chowkamlee81

Error in libcaffe_test.a(hdf5_reader.cpp.o): In function `hdf5_reader::hdf5_reader?

1

After builing evaluator got an error below: Kindly help 100%] Linking CXX executable caffe_test_ex libcaffe_test.a(hdf5_reader.cpp.o): In function `hdf5_reader::hdf5_reader(boost::filesystem::path, std::__cxx11::basic_string const&)': hdf5_reader.cpp:(.text+0x218e): undefined reference to `caffe::GetEmptyStringAlreadyInited[abi:cxx11]()' collect2: error: ld returned 1...

I want to work on my dataset captured from car environment, kindly suggest how to write data in mdb format. Kindly do the needul....

net.load_checkpoint(epoch=args.load_epoch) fails?

2

while excecuting python evaluate_video_ucf101_split1.py File "evaluate_video_ucf101_split1.py", line 107, in net.load_checkpoint(epoch=args.load_epoch) File "../train/model.py", line 62, in load_checkpoint assert os.path.exists(load_path), "Failed to load: {} (file not exist)".format(load_path) AssertionError: Failed to load: ./../exps/_ep-0000.pth...

hai since i don't have GPU capacity in my laptop, iam unable to train. Hence kindly provide some pretrained model which will be helpful

How you have designed anchors using https://github.com/wl5/complex_yolo_3d/blob/e82ed9701c84b0f07f32e6896e53b58ce863e944/utils.py#L232

Error on untimeError: Expected attn_mask dtype to be bool or to match query dtype, but got attn_mask.dtype: float and query.dtype: c10::BFloat16 instead.

1

After giving python scripts/txt2img.py --prompt "a professional photograph of an astronaut riding a horse" --ckpt model_files/v2-1_768-ema-pruned.ckpt --config configs/stable-diffusion/v2-inference-v.yaml --H 768 --W 768 iam getting error below: Creating invisible watermark encoder...

torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 9.49 GiB. GPU 0 has a total capacty of 23.68 GiB of which 8.03 GiB is free. Including non-PyTorch memory, this process has 15.17 GiB memory in use. Of the allocated memory 14.73 GiB is allocated by PyTorch, and 133.53 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting max_split_size_mb to avoid fragmentation. See documentation for Memory Management and PYTORCH_CUDA_ALLOC_CONF

2

when i ran python scripts/txt2img.py --prompt "a professional photograph of an astronaut riding a horse" --ckpt model_files/v2-1_768-ema-pruned.ckpt --config configs/stable-diffusion/v2-inference-v.yaml --H 768 --W 768, it is giving out-of-memory error. I had...

Kindly tell me the procedure to train and test? What are the pretrained models used... Kindly specify

Accuracy on Nuscene dataset

3

Would like to know accuracy on trained with Nuscene dataset? Is it trained for sweeps=1 or sweeps=10. Kindly help

Runtime tensorRT model?

1

Hi, Thanks for your useful code. Do you have tensorRT model so that i can check on inference part. Regards K S Chidanand Kumar