concatenate error

[akshitac8]

The other 2 conctenate layer are working but when executing this layer. I get a valueError

mbox_priorbox = concatenate([conv4_3_norm_mbox_priorbox,
                                 fc7_mbox_priorbox,
                                 conv6_2_mbox_priorbox,
                                 conv7_2_mbox_priorbox,
                                 conv8_2_mbox_priorbox,
                                 pool6_mbox_priorbox],
                                 axis=1,
                                 name='mbox_priorbox')

Error:

ValueError: A `Concatenate` layer requires inputs with matching shapes except for the concat axis. Got inputs 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)]

It would be great if I could get a help with this Error.
Thank you :)

[jedichien]

Hi @akshitac8 Thanks for your report, I will check this issue today :D

[akshitac8]

ohkay, Thank you :)

[jedichien]

Hi @akshitac8 what version of keras and tensorflow do you use? It can help me to figure it out the problem :)

[jedichien]

also I notice that the matrix size of these, [conv4_3_norm_mbox_priorbox,
fc7_mbox_priorbox,
conv6_2_mbox_priorbox,
conv7_2_mbox_priorbox,
conv8_2_mbox_priorbox,
pool6_mbox_priorbox], are not the same as I get.

Have you executed these steps?

conv4_3_norm_mbox_priorbox = PriorBox((300, 300), 30.0, name='conv4_3_norm_mbox_priorbox', 
                                              aspect_ratios=[2], variances=[0.1, 0.1, 0.2, 0.2])(conv4_3_norm)
# fc7
fc7_mbox_priorbox = PriorBox((300, 300), 60.0, name='fc7_mbox_priorbox', max_size=114.0, 
                                  aspect_ratios=[2, 3], variances=[0.1, 0.1, 0.2, 0.2])(fc7)

# conv6_2
conv6_2_mbox_priorbox = PriorBox((300, 300), 114.0, max_size=168.0, 
                                      aspect_ratios=[2, 3], variances=[0.1, 0.1, 0.2, 0.2], name='conv6_2_mbox_priorbox')(conv6_2)

# conv7_2
conv7_2_mbox_priorbox = PriorBox((300, 300), 168.0, max_size=222.0, 
                                      aspect_ratios=[2, 3], variances=[0.1, 0.1, 0.2, 0.2], name='conv7_2_mbox_priorbox')(conv7_2)

# conv8_2
conv8_2_mbox_priorbox = PriorBox((300, 300), 222.0, max_size=276.0, 
                                      aspect_ratios=[2, 3], variances=[0.1, 0.1, 0.2, 0.2], name='conv8_2_mbox_priorbox')(conv8_2)

pool6_reshaped = Reshape((1, 1, 256), name='pool6_reshaped')(pool6)

pool6_mbox_priorbox = PriorBox((300, 300), 276.0, max_size=330.0, aspect_ratios=[2, 3], variances=[0.1, 0.1, 0.2, 0.2], name='pool6_mbox_priorbox')(pool6_reshaped)

[akshitac8]

keras = 2.0.8
tensorflow = 1.4.0
yes, I have executed the steps and found the shape mismatch error at PriorBox.
I was unable to find the reason why this was happening :(

[jedichien]

@akshitac8 Okay, I will figure it out :D

[akshitac8]

@jedichien Any updates?

[jedichien]

@akshitac8 Recenly, I work on the other things. I'll try to find the problem this week as soon as possible :D

[jedichien]

@akshitac8 It seems like I got the answer, and thanks for your long waiting. Can you upgrade your keras and tensorflow version to 2.1.5 and 1.7.0 separately? I think it can solve this issue. If you cannot do it, let me know, and I will try to figure out the alternative solution :D

[akshitac8]

Thank you for the information @jedichien I will try the solution.

[jedichien]

@akshitac8 please feel free to let me know if you still cannot run the code. :)