fcn (三)training cityscapes 學習紀錄
這一篇是想訓練cityscapes的資料庫, 紀錄訓練過程的一些小碰撞 1. 首先是 copy 了 voc-fcn32s/ 的檔案, . ├── infer.py ├── net.py ├── voc_layers.py ---> new add cityscapes_layers.py ├── score.py ├── snapshot ---> cteate snapshot/train ├── solve.py ├── solver.prototxt ├── surgery.py ├── train.prototxt └── val.prototxt 2. datasets cityscapes-dataset download grFine.zip and leftImg8bit.zip 6. Result 512x512 fcn32s mean acc. and mean IU 太低 >>> 2019-12-11 22:45:07.762072 Begin seg tests >>> 2019-12-11 22:45:41.055221 Iteration 100000 loss 126417.949921875 >>> 2019-12-11 22:45:41.055304 Iteration 100000 overall accuracy 0.602877947321908 >>> 2019-12-11 22:45:41.055342 Iteration 100000 mean accuracy 0.09731878508947552 >>> 2019-12-11 22:45:41.055503 Iteration 100000 mean IU 0.061253671561096214 >>> 2019-12-11 22:45:41.055591 Iteration 100000 fwavacc 0.3756002265727415 real 312m59.278s --> 5 hours user 251m9.625s sys 60m