Shai
Hi, Can you share the code/parameters used to generate the different distortions in the dataset? Thanks!
Hi, I took the liberty of submitting the resnet pre-trained model results on VOC2012 TEST to the evaluation server. These are the results on the TEST set: Competition | Category...
I'm trying to train an inpainting model using multiple GPUs. Initial training worked fine, progressed well and saved checkpoints to `experiments/.../checkpoint` folder. However, when I try to resume the same...
n function (`Objecness.cpp:624`) ``` Mat Objectness::trainSVM(const vector &pX1f, const vector &nX1f, int sT, double C, double bias, double eps, int maxTrainNum) ``` If too many positive samples are supplied, `numP`...
When representing the optimized image using CPPN network, current implementation allows for optimizing for a single image per run. This limitation prevents using, e.g., "diversity" objectives during optimization. This PR...
I am trying to use Lucent to visualize deep neurons, but whatever I do it seems like GPU is under-utilized: Examining utilization via `nvidia-smi` I see low utilization (~10%) with...
### Bug description When running multi-node/multi-GPU training with different number of GPUs on each node, `Fabric` `ddp` and `fsdp` will have an incorrect `num_replicas` in `distributed_sampler_kwargs`: Currently `num_replicas` is set...