just a dreamy guy
tranleanh / mobilenets-ssd-pytorch Goto Github PK
View Code? Open in Web Editor NEWMobileNets-SSD/SSDLite on VOC/BDD100K Datasets
MobileNets-SSD/SSDLite on VOC/BDD100K Datasets
Hello,
I have trained several models vgg16-ssd and mb1-ssd-lite. However when I try to run inference on single image and load the model I always get incorrect shapes and weight names. What could cause that?
Examples of incorrect shape and weight names when loading model checkpoints for vgg16-ssd:
Best regards,
Roberts
Thank you
Hi,
create_mobilenetv2_ssd_lite has a problem when using label map of 11 element.
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
[<ipython-input-18-eff74db7755d>](https://localhost:8080/#) in <module>()
14 net = create_mobilenetv2_ssd_lite(11, is_test=1)
15
---> 16 net.load(model_path)
17
18 predictor = create_mobilenetv2_ssd_lite_predictor(net, candidate_size=200, nms_method="soft")
1 frames
[/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py](https://localhost:8080/#) in load_state_dict(self, state_dict, strict)
1481 if len(error_msgs) > 0:
1482 raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
-> 1483 self.__class__.__name__, "\n\t".join(error_msgs)))
1484 return _IncompatibleKeys(missing_keys, unexpected_keys)
1485
RuntimeError: Error(s) in loading state_dict for SSD:
size mismatch for classification_headers.0.3.weight: copying a param with shape torch.Size([126, 576, 1, 1]) from checkpoint, the shape in current model is torch.Size([66, 576, 1, 1]).
size mismatch for classification_headers.0.3.bias: copying a param with shape torch.Size([126]) from checkpoint, the shape in current model is torch.Size([66]).
size mismatch for classification_headers.1.3.weight: copying a param with shape torch.Size([126, 1280, 1, 1]) from checkpoint, the shape in current model is torch.Size([66, 1280, 1, 1]).
size mismatch for classification_headers.1.3.bias: copying a param with shape torch.Size([126]) from checkpoint, the shape in current model is torch.Size([66]).
size mismatch for classification_headers.2.3.weight: copying a param with shape torch.Size([126, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([66, 512, 1, 1]).
size mismatch for classification_headers.2.3.bias: copying a param with shape torch.Size([126]) from checkpoint, the shape in current model is torch.Size([66]).
size mismatch for classification_headers.3.3.weight: copying a param with shape torch.Size([126, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([66, 256, 1, 1]).
size mismatch for classification_headers.3.3.bias: copying a param with shape torch.Size([126]) from checkpoint, the shape in current model is torch.Size([66]).
size mismatch for classification_headers.4.3.weight: copying a param with shape torch.Size([126, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([66, 256, 1, 1]).
size mismatch for classification_headers.4.3.bias: copying a param with shape torch.Size([126]) from checkpoint, the shape in current model is torch.Size([66]).
size mismatch for classification_headers.5.weight: copying a param with shape torch.Size([126, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([66, 64, 1, 1]).
size mismatch for classification_headers.5.bias: copying a param with shape torch.Size([126]) from checkpoint, the shape in current model is torch.Size([66]).
Do you have an idea how to correct this ? thanks
Hi, thanks for the great repository!
I am a bit confused about the val and test datasets:
in the bdd100k folder, the images are split into train (70000) and val (10000).
Inside the bdd_files folder, there are text files indicating the following:
trainval.txt has 70000
test.txt has 10000
I would like to know if test.txt has the same 10000 images as ther val folder within bdd100k. If so, are the words validation dataset ad test set used interchangably and we dont provide any real test set (unseen)?
Do you have mAP index for mobilenetSSD when training mobilenetSSD?
Thank yor for sharing!
I train MobileNet-SSD (VOC),but I can't resume training. It always resumes training from epoch 0. What's the reason?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.