运行 create_voc_roidb.py
报错 No such file or directory: 'data/label_map/voc_label_map.json'
解决方法:https://github.com/TuSimple/simpledet/issues/282
运行:python detection_train.py --config config/faster_r50v1_fpn_1x.py
报错:Check failed: e == cudaSuccess || e == cudaErrorCudartUnloading CUDA: invalid device ordinal #15
解决方法:https://github.com/TuSimple/simpledet/issues/15
修改gpus和 loader_worker
class KvstoreParam:
kvstore = "local"
batch_image = General.batch_image
gpus = [0, 1, 2, 3, 4, 5, 6, 7]
fp16 = General.fp16
训练自己的数据集
运行
python detection_train.py --config config/faster_r50v1_fpn_1x.py
报错:断言失败,显示image_url不存在
assert os.path.exists(image_url)
解决办法:
filename = root.find("filename").text 改为 filename = root.find("filename").text+'.jpg'
成功运行
10-27 19:13:49 Epoch[5] Batch [690] Iter: 4170/4176 Lr: 0.00250 Speed: 2.36 samples/sec Train-RpnAcc=0.999308, RpnL1=0.153242, RcnnAcc=0.990205, RcnnL1=0.548991,
10-27 19:13:52 Epoch[5] Train-RpnAcc=0.999307
10-27 19:13:52 Epoch[5] Train-RpnL1=0.152955
10-27 19:13:52 Epoch[5] Train-RcnnAcc=0.990232
10-27 19:13:52 Epoch[5] Train-RcnnL1=0.548295
10-27 19:13:52 Epoch[5] Time cost=462.154
10-27 19:13:53 Saved checkpoint to "experiments/faster_r50v1_fpn_1x/checkpoint-0006.params"
10-27 19:13:53 Training has done
10-27 19:14:03 Exiting
其中
10-27 19:13:52 Epoch[5] Train-RpnAcc=0.999307
10-27 19:13:52 Epoch[5] Train-RpnL1=0.152955
10-27 19:13:52 Epoch[5] Train-RcnnAcc=0.990232
10-27 19:13:52 Epoch[5] Train-RcnnL1=0.548295