Comments (4)
I think the problem was that I was using CUDA 8.0, I had to add
-gencode arch=compute_52,code=sm_52 \
-gencode arch=compute_60,code=sm_60 \
-gencode arch=compute_61,code=sm_61 \
-gencode arch=compute_61,code=compute_61
To CUDA_ARCH in Makefile.config after that I ran into a file not found error and had to change the bottom level directory in dataFolder
and source to lmdb
instead of lmdb_trainVal
so that it could find the .mdb files
Just figured I would post that in case anyone else ran into the same problem
from realtime_multi-person_pose_estimation.
@mddrill I am getting the same problem, I use the CUDA_ARCH you added above, and I am sure that the source is pointed to correct lmdb directory in pose_train_test.prototxt. But the problem still exists.
Any further idea about the problem?
Thank you!
from realtime_multi-person_pose_estimation.
I bave error when training the lmdb ,when training 1900 iteration.
Any one solve this problem before?
Thanks in advance!
Regards!
=================================================================
I1016 10:34:47.675484 11884 sgd_solver.cpp:106] Iteration 1900, lr = 4e-05
F1016 10:36:11.466152 11892 cpm_data_transformer.cpp:386] Check failed: datum_channels == 6 (0 vs. 6)
*** Check failure stack trace: ***
@ 0x7f3ae04f45cd google::LogMessage::Fail()
@ 0x7f3ae04f6433 google::LogMessage::SendToLog()
@ 0x7f3ae04f415b google::LogMessage::Flush()
@ 0x7f3ae04f6e1e google::LogMessageFatal::~LogMessageFatal()
@ 0x7f3ae0d07e1b caffe::CPMDataTransformer<>::Transform_nv()
@ 0x7f3ae0b720f5 caffe::CPMDataLayer<>::load_batch()
@ 0x7f3ae0b837af caffe::BasePrefetchingDataLayer<>::InternalThreadEntry()
@ 0x7f3ae0b37d05 caffe::InternalThread::entry()
@ 0x7f3ad673a5d5 (unknown)
@ 0x7f3ad0d796ba start_thread
@ 0x7f3aded713dd clone
@ (nil) (unknown)
from realtime_multi-person_pose_estimation.
maybe that one of dataset is wrong.I thank u can delete that image of the dataset
from realtime_multi-person_pose_estimation.
Related Issues (20)
- training loss is strange,for openpose body_25 model training HOT 9
- training HOT 3
- training of images with no humans HOT 1
- Retraining with lesser COCO images.
- Pretrained model? HOT 2
- Is it ok to use "CMU-Perceptual-Computing-Lab/caffe" instead of "caffe_train" for training?
- How can I find models and papers about body25?
- Problem about train on own dataset HOT 3
- Dataset problem
- Low resolution images
- Limb width is hardcoded?
- bug when generating mask
- mxnet version
- MMC demo
- Extracting keypoints to json file HOT 2
- finetuning the model HOT 12
- heatmap evaluatin metric HOT 1
- bash getData.sh wget didn't work HOT 4
- Error in gason.m
- Where can I download matconvnet_coco_openpose_model.mat ? HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from realtime_multi-person_pose_estimation.