From 01b80e8433d61965481b46d527f3312feb2617ce Mon Sep 17 00:00:00 2001 From: Zhi Tian Date: Wed, 11 Sep 2019 17:23:27 +0930 Subject: [PATCH] fixed training command line --- README.md | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 6c84b50..2e6d22d 100644 --- a/README.md +++ b/README.md @@ -118,10 +118,9 @@ The following command line will train FCOS_R_50_FPN_1x on 8 GPUs with Synchronou --nproc_per_node=8 \ --master_port=$((RANDOM + 10000)) \ tools/train_net.py \ - --skip-test \ - --config-file configs/fcos/fcos_R_50_FPN_1x.yaml \ + --config-file configs/fcos/fcos_imprv_R_50_FPN_1x.yaml \ DATALOADER.NUM_WORKERS 2 \ - OUTPUT_DIR training_dir/fcos_R_50_FPN_1x + OUTPUT_DIR training_dir/fcos_imprv_R_50_FPN_1x Note that: 1) If you want to use fewer GPUs, please change `--nproc_per_node` to the number of GPUs. No other settings need to be changed. The total batch size does not depends on `nproc_per_node`. If you want to change the total batch size, please change `SOLVER.IMS_PER_BATCH` in [configs/fcos/fcos_R_50_FPN_1x.yaml](configs/fcos/fcos_R_50_FPN_1x.yaml). -- GitLab