can not reduce model reduce

[kikyou123]

when i download your model, the Model MSE is 0.08421.
But when I run the kitti_train.py and use the trained weights, I get the Model MSE 0.018259
this is my results in the test set:

Is the model in download_models.sh using the kitti_train.py?

[bill-lotter]

Yes the weights are trained using kitti_train. With the downloaded weights, are you missing a zero and it's 0.008421? Because that's about what I get when I use the tensorflow backend (with theano, I get ~0.007). Not sure why it seems to not train as well for some people. Easy first things to try are different optimizers/learning rates/momentum. Sometimes Rmsprop works better when adam struggles, so you can give that a try.

[robbiewu008]

@kikyou123 I got the similar result with you, my env is tensorflow-gpu 1.2.1, keras 2.0.6 with cudnn v5.1 for cuda 8.0.

Model MSE: 0.017124
Previous Frame MSE: 0.021246

[kikyou123]

@robbiewu008 It seems there is a bug in the code.
in the kitti_train.py rrors_by_time = TimeDistributed(Dense(1, weights=[layer_loss_weights, np.zeros(1)], trainable=False), trainable=False)(errors) # calculate weighted error by layerr. It seems the layer_loss_weights can't load. you can change it

and try it again!
I got the about the 0.007

[robbiewu008]

@kikyou123 missing the Reshape, could you share it?

[kikyou123]

@robbiewu008

[robbiewu008]

@kikyou123 still don't work.

[kikyou123]

sorry, It is multi prediction code. You can change

)
15 to 10

[robbiewu008]

@kikyou123 It works now, thank you so much!

Model MSE: 0.006937
Previous Frame MSE: 0.021246

[xukai8]

@kikyou123 Did you successfully train the model for muti-step prediction? I get the stable frames over time step.

[bill-lotter]

@kikyou123 It looks like there's an issue with TimeDistributed in Keras 2 where it overrides the initial weights of the layer to be wrapped (keras-team/keras#8895). I changed the kitti_train.py code to account for this (9f6482e). It should work now, but let me know if you find any other issues - thanks!

[alvinxiii]

@kikyou123 @bill-lotter hi. I tried run the multi prediction code. I barely see the differences from it. Is this the correct steps?
This is my step:

1. run kitti_train.py
2. run kitti_extrap_finetune.py
3. run kitti_evaluate.py