Comments (6)
@KeyKy I have fixed the issue with an updated caffe_train (https://github.com/CMU-Perceptual-Computing-Lab/caffe_train). Also, it uses a newer version of caffe so that it is compatible with CUDA 7.5/ 8.0 and cudnn v5. Let me know if you meet other issues.
from realtime_multi-person_pose_estimation.
I found these code in caffe.proto. I guess author move cpm_transform_param to transform_param.
message TransformationParameter {
...
optional uint32 stride = 6 [default = 4];
optional float scale_cvg = 7 [default = 0.5];
optional uint32 max_cvg_len = 8 [default = 50];
optional uint32 min_cvg_len = 9 [default = 50];
optional bool opaque_coverage = 10 [default = true];
optional string coverage = 11 [default = "gridbox_max"];
optional float flip_prob = 12 [default = 0.5];
optional float max_rotate_degree = 13 [default = 5.0];
optional bool visualize = 14 [default = false];
optional uint32 crop_size_x = 15 [default = 368];
optional uint32 crop_size_y = 16 [default = 368];
optional float scale_prob = 17 [default = 0.5];
optional float scale_min = 18 [default = 0.9];
optional float scale_max = 19 [default = 1.1];
optional float bbox_norm_factor = 20 [default = 300];
optional string img_header = 21 [default = "."];
// Force the decoded image to have 3 color channels.
optional bool force_color = 22 [default = false];
// Force the decoded image to have 1 color channels.
optional bool force_gray = 23 [default = false];
optional float target_dist = 24 [default = 1.0];
optional float center_perterb_max = 25 [default = 10.0];
optional float sigma = 26 [default = 7.0];
optional float sigma_center = 27 [default = 21.0];
optional float clahe_tile_size = 28 [default = 8.0];
optional float clahe_clip_limit = 29 [default = 4.0];
optional bool do_clahe = 30 [default = false];
optional uint32 num_parts = 31 [default = 14];
optional uint32 num_total_augs = 32 [default = 82];
optional string aug_way = 33 [default = "rand"];
optional uint32 gray = 34 [default = 0];
optional uint32 np_in_lmdb = 35 [default = 16];
optional bool transform_body_joint = 38 [default = true];
}
from realtime_multi-person_pose_estimation.
Thanks for your kindness
from realtime_multi-person_pose_estimation.
@KeyKy Could you train now? when I use caffe_train, compiling has some problem, I can't 'make all' so other work can not continue. Could you help me to find the problem?
from realtime_multi-person_pose_estimation.
Not yet, I also have compiling problem because i use cudnn v5 and the caffe_train may be too old to compile. Now i am rewriting the test code.
And if i do not use cudnn, i get the same error as you.
from realtime_multi-person_pose_estimation.
Thanks a lot, I use cudnn v4 and opencv3.1. If you solve the problem, Please inform me , Thank you very much.
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.