LauncH comments

Results 21 comments of


                                            LauncH

Syncing with the implementation of official repo

Yes, it is 256 https://github.com/d-li14/efficientnetv2.pytorch/blob/775326e6c16bfc863e9b8400eca7d723dbfeb06e/effnetv2.py#L179 the c column indicates the output of efficientnetv2-s backbone (before the last layer conv-avgpool-linear) is 256. Or you can put the code in your program...

which config file is used?

You need not change the num_workers, I try 1 Tesla V32gpu 4Tesla V32 gpu and 8 Tesla V32 gpu training and keep the num_workers=4. Just wait. The first time to...

which config file is used?

> Hello, I'm sorry the server is running other programs in the past few days. I cannot demonstrate the problem I saw it that night after you responded to me...

which config file is used?

> > Hello, I'm sorry the server is running other programs in the past few days. I cannot demonstrate the problem I saw it that night after you responded to...

which config file is used?

> 不好意思我可能没有表述清楚，我是通过邮件发送的，附件在邮件里，我在issue重新说明一下。 > > 1.GPU使用情况 > log.txt说明如下： > 2020-09-01 21:52:38,942 mega_core INFO: Using 1 GPUs > 2020-09-01 21:52:38,942 mega_core INFO: Namespace(config_file='configs/MEGA/vid_R_101_C4_MEGA_1x.yaml', distributed=False, launcher='pytorch', local_rank=0, master_port='27341', motion_specific=True, opts=['OUTPUT_DIR', 'training_dir/MEGA_R_101_1x'], save_name='', skip_test=False)...

which config file is used?

> 跑成功啦，就是acc不太行，你是哪里报错啦 > […](#) > On Wed, Jan 27, 2021 at 04:04 zhanghaoo ***@***.***> wrote: 我又回来了，这阵子忙完了要继续做这个了。 @ZhijunHou @liwenjielongren 兄弟们你们都跑成功了吗？ — You are receiving this because you were mentioned. Reply to...

which config file is used?

> > > 跑成功啦，就是acc不太行，你是哪里报错啦 > > > […](#) > > > On Wed, Jan 27, 2021 at 04:04 zhanghaoo _**@**_.***> wrote: 我又回来了，这阵子忙完了要继续做这个了。 @ZhijunHou https://github.com/ZhijunHou @liwenjielongren https://github.com/liwenjielongren 兄弟们你们都跑成功了吗？ — You are...

which config file is used?

Excuse me, why can I only run one img on one GPU?

比如说你用4个gpu,mega.pytorch/configs/BASE_RCNN_4gpu.yaml solver和test 的ims_per_batch是4 如果你用8个gpu或者更多。把上述两个参数改成对应的8或其他 SOLVER: BASE_LR: 0.001 WEIGHT_DECAY: 0.0001 STEPS: (80000, ) MAX_ITER: 120000 **IMS_PER_BATCH: 4** WARMUP_ITERS: 500 TEST: **IMS_PER_BATCH: 4** DETECTIONS_PER_IMG: 300

Excuse me, why can I only run one img on one GPU?

> > 比如说你用4个gpu,mega.pytorch/configs/BASE_RCNN_4gpu.yaml solver和test 的ims_per_batch是4 > > 如果你用8个gpu或者更多。把上述两个参数改成对应的8或其他 > > SOLVER: > > BASE_LR: 0.001 > > WEIGHT_DECAY: 0.0001 > > STEPS: (80000, ) > > MAX_ITER: 120000 > >...