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.
I faced the same issue in training with mobilenetv3. I just get rid off the part that indicates the pre-trained model. The comment should like this
"python train_ssd.py --datasets D:\pytorch-ssd\voc_v1 --validation_dataset D:\pytorch-ssd\voc_v1 --net mb3-large-ssd-lite --scheduler multi-step --milestone 40,60 --lr 0.01 --t_max 100 --batch_size 36 --num_epochs 100 --base_net_lr 0.001"
I faced the same issue in training with mobilenetv3. I just get rid off the part that indicates the pre-trained model. The comment should like this "python train_ssd.py --datasets D:\pytorch-ssd\voc_v1 --validation_dataset D:\pytorch-ssd\voc_v1 --net mb3-large-ssd-lite --scheduler multi-step --milestone 40,60 --lr 0.01 --t_max 100 --batch_size 36 --num_epochs 100 --base_net_lr 0.001"