Comments (4)
Yes i have the same problem. Swap_data becomes an -nan. In my case, one of my data label goes wrong. ymin = ymax, which means w=0. divide to 0 can cause nan.
from caffe-yolov2.
how to add negative data?
from caffe-yolov2.
Yes i have the same problem. Swap_data becomes an -nan. In my case, one of my data label goes wrong. ymin = ymax, which means w=0. divide to 0 can cause nan.
I also met the same issue, and in my case it also seems to be data problem. I found some of my data has swapped min
and max
or the coordinates. After fixing that, it works again.
from caffe-yolov2.
I0804 17:49:41.090296 13616 solver.cpp:245] Train net output #0: region1 = 130.248 (* 1 = 130.248 loss)
I0804 17:49:41.090306 13616 sgd_solver.cpp:115] Iteration 0, lr = 0.0001
I0804 17:50:22.566540 13616 region_loss_layer.cpp:469] avg_noobj: 0.440657 avg_obj: 0.441241 avg_iou: 0.623299 avg_cat: 0.250071 recall: 1 class_count: 5
I0804 17:50:53.259757 13616 solver.cpp:229] Iteration 20, loss = 104.177
I0804 17:50:53.259923 13616 solver.cpp:245] Train net output #0: region1 = 96.0165 (* 1 = 96.0165 loss)
I0804 17:50:53.259968 13616 sgd_solver.cpp:115] Iteration 20, lr = 0.0001
I0804 17:51:07.790935 13616 region_loss_layer.cpp:469] avg_noobj: 0.348465 avg_obj: 0.348111 avg_iou: 0.431767 avg_cat: 0.250216 recall: 0.391304 class_count: 23
I0804 17:51:53.122269 13616 region_loss_layer.cpp:469] avg_noobj: 0.270268 avg_obj: 0.270857 avg_iou: 0.55787 avg_cat: 0.24985 recall: 0.857143 class_count: 7
I0804 17:52:06.210116 13616 solver.cpp:229] Iteration 40, loss = 49.2193
I0804 17:52:06.210199 13616 solver.cpp:245] Train net output #0: region1 = 41.1888 (* 1 = 41.1888 loss)
I0804 17:52:06.210211 13616 sgd_solver.cpp:115] Iteration 40, lr = 0.0001
I0804 17:52:39.102437 13616 region_loss_layer.cpp:469] avg_noobj: 0.223499 avg_obj: 0.225008 avg_iou: 0.568238 avg_cat: 0.250957 recall: 0.666667 class_count: 6
F0804 17:53:05.186326 13616 region_loss_layer.cpp:234] **Check failed: ## swap_data[index] >= 0 (-nan vs. 0)
*** Check failure stack trace: *****
@ 0x7f2e06772daa (unknown)why the value below 0 ?
I0327 05:32:30.823518 16831 solver.cpp:218] Iteration 200 (3.38936 iter/s, 59.0082s/200 iters), loss = inf
I0327 05:32:30.823693 16831 solver.cpp:237] Train net output #0: det_loss = inf (* 1 = inf loss)
I0327 05:32:30.823709 16831 sgd_solver.cpp:114] Iteration 200, lr = 0.0001
F0327 05:32:30.917165 16831 region_loss_layer.cpp:230] Check failed: swap_data[index] >= 0 (-nan vs. 0)
*** Check failure stack trace: ***
@ 0x7fb37d19d5cd google::LogMessage::Fail()
@ 0x7fb37d19f433 google::LogMessage::SendToLog()
@ 0x7fb37d19d15b google::LogMessage::Flush()
@ 0x7fb37d19fe1e google::LogMessageFatal::~LogMessageFatal()
@ 0x7fb37d818144 caffe::RegionLossLayer<>::Forward_cpu()
@ 0x7fb37d7e5857 caffe::Net<>::ForwardFromTo()
@ 0x7fb37d7e5be7 caffe::Net<>::Forward()
@ 0x7fb37d97caa8 caffe::Solver<>::Step()
@ 0x7fb37d97d64a caffe::Solver<>::Solve()
@ 0x40f1e5 train()
@ 0x40b4bd main
@ 0x7fb37b75b830 __libc_start_main
@ 0x40c049 _start
@ (nil) (unknown)
Aborted (core dumped)
Does anyone know how to solve it?
from caffe-yolov2.
Related Issues (20)
- How do I get mAP? HOT 7
- How to detect a picture after use convert_weights_to_caffemodel.py get a caffe model weight HOT 2
- Loss
- How to convert the weights to caffemodel? HOT 6
- What is the meaning of '30' in region_loss_layer.cpp HOT 1
- How about the speed?
- Aborted at 1526157655 (unix time) try "date -d @1526157655" if you are using GNU date HOT 1
- How to convert the weights to caffemodel HOT 3
- Got training stuck.
- how to convert densenet201_yolo.cfg and .weights to .prototxt and .caffemodel
- Cudnn version and reorg_param problems
- cudnn version and reorg_param problems HOT 1
- Segmentation fault when running examples/indoor/eval_detection test_yolo_v2.py
- Does anyone ever successfully installed this software on any platform?
- caffe-yolov2/include/caffe/layers/box_data_layer.hpp
- what's tje required cudnn version?
- Apply this to movidius
- Question about Input data "BoxData"
- About “ERROR : size mismatch”, why I can't get the output of .caffemodel? HOT 2
- Logical error in BoxDataLayer?
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 caffe-yolov2.