louyanyang
louyanyang
@Franciszzj I do this experiment on Mxnet,but i modified the symbols. when training, the RCNNAcc was abnormal. i dont known if the symbols is wrong or not.
@Franciszzj 'MXNET_VERSION': 'mxnet', 'SCALES': [(600, 1000)], 'TEST': {'BATCH_IMAGES': 1, 'CXX_PROPOSAL': False, 'HAS_RPN': True, 'NMS': 0.3, 'PROPOSAL_MIN_SIZE': 0, 'PROPOSAL_NMS_THRESH': 0.7, 'PROPOSAL_POST_NMS_TOP_N': 2000, 'PROPOSAL_PRE_NMS_TOP_N': 20000, 'RPN_MIN_SIZE': 0, 'RPN_NMS_THRESH': 0.7, 'RPN_POST_NMS_TOP_N': 300, 'RPN_PRE_NMS_TOP_N':...
@Franciszzj thanks for your reply
@wenqingchu offset channels = num_deformable_group * 2 * kernel_height * kernel_width
@Fragrance307 so sorry, it's classified to share codes for company rules.
more epoches is also bad. num_deformable_group affects much in my implementation based on caffe.
呵呵，我（娄艳阳）已收到您的信，祝你事事顺心，快乐相随
呵呵，我（娄艳阳）已收到您的信，祝你事事顺心，快乐相随