-
I implement in pytorch and follow your settings and get 61.9 auc on shanghaitech, using only rgb. can you show your auc of it?
If I use three-stream, training of svm will terminate because of excess…
-
How can I see the proceeding status (validation) during training?
I added `workflow = [('train, 1), ('val', 1)]` to config file and executed `python tools/train.py configs/faster_rcnn_r50_fpn_1x.py…
-
I am trying to finetune single class object detection model without segmentation (just predict boxes/scores). I was following [this tutorial](https://pytorch.org/tutorials/intermediate/torchvision_tut…
-
The link `https://pytorch.org/docs/stable/_modules/torchvision/models/detection/faster_rcnn.html#fasterrcnn_resnet50_fpn`, specifically at `https://pytorch.org/docs/stable/torchvision/models.html#fast…
-
## 🐛 Bug
Retraining the 'fasterrcnn_resnet50_fpn ' model for custom dataset is failing
## To Reproduce
Steps to reproduce the behavior:
1. Successfully ran the [sample ](https://pytorch…
-
I am training Faster-RCNN for ms-coco 2017. I am running the command as shown in title. But I am getting the following error:
```
2019-12-12 13:53:50,181 - INFO - Distributed training: False …
-
## 🐛 Bug
Retraining the 'fasterrcnn_resnet50_fpn ' model for custom dataset is failing
## To Reproduce
Steps to reproduce the behavior:
1. Successfully ran the [sample ](https://pytorch…
-
the default parameter, as well as the COCO pretrained .pth that it pulls from use num_classes=91. while COCO does indeed have 91 classes, other issue tickets as well as the code demand that num_class…
-
I am doing a object detection task and I fine-tune the fasterrcnn_resnet50_fpn model on my own dataset。
```
GPU: a GTX1080ti
Memory: 11178MiB
```
But when I train, I have to set the batchsize to…
-
When I start to train faster-rcnn-r50 on my own dataset, there's a problem I cannot figure out.
I defined my own data set type and initialized it.
```python
from .registry import DATASETS
from …