liu-yicheng / faster-rcnn Goto Github PK
View Code? Open in Web Editor NEWMy implementation of Faster-RCNN (Pytorch)
My implementation of Faster-RCNN (Pytorch)
我用一张图片训练的时候是正常的,但是将全部图片写进train.txt和放到其他xml的文件夹时,显示AssertionError,我想请问一下这个error的情况
Called with args:
Namespace(batch_size=1, checkepoch=1, checkpoint=0, checkpoint_interval=10000, checksession=1, class_agnostic=True, cuda=True, disp_interval=1, large_scale=False, lr=0.001, lr_decay_gamma=0.5, lr_decay_step=50, max_epochs=500, num_workers=0, optimizer='adam', resume=False, save_epochs=500, session=1, start_epoch=1, use_tfboard=False)
Preparing training data
gt roidb loaded from /home/liangfeifan161_gmail_com/Faster-rcnn/Data/picture_data/cache/gt_roidb.pkl
Traceback (most recent call last):
File "trainval_net.py", line 154, in <module>
imdb, roidb, ratio_list, ratio_index = get_imdb_and_roidb('train')#'train'代表读取的是train.txt文件
File "/home/liangfeifan161_gmail_com/Faster-rcnn/Data/pascal.py", line 81, in get_imdb_and_roidb
roidb = get_roidb(imdb_set)
File "/home/liangfeifan161_gmail_com/Faster-rcnn/Data/pascal.py", line 42, in get_roidb
roidb = get_training_roidb(imdb)
File "/home/liangfeifan161_gmail_com/Faster-rcnn/Data/pascal.py", line 35, in get_training_roidb
prepare_roidb(imdb)
File "/home/liangfeifan161_gmail_com/Faster-rcnn/Data/pascal.py", line 27, in prepare_roidb
assert all(max_classes[nonzero_inds] !=0)
AssertionError
你好,在编译程序所需要的组件nms时,我遇到了“command 'gcc' failed with exit status 1”的bug,一直困扰着我,请问您之前有遇到过吗,谢谢
这个可以训练png 图片吗?
I think your pictures are quite large. Do you need to cut them into the model?
i just tried to compile but failed because i don't have cuda in my laptop, And I find roi_pooling.c and roi_pooling_cuda.c in the folder under lib, so I think maybe this code can be used without cuda. How can i change the make.sh to run without cuda?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.