Comments (11)
And, I tried to train the model without pre-trained model, the "detection_eval" increased slowly, which is about "0.2" when the "Iteration 60000"
from dsod.
Hi @wangzhe0623,
- The inconsistent model size is caused by the final classification layers (different numbers of category). We adopted the same network structure for VOC and coco but obtained totally different model size (59.2M vs. 87.2M). If you want to use our pre-trained model, use this script (https://github.com/weiliu89/caffe/blob/ssd/examples/convert_model.ipynb) provided by SSD's author to convert our model to your data, or simply rename the prediction layers.
- I think #7 will help you.
from dsod.
@szq0214 Thanks a lot~ But I think I didn't make it clear in last comment. I have converted my dataset to VOC style, and "test_name_size", "labelmap" are also OK. I changed "num_classes" in "DSOD300_pascal.py". then run it without pre-trained model. Now the "detection_eval" is slower after 70000 iterations, it's lower than 0.2~ Is that normal? Should I continue training this model or stop to check?
Thanks again!
from dsod.
Hi @wangzhe0623, It's not normal with so poor performance. I think you should stop it and try other parameters. BTW, what "accum_batch_size" number do you use?
from dsod.
@szq0214 I set "accum_batch_size" 8, and "batch_size" is 8, either.
from dsod.
@wangzhe0623 "accum_batch_size" is too small, try 128 or other larger number.
from dsod.
@szq0214 OK,I modified iter_size to 8 in "solver.protxt" instead, should I restart all over again OR fine tune the model with low precision? So much thanks~
from dsod.
@wangzhe0623 I recommend restarting from scratch.
from dsod.
@szq0214 OK, I will try it. Thanks a lot!
from dsod.
@szq0214 It worked. "iter_size" is quite importent in training this kind of net, I used to ignore it in the past. So many many many thanks~
from dsod.
@wangzhe0623 :)
from dsod.
Related Issues (20)
- Video Detection HOT 1
- Did the DSOD model code have tensorflow version? HOT 1
- about how to batch test many image files? HOT 1
- Have you tried large input images (600 * 1000)? HOT 1
- About 1 Channel images HOT 2
- small batchsize has a lower mAP. HOT 3
- Question about pooling layer in your DSOD300 HOT 1
- No such File or Directory - Core Dumped HOT 1
- Couldn't find any detections HOT 1
- Test on VOC2012 HOT 2
- The result after relu activation function isn't used in grp-dsod. HOT 1
- training on new dataset HOT 1
- Sixth_norm_mbox_priorbox step parameter is wrong HOT 1
- grp-dsod pretrained models
- Reproduced result is lower than the reported result HOT 1
- Why not public caffe train_val.prototxt?
- NameError :name ‘DSOD300_V3_Body’ is not defined. How to deal with it? HOT 1
- Any Dockerfile?
- Why the speed of DSOD is too slow in the process of training? HOT 1
- How long does model take when I have 20 000 images, 1 class with Quadro P4000
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 dsod.