hypercost

@Lupin1998 Thanks for your work. I tried to find the self-supervised pre-training weight of a2mim without finetune. Does [full_a2mim_r50_l3_sz224_init_8xb256_cos_ep100](https://github.com/Westlake-AI/openmixup/releases/download/a2mim-in1k-weights/full_a2mim_r50_l3_sz224_init_8xb256_cos_ep100.pth) stand for that?

Hi, @xvbw , Did you run the training with cuDNN support? Further, If you work with cuDNN, which cuDNN version did you use? I have successfully compile the caffe with...

I figured out this problem. I compile the caffe use CMake. The `CMakeLists.txt` originally is: ``` set(CUDA_NVCC_FLAGS ${CUDA_NVCC_FLAGS} -gencode arch=compute_20,code=sm_20 -gencode arch=compute_20,code=sm_21 -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 ) ``` I added...

@xvbw Yes, I use a Titan X and I changed the FLAG to compute_50. By the way, it trained successfully in VOC2012 original dataset. But in the augmented VOC dataset,...

@xvbw ``` I1220 16:00:51.012964 8727 caffe.cpp:118] Finetuning from /media/ksnzh/DATA/deeplab/train- DeepLab/exper/voc12/model/DeepLab-LargeFOV/train_iter_6000.caffemodel E1220 16:00:51.019429 8755 io.cpp:76] Could not open or find file /media/ksnzh/DATA/deepla b/train-DeepLab/exper/voc12/data/images_aug/2007_006560.jpg I1220 16:00:51.019639 8755 image_seg_data_layer.cpp:180] Fail to load img:...

@xvbw It means that augmented VOC is the union of the downloaded benchmark and original voc2012?

Hi @ruida , I have compiled caffe successfully with cmake too and also encounter the same issue when `make runtest`. ``` /media/ksnzh/DATA/deeplab/train-DeepLab/code/src/caffe/test/test_memory_data_layer.cpp:97:3: note: candidate is: In file included from /media/ksnzh/DATA/deeplab/train-DeepLab/code/src/caffe/test/test_memory_data_layer.cpp:4:0:...

Same question. Will you release the code for train data generation?

Graphdeco-inria has adopted 3dgs_accel or taming-gs rasterizer implementation in this [branch ](https://github.com/graphdeco-inria/diff-gaussian-rasterization/tree/3dgs_accel). Can these idea be integrated into gsplat for further accelerating. https://github.com/humansensinglab/taming-3dgs/blob/main/submodules/diff-gaussian-rasterization/cuda_rasterizer/forward.cu#L349 https://github.com/humansensinglab/taming-3dgs/blob/main/submodules/diff-gaussian-rasterization/cuda_rasterizer/backward.cu#L404

Same error. ``` AttributeError: 'SimulationCfg' object has no attribute 'render' ```