Vishal Thengane

icon indicating a website link https://vgthengane.github.io

icon company University of Surrey, UK; University of Wollongong, Australia icon location Earth icon location PhD Student | Continual Learning | Multimodal Models | 3D Vision

Results 4 comments of Vishal Thengane

No feature to add custom metric (mAP) for model training

Hi folks, Any updates on this?

ResNet-18 parameters are much much higher

Have a look at this https://pytorch-tutorial.readthedocs.io/en/latest/tutorial/chapter03_intermediate/3_2_2_cnn_resnet_cifar10/. It uses the same configuration as mentioned in the [Deep Residual Learning for Image Recognition](https://arxiv.org/pdf/1512.03385.pdf).

How to get the mean Average Performance (mAP) in Segmentation models?

Can I also integrate the mAP metric to `keras.compile()` to get mAP while training?

MinkowskiConvolutionFunction cannot support multi-gpu?

Has anyone solved this?