-
Notifications
You must be signed in to change notification settings - Fork 553
keras 2.0 concat error in ssd.train ipython #60
Comments
@hzycn you need to rename |
Thank you @rykov8 , I changed the get_output_shape to computer_output_shape in |
@hzycn is it a missprint in your comment? You need |
Works after @rykov8 suggestion implemented, and it seems to be only necessary change. |
i'm having the same issue. not sure i am interpreting the suggested fix correctly though: in Class PriorBox change: ??? |
@BenMacKenzie not exactly. You need to rename def get_output_shape_for(self, input_shape):
... to def compute_output_shape(self, input_shape):
... It's just a |
When I code the ssd.train.ipython in notebook, the follwing error will appear, i has upgrade the keras 2.0 version:
ValueError: "concat" mode can only merge layers with matching output shapes except for the concat axis. Layer shapes: [(None, 38, 38, 512), (None, 19, 19, 1024), (None, 10, 10, 512), (None, 5, 5, 256), (None, 3, 3, 256), (None, 1, 1, 256)]
The text was updated successfully, but these errors were encountered: