Comments (5)
try dev branch with lr=0.0001
from mxnet-yolo.
@zhreshold thank you very much. I change the learning rate as you said. It is much better.
I didn't use pretrain model, and after 200 epoch, mAP is 0.51.
INFO:root:Epoch[200] Train-Acc=0.882000
INFO:root:Epoch[200] Train-IOU=0.685558
INFO:root:Epoch[200] Train-BG-score=0.004245
INFO:root:Epoch[200] Train-Obj-score=0.256506
INFO:root:Epoch[200] Time cost=297.076
INFO:root:Saved checkpoint to "/home/sooda/deep/object/mxnet-yolo/model/yolo2_416-0201.params"
INFO:root:Epoch[200] Validation-aeroplane=0.595343
INFO:root:Epoch[200] Validation-bicycle=0.642839
INFO:root:Epoch[200] Validation-bird=0.428441
INFO:root:Epoch[200] Validation-boat=0.413425
INFO:root:Epoch[200] Validation-bottle=0.204297
INFO:root:Epoch[200] Validation-bus=0.623591
INFO:root:Epoch[200] Validation-car=0.685286
INFO:root:Epoch[200] Validation-cat=0.599618
INFO:root:Epoch[200] Validation-chair=0.307342
INFO:root:Epoch[200] Validation-cow=0.450331
INFO:root:Epoch[200] Validation-diningtable=0.528938
INFO:root:Epoch[200] Validation-dog=0.531340
INFO:root:Epoch[200] Validation-horse=0.639920
INFO:root:Epoch[200] Validation-motorbike=0.583562
INFO:root:Epoch[200] Validation-person=0.632997
INFO:root:Epoch[200] Validation-pottedplant=0.254757
INFO:root:Epoch[200] Validation-sheep=0.497984
INFO:root:Epoch[200] Validation-sofa=0.472311
INFO:root:Epoch[200] Validation-train=0.686695
INFO:root:Epoch[200] Validation-tvmonitor=0.527394
INFO:root:Epoch[200] Validation-mAP=0.515321
from mxnet-yolo.
@zhreshold after 240 epochs, the mAP drop to 0.48. the highest mAP is 0.52. I only use one gpu. how can I get a better result? use a pretrained model?
Thank you.
from mxnet-yolo.
A pretrained model on imagenet is prefered
from mxnet-yolo.
Thanks, I will have a try.
from mxnet-yolo.
Related Issues (20)
- import HOT 1
- Error in building HOT 4
- What the number of column 9 mean in file *.lst? HOT 1
- Can not run using GPU HOT 2
- how to write a .json config file? HOT 1
- why error when using pretrained model?
- MXNet built from source problem HOT 3
- AttributeError: module 'mxnet.contrib.symbol' has no attribute 'YoloOutput' HOT 10
- The different effects of different resnet pretrained models HOT 3
- 'module' object has no attribute 'Yolo2Output' HOT 8
- Errors when running demo.py and video_demo.py HOT 1
- mxnet.base.MXNetError: Failed loading Op yolo_output of type _contrib_Yolo2Output: [13:11:48] src/core/op.cc:55: Check failed: op != nullptr Operator _contrib_Yolo2Output is not registered HOT 6
- Any plans for yolov3? HOT 8
- method get_symbol() cannot be invoked correctly HOT 2
- Acc don't change
- training on my own dataset
- symbol_darknet19.py batchnorm layers use_global_stats problems
- Why not use the mxnet.image.ImageDetIter?
- Not reliable
- What is the execution environment
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 mxnet-yolo.