search

pydsgz / DeepVOG

Pupil segmentation and gaze estimation using fully convolutional neural networks
GNU General Public License v3.0
153 stars 68 forks source link

Keras type error : symbolic inputs/outputs donot match #15

Open Jay2109 opened 3 years ago

Jay2109 commented 3 years ago

raise TypeError('Keras symbolic inputs/outputs do not ' TypeError: Keras symbolic inputs/outputs do not implement __len__. You may be trying to pass Keras symbolic inputs/outputs to a TF API that does not register dispatching, preventing Keras from automatically converting the API call to a lambda layer in the Functional Model. This error will also get raised if you try asserting a symbolic input/output directly

mangotee commented 3 years ago

Hi Jay2109, this reads like a Tensorflow >2.0 issue to me. Either downgrade your TF version to 1.12.0, or you may need to make a port to TF2.0, since we are working on a major update (including a switch to PyTorch) which is taking up our ressources for this project. However, afaik, spokV has already been working on a port to TF2.0 already, you can check out their version at: https://github.com/spokV/DeepVOG

KamranBinaee commented 3 years ago

Hi, I have the same issue. I was able to run on CPU after downgrading the TF. Trying to run on GPU and I get Cuda error apparently: ImportError: libcublas.so.9.0: cannot open shared object file: No such file or directory