Tushar

how can I verify if it is using gpu resources to full throttle

 ldd g2o_viewer a.g2o g2o_viewer: ldd: ./g2o_viewer: No such file or directory a.g2o: not a dynamic executable

same problem ... filter size should not be greater than input layer size on which filter is applied ... @tokb23 please highlight this issue

this problem has to do with input convention of input_shape=(STATE_LENGTH, FRAME_WIDTH, FRAME_HEIGHT) @a920604a option is to change keras.json file to following configuration { "image_dim_ordering": "th", "epsilon": 1e-07, "floatx": "float32", "backend":...

I think updating ur keras API should solve problem pip install --upgrade keras

Ohhh !!! in that can you post your ~/.kerasrc file? ‌ On Mon, Oct 23, 2017 at 12:11 PM, 仲耀晖 wrote: > As I upgraded, I still have the same...

sorry actually ~/.keras/keras.json this file ‌ On Mon, Oct 23, 2017 at 5:13 PM, tushar vaidya wrote: > > Ohhh !!! in that can you post your ~/.kerasrc file? >...

May be you refer here and change function call ‌ On Thu, Jan 18, 2018 at 12:41 AM, impulsecorp wrote: > I get that same error, even after I change...

parallelly I would encourage to use this fork as original author did not merge pull request. https://github.com/Exception4U/dqn-1

@jyomu @bchretien Facing the same issue ... any leads on cause of this ?