-
**Description**
A clear and concise description of what the bug is.
Cannot load FasterRCNN model exported to TorchScript using Triton r20.03.
**Triton Information**
What version of Triton are …
-
I am trying to train a new model on my own dataset which is converted to coco style by following the steps in the tutorial2.
I added a new config file called 'faster_rcnn_r50_fpn_1x_coco.py', the con…
-
When I train Detectors using my custom dataset(COCO format), config file detectors_cascade_rcnn_r50_1x_coco.py,
loss_rpn_bbox is 0 in firtst step.
logs:
2020-07-20 17:31:41,512 - mmdet - INFO - E…
-
## 🚀 Feature
- It would be hard for end-user to understand where to implement custom architectures and backbones. They require same training code as there is a change in backbone which is feature e…
-
I would like to you the to use the following with `fasterrcnn_resnet50_fpn`:
```python
AnchorGenerator(sizes=((128, 256, 512),),
aspect_ratios=((2, 1.0, 0.5),))
```
But I get …
-
I trained my dataset for several times on training set using pretrained weights, but there are no values in validation outputs. `[{'boxes': tensor([], device='cuda:0', size=(0, 4), grad_fn=), 'labels'…
-
这是配置
faster_reader.yml
TrainReader:
inputs_def:
fields: ['image', 'im_info', 'im_id', 'gt_bbox', 'gt_class', 'is_crowd']
dataset:
!COCODataSet
image_dir: train2017
anno_pat…
-
/kind bug
**Describe the Bug:**
After following the installation instructions in the contributing guide (https://github.com/Unity-Technologies/datasetinsights/blob/master/CONTRIBUTING.md) I hi…
-
打印信息：
The 'num_classes'(number of classes) you set is 29, and 'with_background' in 'dataset' sets False.
So please note the actual number of categories is 29.
config文件中设置：
metric: VOC
num_clas…
-
Hello, thank you for sharing. I want to ask you if you test the configuration file settings of faster RCNN to add Pconv, as shown below.
model = dict(
type='FasterRCNN',
pretrained='torchvi…