XiLu
XiLu
https://github.com/liuziwei7/voxel-flow/blob/e796773c4a93ab5b8bf9671f0dd11b6ecfc12007/voxel_flow_train.py#L189 I am wondering why is_train=True when testing model. I compared the results between when is_train=True and when is_train=False. Oddly, is_train=True produces the correct result when testing.
> python preprocess.py, resize image to 256256,384384,512512,640640,736*736, and train respectively could speed up training process. I am kinda confused the meaning of train respectively? Does this mean to train the...
Hi @TropComplique , Have you ever tried to quantize the model by Quantization-aware training? If so, how is the result? I am trying to create_training_graph in model.py [at line 72](https://github.com/TropComplique/FaceBoxes-tensorflow/blob/0dde35eda1cb3dab6586b94c583029162ec37aa5/model.py#L72)...
I am trying to evaluate my model on your SPMCS dataset. But I cannot find any details about this dataset in the paper or on GitHub. Could you please provide...