Closed wxy656 closed 5 years ago
line 298:
conv5_1 = slim.convolution2d(conv4_1, 512, [1, 1], stride=2, activation_fn=None,scope='conv5_1/expand')
line 362:
conv6_1 = slim.convolution2d(block5_6, 256,
the data output from conv5 is 7 7 128 ,not the one you write on line 362. Maybe stride on line 299 shouldbe 1 ,not 2 which you write
Compared the convolution stride with the paper ,stride on line 299 should be 1 rather than 2.
line 298:
14 14 128
line 362:
14 14 128
the data output from conv5 is 7 7 128 ,not the one you write on line 362. Maybe stride on line 299 shouldbe 1 ,not 2 which you write