Dataset for MobileNetV2 SSD-Lite

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 529 forks source link

Dataset for MobileNetV2 SSD-Lite #164

Open ashg1910 opened 2 years ago

ashg1910 commented 2 years ago

Hi,

The results obtained for MV2 SSD-Lite are specified as- Average Precision Across All Classes:0.6860690100560214

On which set of images was the model run to get this result? Is it the complete 4952 images in VOC2007 test set? Please clarify.

ashg1910 commented 2 years ago

@qfgaohao could you please help?

Lucky2593 commented 2 years ago

Hi, The model is trained on both the datasets(VOC 07+12), training on VOC07+VOC12, validation on VOC07.

The dataset size when I trained the model using VOC(07+12). Train dataset size: 16551 Validation dataset size: 4952

Hope it will help!.