gobears21

once created the docker container, can i directly train the model? or should i starting with env build up (such conda install, python setup.py build ..etc.)?

=> ERROR [6/6] RUN pip install --no-cache-dir -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ && pip install --no-cache-dir -e . 203.8s ------ > [6/6] RUN pip install --no-cache-dir -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ &&...

Command 'apex' not found

1

when i try with `cd && apex && pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./` it shows `Command 'apex' not found `

AssertionError when trying to reproduce result

2

When I trying to reproduce the result, using following command: `python train_net.py --dist-url 'tcp://127.0.0.1:50163' --num-gpus 2 --config-file configs/coco/swin/oneformer_swin_tiny_bs16_50ep.yaml OUTPUT_DIR outputs/coco_swin_tiny WANDB.NAME coco_swin_tiny ` I got a missing file error :...

this dataset seems not available to download