Comments (5)
Thanks @jinfagang . I had a brief look at your implementation. They are very impressive! I am happy to integrate. Have you got some benchmark results of your MobileNetv2 or SSD models? So we can quickly get started.
Btw, there is a hacky mobilenetV2 SSD Lite impl https://github.com/qfgaohao/pytorch-ssd/blob/squeezenet-ssd-lite/vision/ssd/mobilenet_v2_ssd_lite.py . The problem I am facing is that ONNX doesn't support Relu6 used in Mobilenetv2. I replaced it with Relu. Currently I am training MobileNetv2 Imagenet Models.
I assume the ONNX Relu6 problem will resolve over time.
from pytorch-ssd.
@qfgaohao That is the question, I just borrowed some codes from others, change it into pytorch 0.41 fully supported, but after I test it, just not got any results (seems the whole process of SSD was broken).
But the backends that MobilenetV2 works fine.
theoretically, mobilenetv2 should be faster than mobilenetv1 backend, at least should be more accurate.
Now that you already training MobileNetV2 on imagenet, I can help you training on other datasets.
I think ReLu6 should not be the problem, if ONNX not support it now, we can just skip it at now time, hopefully ONNX will support it in the near future
from pytorch-ssd.
Hi @jinfagang you are right, we can safely skip Relu6. I will merge the code next week. I will let you how it goes.
from pytorch-ssd.
@qfgaohao Sounds great! Waiting for you response!
from pytorch-ssd.
@jinfagang Sorry for the delay. I was occupied by an urgent project. Plz see the trained MobleNetV2 SSD-Lite model with mp 0.686. https://storage.googleapis.com/models-hao/mb2-ssd-lite-mp-0_686.pth .
I have merged the code into the master branch. Here is code is reproduce the model.
wget -P models https://storage.googleapis.com/models-hao/mb2-imagenet-71_8.pth
python train_ssd.py --dataset_type voc --datasets ~/data/VOC0712/VOC2007 ~/data/VOC0712/VOC2012 --validation_dataset ~/data/VOC0712/test/VOC2007/ --net mb2-ssd-lite --base_net models/mb2-imagenet-71_8.pth --scheduler cosine --lr 0.01 --t_max 200 --validation_epochs 5 --num_epochs 20
I haven't got a MobileNetV2 with Relu base net having a reasonable accuracy. So the above model is based on the original MobileNetV2. The pre-trained base net is from https://github.com/tonylins/pytorch-mobilenet-v2
from pytorch-ssd.
Related Issues (20)
- Training doesn't start - I'm getting an error with the data loader HOT 4
- convert_to_caffe2_models.py: RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! HOT 2
- SSDSpec for image size smaller than 300 HOT 1
- Re-training SSD-Mobilenet - loss going up and down
- Error using run_ssd_live_demo.py HOT 1
- [Question] what these parameters mean? HOT 2
- base net for mobilenetv3 ssd HOT 1
- ssd-mobilenet to tensorrt
- pytorch模型量化时报错
- Mobilnet-ssdv2 HOT 1
- NAN values in Boxes HOT 1
- How can I train the model without pre-trained weight specified? HOT 1
- runtime error mobillenet-ssd-v2 HOT 5
- run_ssd_example.py box variable type does not mach opencv rectangle and putText functions
- FileNotFoundError: [Errno 2] No such file or directory: 'models/mobilenet_v1_with_relu_69_5.pth'
- cv2.error: OpenCV(4.5.5) : -1 : error: (-5:Bad argument) in function 'rectangle' HOT 1
- Could u add Nesterov momentum in SGD
- 4xgx
- RuntimeError: The size of tensor a (12828) must match the size of tensor b (3000) at non-singleton dimension 1 HOT 3
- ValueError encountered during retraining on Open Images Dataset HOT 1
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 pytorch-ssd.