Cat
Cat
For example, Memory and inference time.
Hello, I tested the code on many GCC version + many Pytorch version + many CUDA versions, but they all do not work. Here is the error on CUDA11.0+Pytorch1.4+GCC7.5. ```...
I met the following problem: ``` (base) -bash-4.2$ cd inplace_abn (base) -bash-4.2$ ls CODE_OF_CONDUCT.md CONTRIBUTING.md equation.svg include inplace_abn inplace_abn.png LICENSE licenses.csv MANIFEST.in README.md requirements.txt scripts setup.cfg setup.py src (base) -bash-4.2$...
Hello, we have sent you several emails before asking about this problem. We first try to use 10% training set for training and 2.5% training set for validation and use...
Hello. I first run the command `python sh/bld.py local`, the `sh/dir.json` file is set as: ``` { "local": { "bld_dir": "dataset_low_res", "dtu_dir": "", "tnt_dir": "tankandtemples", "tnt_training_dir": "", "save_dir": "save", "batch_size":...
Hello, I am writing a instance segmentation network and I adopt a SSD head as the detection head. If I want to adopt CIOU/DIOU, how should I modify my code...
Hello, It seems the paper only shows the 3D mesh quality. Is it possible to release some 2D semantic maps? By the way, how should we obtain the 2D semantic...
Hello, should I use what kind of hyper-paramter for the first try? For example, learning rate, AdamW or Madgrad?
I am training a Instance Segmentation network, before I adopt WS, I can achieve mAP 35.66 with Conv+GN, however after adopting WS, I can only achieve 35.27. Is there something...