search

qfgaohao / pytorch-ssd

MobileNetV1, MobileNetV2, VGG based SSD/SSD-lite implementation in Pytorch 1.0 / Pytorch 0.4. Out-of-box support for retraining on Open Images dataset. ONNX and Caffe2 support. Experiment Ideas like CoordConv.
https://medium.com/@smallfishbigsea/understand-ssd-and-implement-your-own-caa3232cd6ad
MIT License
1.39k stars 530 forks source link

Run ssd_sample.py with mb2-ssd-lite ERROR #20

Closed ZLeopard closed 5 years ago

ZLeopard commented 5 years ago

there‘s a little bug in the code. when i run the file to test a image with the mobilenetv2-ssdlite, got a TensorType ERROR, So i change the default params of "create_mobilenetv2_ssd_lite_predictor" in the file mobilenet_v2_ssd_lite.py . by set the device as None

def create_mobilenetv2_ssd_lite_predictor(net, candidate_size=200, nms_method=None, sigma=0.5, device=None):

Any better suggestion? i learn a lot from your code, thank you a lot. 太感谢啦~~

ZLeopard commented 5 years ago

I will try to train the shufflenetv2 using this code, if got some result, I will tell you~~your code is amazing, thanks again!

qfgaohao commented 5 years ago

@ZLeopard That's good. None is better. Looking forward to your shufflenetv2 implementation. Happy coding!

hahanigehaha233 commented 5 years ago

You should make a MR.