Comments (5)
Standard training already uses pre-trained SqueezeNet trained on Imagenet to start, you should be able to use your 1060 if you are patient enough... especially since the GPU is starved during training with the current code.
from squeezedet.
Download the one from classification, not the one from detection, the detection model is based on the classification squeeze net so it is a good way to initialise it.
You can use it on as many classes you want just change the classes on the right model config file
from squeezedet.
Thank you for the reply,
-
Where should I change to train the model for different number of classes?
-
How many classes do the pre-trained model support? I think for example if you have trained it for 2 classes, we can not use it for 3 and should have the same or lower number of classes, am I right?
-
in the readme you mentioned:
Download SqueezeDet model parameters from here, untar it, and put it under $SQDT_ROOT/data/ If you are using command line, type:
Should I use this to find-tune isn't it? Then why I should download the pre-trained classification model also?
Next, download the CNN model pretrained for ImageNet classification:
from squeezedet.
last question:
Have you tested the mAP on VOC also?
from squeezedet.
@andreapiso I have the same question: if I train the SqueezeDet model, i.e. the detector, can I - in a second moment - have its weights as an initial starting point to begin my training?
And if yes, how do I do it?
from squeezedet.
Related Issues (20)
- Gpu occupancy rate
- where is base_model_config.py?
- Will random initialization parameters have no precision? HOT 1
- Fine-tune SqueezeDet from sparse labels
- How to do hard negative mining HOT 1
- Publish frozen model? HOT 3
- Problem converting to TFLite HOT 3
- low GPU usage
- 8-bit weights
- Deploying squeezeDet on mobile HOT 3
- How to convert checkpoint of squeezedet to frozen graph for tflite conversion?! HOT 1
- Image resolution problem
- How to run demo.py using train.py checkpoint model HOT 1
- Train with different size and Inference with different size.
- Fine tuning with the model
- Train error and Eval error
- Using negative samples for training.
- print weights per layer during training
- Performance issue in src/eval.py (by P3) HOT 1
- The loss plateaus after 100 Epoch
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 squeezedet.