busycalibrating
busycalibrating
Currently, the primary ResNet backbone uses a custom implementation that would not be directly compatible with the default PyTorch implementations (in addition to having a slightly different layer configuration). I...
I was wondering if there was any easy way to use a custom sampler (inheriting from `torch.utils.data.Sampler`)? At first glance it seems like I'd have to implement something that extends...
Hello! I'm trying play around with the stochastic Frank-Wolfe benchmarks you have in [this example](https://openopt.github.io/copt/auto_examples/frank_wolfe/plot_sfw_real_data.html#sphx-glr-download-auto-examples-frank-wolfe-plot-sfw-real-data-py) and I'm having trouble reproducing the figure by running the provided example. The expected results...