Dai wenxin comments

Results 34 comments of


                                            Dai wenxin

where is the pre-training model ？ how to get it ?

thank you !

训练时，任意width、height的图片都不会报错么？

when I run the demo.py,there is a problem,could you help me?????? Loaded network /home/xmpu234/Documents/FPN-caffe_1/data/faster_rcnn_models/fpn_iter_25000.caffemodel Traceback (most recent call last): File "/home/xmpu234/Documents/FPN-caffe_1/tools/demo.py", line 142, in _, _= im_detect(net, im) File "/home/xmpu234/Documents/FPN-caffe_1/tools/../lib/fast_rcnn/test.py",...

scale problem

training on my own dataset

作者您好，请问训练集像素大小为100*100，目标大小为40*40 ，请问训练时如何设置anchor大小？？谢谢作者啦

training on my own dataset

您好，请问为什么我训练自己的模型会怎么慢速度？前面几百次迭代，每20次只需要 34S 左右，到了2000次左右时，每20次需要 5-6分钟为什么会那么慢？？？？？我的显卡是 GPU 1080Ti 的 12G运行内存

FPN训练小目标数据

> 你好，unsky。我在做小目标检测的实验，之前用你的旧代码（VGG16模型）召回率可以达到90%左右，用新的代码（RESNET50 sharedrcnn）召回率只有70%左右。尝试改了scales为[4,8]和FPN/lib/fast_rcnn/config.py里的一些参数，但是效果都不理想，能不能给一些建议，谢谢！您好，我也是做小目标检测，您好，请问为什么我训练自己的模型会怎么慢速度？前面几百次迭代，每20次只需要 34S 左右，到了2000次左右时，每20次需要 5-6分钟为什么会那么慢？？？？？我的显卡是 GPU 1080Ti 的 12G运行内存

Does the code support training fpn with batch size 1 with one gpu?

@anorthman there is this layer named “rpn_rois/p2”

Does the code support training fpn with batch size 1 with one gpu?

when I run the demo.py,there is a problem,could you help me?????? Traceback (most recent call last): File "/home/xmpu234/Documents/FPN_1/tools/demo.py", line 144, in _, _= im_detect(net, im) File "/home/xmpu234/Documents/FPN_1/tools/../lib/fast_rcnn/test.py", line 298, in...