I've recently started to encounter a new problem with LEAP.
When I run label_joints and do fast training, the outcome is the following:
python "C:\Users\Yinlab\Documents\GitHub\leap\leap\training.py" "C:\Users\Yinlab\AppData\Local\Temp\tp3659dd2a_0acd_4e2e_85e5_e254838f4448.h5" --base-output-path="C:\Data\WT471\May 14 2019\Video 1\PeriLickVid\models" --run-name="190518_141406-n=22" --net-name="leap_cnn" --filters=32 --rotate-angle=5 --val-size=0.10000 --epochs=1 --batch-size=10 --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 "C:\Users\Yinlab\Documents\GitHub\leap\leap\training.py", line 2, in <module> import h5py File "C:\Users\Yinlab\Anaconda3\lib\site-packages\h5py\__init__.py", line 36, in <module> from ._conv import register_converters as _register_converters File "h5py\h5r.pxd", line 21, in init h5py._conv File "h5py\_objects.pxd", line 12, in init h5py.h5r File "h5py\_objects.pyx", line 1, in init h5py._objects ImportError: DLL load failed: The specified procedure could not be found.
the version of h5py I have (using the conda list h5py command in terminal) is 2.7.1.
I've also noticed that running the test line
!python -c "import tensorflow as tf; print(tf.test.is_gpu_available())"
no longer results in any output in matlab. It works when I run it in terminal.
I reinstalled tensorflow-gpu to version 1.12 using that walk through you made, but there was no success.
Hi Talmo,
I've recently started to encounter a new problem with LEAP.
When I run label_joints and do fast training, the outcome is the following:
python "C:\Users\Yinlab\Documents\GitHub\leap\leap\training.py" "C:\Users\Yinlab\AppData\Local\Temp\tp3659dd2a_0acd_4e2e_85e5_e254838f4448.h5" --base-output-path="C:\Data\WT471\May 14 2019\Video 1\PeriLickVid\models" --run-name="190518_141406-n=22" --net-name="leap_cnn" --filters=32 --rotate-angle=5 --val-size=0.10000 --epochs=1 --batch-size=10 --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 "C:\Users\Yinlab\Documents\GitHub\leap\leap\training.py", line 2, in <module> import h5py File "C:\Users\Yinlab\Anaconda3\lib\site-packages\h5py\__init__.py", line 36, in <module> from ._conv import register_converters as _register_converters File "h5py\h5r.pxd", line 21, in init h5py._conv File "h5py\_objects.pxd", line 12, in init h5py.h5r File "h5py\_objects.pyx", line 1, in init h5py._objects ImportError: DLL load failed: The specified procedure could not be found.the version of h5py I have (using the conda list h5py command in terminal) is 2.7.1.
I've also noticed that running the test line
!python -c "import tensorflow as tf; print(tf.test.is_gpu_available())"no longer results in any output in matlab. It works when I run it in terminal.
I reinstalled tensorflow-gpu to version 1.12 using that walk through you made, but there was no success.
Thanks and have a great weekend, Konstantin