About the train speed

[ztyxd]

I use this code to train my own dataset, I used to use the facebook maskrcnn-benchmark and the speed is about 20 ours when traning 180000 iteration, but in this code , i train the rrpn with

`MODEL: META_ARCHITECTURE: "RRPN" WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" RPN: PRE_NMS_TOP_N_TEST: 6000 POST_NMS_TOP_N_TEST: 1000 RPN_HEAD: "SingleConvRRPNHead"

ROI_BOX_HEAD: NUM_CLASSES: 11 ROI_HEADS: BATCH_SIZE_PER_IMAGE: 256

DATASETS: TRAIN: ("RRPN_train", ) SOLVER: BASE_LR: 0.005 WEIGHT_DECAY: 0.0001 STEPS: (50000, 100000) MAX_ITER: 150000 IMS_PER_BATCH: 2

OUTPUT_DIR: './models/XXX`

It shows that it use smore than 2 days to finish the training phase

Is there something i ignored in the code or can U give me your training speed

Thanks a lot

[mjq11302010044]

@ztyxd I notice that your training batch is 2, while we use 1 in original training phase.

[ztyxd]

I will try， thanks a lot