Closed ACkuku closed 5 years ago
Also supply key (a name of your choice), e.g. https://github.com/apache/incubator-mxnet/blob/3ae43316549bc9f7488028475861729aeaf56df1/python/mxnet/gluon/contrib/nn/basic_layers.py#L225
Thanks for your reply~ I trained the resnet-50, the VOD dataset, and I got the results:
no syncBN, and the Mean AP = 0.6242
,
with syncBN, and the Mean AP = 0.5654
all of BN layers changed to SyncBN, and fix_gamma=False, use_global_stats=False, ndev=2
,
and fixed the layer params:
'conv0',
'stage1_unit1_conv1',
'stage1_unit1_conv2',
'stage1_unit1_conv3' ,
'stage1_unit1_sc',
'stage1_unit2_conv1',
'stage1_unit2_conv2',
'stage1_unit2_conv3',
'stage1_unit3_conv1',
'stage1_unit3_conv2',
'stage1_unit3_conv3'
I don't know why the AP drop off ? Do you have any idea about this? Thank you~
Effective batch size = 2 is still a small batch size. Maybe try set rcnn-batch-size to be more than 1.
I changed the
symbol_resnet.py
BatchNorm to SyncBatchnorm, for example:but, when I training VOC dataset, I got the error:
Do you know why? Thank you~