-
1.Linux
Ubuntu 18.04
gcc/g++ 7.4.0
pytorch 1.3.1
python 3.7
cuda 10.1
2.Issue description
When I try
`- CUDA_VISIBLE_DEVICES=0 python trainval_net.py --dataset pascal_voc --net vgg16 --bs=4…
-
[paper](https://arxiv.org/pdf/2006.07733.pdf), [code](https://github.com/deepmind/deepmind-research/tree/master/byol)
## Introduction
Bootstrap* Your Own Latent(BYOL)은 online network, target …
-
Hello~ Thanks for the nice work and code. I was trying to reproduce the (image/pixel) auroc for ResNet50 and ResNet101, which are (92.4/96) and (92.2/95.9) in the paper, respectively. However, with th…
-
Hey Hi!
We would like to submit our CombOOD results to the OpenOOD Leaderboard.
Here's the link to my paper (https://epubs.siam.org/doi/abs/10.1137/1.9781611978032.74),
and the GitHub repos…
-
I'm trying to trace the model to use it later in c++ code by `torch::jit::load()`, but getting an error.
Before running the tracing I modified the backbone.py and efficientdet/model.py like in #111 …
-
Hi Guys
@huzecong @ezyang @gqchen @albanD
Is there a way we could get hold of Backward Graph in C++ code .
We have a custom FPGA and asic & we would like to perform training on a multi-chips HW…
-
首先是运行test_BadNets.py得到中毒的预训练模型（ResNet-18_CIFAR-10_BadNets_2024-08-19/ckpt_epoch_170.pth）
结果如下：
==========Test result on benign test dataset==========
[2024-08-19_23:07:20] Top-1 correct / Total: 87…
-
My data has 4 classes(not include background), i used the configs is solov2_r50_fpn_8gpu_3x.py, i didn't change the dufault params, but i get the bad results!
![index](https://user-images.githubuserc…
-
I'm not sure if this was by design, or just the way it worked out, but Objax forges in own path for many parameter/variable, state naming/order conventions, default arguments etc.
While it may see…
-
I want to use the npy2ckpt.py to transfer my own resnet50 pre-train model:
the layer name in my pre-train resnet50 model are:
bn4c_branch2c
bn5b_branch2b
res3d_branch2b
res2b_branch2b
…
y-kl8 updated
6 years ago