sounansu

"CUDA out of memory." at training.

8

Hi! I try to train with this command.(At my windows PC with RTX2070) ``` F:\Users\sounansu\Anaconda3\FCHarDNet>\python train.py --config configs\hardnet.yml ..... RuntimeError: CUDA out of memory. Tried to allocate 40.00 MiB (GPU...

I try to resume from checkpoint data, as blow. ``` python train_mvod_basenet.py --datasets ./ILSVRC --cache_path ./ --batch_size 60 --num_epochs 30 --width_mult 1 --resume models/basenet/WM-1.0-Epoch-15-Loss-111.27649793882628.pth ``` But, I can not restart...

I try to use pruned yolov3.cfg and weights data. It occurred CUDNN_STATUS_BAD_PARAM error as below. ``` darknet detector test cfg/coco.names cfg/yolov3prune.cfg backup/yolov3prune_last.weights -thresh 0.10 data/eagle.jpg -quantized ........ CUDNN failure Error:...

I can not test.

2

Hi. I tried to train by Make train command. But, I can not finished training. as below ``` Traceback (most recent call last): File "/home/sounansu/anaconda3/envs/tiny-yolo-tensorflow/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1350, in _do_call return...

GTX1060の6GBでTrainingしようとして、メモリが足りない的なメッセージが出たのですが、 leetenkiさんがお使いのGPUは何なのでしょうか？ 参考までにお教え願えないでしょうか？

When i compiled at Windows using Visual Studio 2017, C4703 error was occurred. So, I modified prune.cpp as below. ``` diff --git a/src/prune.cpp b/src/prune.cpp index 6ccf919..1efcff0 100644 --- a/src/prune.cpp +++...