Fangweicheng commented 7 years ago

Hello, I am a Chinese, first of all thank you for sharing. I have some questions that need your answers. The following error occurred while running the SSD300 function: Use the merge function, mode = 'concat' when the six net output dimensions are not the same, resulting in the inability to merge, I do not know how to fix it. Please help me, thank you

The net（SSD300 function ，Line 267 to Line 274 ）： net['mbox_priorbox'] = merge([net['conv4_3_norm_mbox_priorbox'], net['fc7_mbox_priorbox'], net['conv6_2_mbox_priorbox'], net['conv7_2_mbox_priorbox'], net['conv8_2_mbox_priorbox'], net['pool6_mbox_priorbox']], mode='concat', concat_axis=1, name='mbox_priorbox')

Error： 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)]

ahmed-18 commented 7 years ago

@Fangweicheng Did you find a solution? I'm also having the same issue.

viralbthakar commented 7 years ago

60 Duplicate of this I think

Fangweicheng commented 7 years ago

change the version of keras and tensorflow ,keras(1.2.2) tensor flow(1.0)

Fangweicheng commented 7 years ago

@ahmed-18 change the version of keras and tensorflow ,keras(1.2.2) tensor flow(1.0)

Dref360 commented 7 years ago

Add this https://github.com/rykov8/ssd_keras/pull/63/files#diff-53099e21b216bdb89802158e8eaae9baR119 in Keras 2

rykov8 / ssd_keras

The problem of SSD300 #72

60 Duplicate of this I think