Comments (4)
Indeed it was related to dropout, it was saved as 0.5 instead of 1.0
from darkflow.
Can you elaborate on this? If this is a bug I am welcoming your pull requests!
from darkflow.
I am not sure if it is a bug or planned feature, but TensorFlow graphs saved using --savepb contain a dropout layer with a keep probability of 0.5. For evaluation/testing purposes, it is not good, because
- It makes the net "weaker"
- It makes the results non deterministic, each run a bit different result.
It might be good if one is planning to re-train the network in another framework.
I don't know how to fix it correctly. Currently I hard-coded the keep probability to 1.0 when the layer is being built. That is of course not good for training.
I guess that you can put a code right before the actual saving that changes the probability?
class dropout_layer(Layer):
def setup(self, p):
self.h['pdrop'] = dict({
#'feed': p, # for training
'feed': 1.0, # for training
'dfault': 1.0, # for testing
'shape': ()
})
from darkflow.
Thanks for spotting this silly bug. Please pull the new code and check if it is working.
from darkflow.
Related Issues (20)
- [Documentation] Link to the Android demo is broken
- tiny yolo predict a lot of bounding boxes for one class problem HOT 1
- Result is empty HOT 2
- PermissionError: [Errno 13] Permission denied: './ckpt/checkpoint' HOT 1
- How to put a darkflow model into Android Studio
- Importing to external project
- Accuracy HOT 1
- error in getting started
- Version of yolo from the yolo.cfg file
- Shrikant@ can you help in in regard of this.
- What's wrong with Darkflow?
- can't import darkflow
- Build Error darkflow on 20.04 Ubuntu
- Training own model
- How to convert tensorflow to darknet?
- Convert annotation video mat files to COCO
- Tensorflow update to TF 2.x
- python setup.py build_ext --inplace HOT 3
- pip install -e .
- NMS.pxd not found
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 darkflow.