-
Hi, everyone.
When I run the command "CUDA_VISIBLE_DEVICES=2,3 python tools/train.py configs/dcn/cascade_rcnn_dconv_c3-c5_r50_fpn_1x.py --gpus 2", I get the error as below:
(openmmlab) wangqing…
-
Hi, sir. I use the cascade_rcnn_r101_fpn to train my dataset and use the trained detector to do track task. I trained the detector twice, and keep the config the same and didn't change the tracker, th…
-
Here is my config. I want to train an object detector with 7 classes.
```
Config:
dataset_type = 'COCODataset'
data_root = ''
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.…
-
Hi Everyone.
I want to train only 1 class i.e person out of all classes in COCO dataset. I have made changes to config files like below:
Is this correct that it will load only person class ? also,…
-
how to test the SP-NAS mAP on COCO with vega
-
Hello, I want train cascade-rcnn with GIoU or DIoU loss to replace smooth L1 loss, here is my part of config file.
```python
model = dict(
type='CascadeRCNN',
num_stages=3,
pretraine…
-
python tools/train.py configs/st_bottle_models/cascade_models/cascade_rcnn_r50_caffe_fpn_mstrain_3x_diou_coco.py
2020-11-18 21:18:30,386 - mmdet - INFO - Environment info:
--------------------------…
-
When I use dist_train to train a model, I got an error like
from mmcv.ops import (ContextBlock, Conv2d, ConvTranspose2d, ConvWS2d,
ImportError: cannot import name 'ContextBlock'
And I have che…
-
Hi, I want train Cityscapes for longer and set total_epochs = 64 as flollows:
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=0.001,
step=[48, 60])
total_epochs…
-
Hi All,
I am facing issue with MOT16 dataset training, I have converted dataset to coco annotation and run training, but from first batch I am getting huge loss which seems is caused by low boundi…