Zesen Chen
Zesen Chen
> No, it doesn't support multi-GPUs. I think multi-GPUs can help improve efficiency, especially when performing cross-validation or multi-class SVMs. Hello，zeyiwen. I have a question that if 0-th GPU has...
I got it that I made a silly mistake. The probability index is different from sklearn.svm.SVC. Probability index of sklearn's SVC is [0 probability, 1 probability]. Probability of thundersvm.SVC is...
如果你配好了CUDA和CUDNN，那可以只要改一下mask_rcnn_v7.py里面的训练样本和测试样本的路径然后直接运行。
另外可以看看train_shapes.ipynb这个demon，里面是系统随机生成各种形状的样本进行简单的训练，没GPU也能跑。可以帮助理解mask-rcnn的使用。
那个没什么用，是之前的版本，可以删掉。主要是gsample.py和mask_rcnn.py。gsample是读图像的，mask_rcnn_v7是做模型接口的，包括参数设置和样本传入。