Closed banxia1994 closed 5 years ago
hi, I train the model with coco dataset. config as original cascade_rcnn_r50_fpn_1x.py
model = dict( type='CascadeRCNN', num_stages=3, pretrained='modelzoo://resnet50', backbone=dict( type='ResNet', depth=50, num_stages=4, out_indices=(0, 1, 2, 3), frozen_stages=1, style='pytorch'), neck=dict( type='FPN', in_channels=[256, 512, 1024, 2048], out_channels=256, num_outs=5), rpn_head=dict( type='RPNHead', in_channels=256, feat_channels=256, anchor_scales=[8], anchor_ratios=[0.5, 1.0, 2.0], anchor_strides=[4, 8, 16, 32, 64], target_means=[.0, .0, .0, .0], target_stds=[1.0, 1.0, 1.0, 1.0], use_sigmoid_cls=True), bbox_roi_extractor=dict( ....
but i use one gpu with lr = 0.002
log show as follow:
and test: python tools/test.py --config --model --eval bbox --out result:
help.. what's wrong ?
According to the log, you used lr=0.02.
hi, I train the model with coco dataset. config as original cascade_rcnn_r50_fpn_1x.py
but i use one gpu with lr = 0.002
log show as follow:
and test: python tools/test.py --config --model --eval bbox --out result:
help.. what's wrong ?