2 --reduce-lr-cooldown=0 --reduce-lr-min-delta=0.0000100000 --reduce-lr-min-lr=0.0000000001 --upsampling-layers --amsgrad
Traceback (most recent call last):
File "/Users/kacsoh/Desktop/LEAP/leap/leap/training.py", line 10, in
import keras
ModuleNotFoundError: No module named 'keras'
Found 11/250 labeled frames.
Loaded 11 images [0.01s]
Generated confidence maps [0.07s]
9.281 MB
Symmetric channels:
earL (5) <-> earR (6)
Saved:
/private/var/folders/sq/qflygrvs7bxfmh698b3mntzx6yxtgs/T/tp76ab9383_b2f1_4d47_86ea_3739c7447f5f.h5 [0.36s]
tp76ab9383_b2f1_4d47_86ea_3739c7447f5f.h5: 21.7 MB
Finished generating training set. [0.51s]
session timestamp message
_______ ____________________ ________________________

   1       06-Aug-2019 17:06:27    "Fast training (n = 11)"

python "/Users/kacsoh/Desktop/LEAP/leap/leap/training.py" "/private/var/folders/sq/qflygrvs7bxfmh698b3mntzx6yxtgs/T/tp76ab9383_b2f1_4d47_86ea_3739c7447f5f.h5" --base-output-path="/Users/kacsoh/Desktop/LEAP/models" --run-name="190806_170624-n=11" --net-name="leap_cnn" --filters=32 --rotate-angle=5 --val-size=0.10000 --epochs=15 --batch-size=50 --batches-per-epoch=50 --val-batches-per-epoch=10 --reduce-lr-factor=0.1000000000 --reduce-lr-patience=2 --reduce-lr-cooldown=0 --reduce-lr-min-delta=0.0000100000 --reduce-lr-min-lr=0.0000000001 --upsampling-layers --amsgrad
Traceback (most recent call last):
File "/Users/kacsoh/Desktop/LEAP/leap/leap/training.py", line 10, in
import keras
ModuleNotFoundError: No module named 'keras'
Found 11/250 labeled frames.
Loaded 11 images [0.01s]
Generated confidence maps [0.07s]
9.281 MB
Symmetric channels:
earL (5) <-> earR (6)
Saved:
/private/var/folders/sq/qflygrvs7bxfmh698b3mntzx6yxtgs/T/tp7e1beeb5_a952_4c3d_8c71_08b996327b0c.h5 [0.21s]
tp7e1beeb5_a952_4c3d_8c71_08b996327b0c.h5: 21.7 MB
Finished generating training set. [0.40s]
session timestamp message
_______ ____________________ ________________________

   1       06-Aug-2019 17:07:10    "Fast training (n = 11)"

python "/Users/kacsoh/Desktop/LEAP/leap/leap/training.py" "/private/var/folders/sq/qflygrvs7bxfmh698b3mntzx6yxtgs/T/tp7e1beeb5_a952_4c3d_8c71_08b996327b0c.h5" --base-output-path="/Users/kacsoh/Desktop/LEAP/models" --run-name="190806_170708-n=11" --net-name="leap_cnn" --filters=32 --rotate-angle=5 --val-size=0.10000 --epochs=15 --batch-size=50 --batches-per-epoch=50 --val-batches-per-epoch=10 --reduce-lr-factor=0.1000000000 --reduce-lr-patience=2 --reduce-lr-cooldown=0 --reduce-lr-min-delta=0.0000100000 --reduce-lr-min-lr=0.0000000001 --upsampling-layers --amsgrad
Traceback (most recent call last):
File "/Users/kacsoh/Desktop/LEAP/leap/leap/training.py", line 10, in
import keras
ModuleNotFoundError: No module named 'keras'

The python path has been set to python 3.7, which is what we though was the most likely culprit, but it does not seem to fix it. We are analyzing the Tyson demo video (just finished labeling and onto training).

Thanks!

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant