-
I am trying to train and test on a dataset that was converted to COCO format. The class number in the JSON annotation file matches that of the original label files. e.g. 0 is Traffic light and 2 is ca…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues
### Bug description
This is separate from [Issue 2639](https://github.com/DeepLabCut/DeepLabCut/issues/2639) as it…
-
when I train the model using"bash tools/dist_train_partially,sh semi 1 10 2", there is a problem. Can you help me？
Traceback (most recent call last):
File "tools/train.py", line 200, in
main…
-
Hi all,
I have a question regarding the configuration of SSD.
An interesting task for me is to fine-tuning the SSD_mobilenet_v1_coco_2017_11_17 with [Bosch small traffic light dataset](https://hci…
-
Hi,
while customizing and training a Faster-RCNN object detection model based on `torchvision.models.detection.faster_rcnn`, I've noticed that the pre-trained model of type `fasterrcnn_resnet50_fpn_v…
-
在configs/datasets下设置了 allow_empty: True 进行faster_rcnn模型的无标签学习，batch_size只能设为1，尝试大的batch_size提示显存不够，但是设为1时，
Test mode: `inference` and `training`
Test datatype: `amp_bf16` `amp_fp16` `float32`
#### This …
-
### Summary
Hi, trying to install TorchBench with python 3.10 with the command `python install.py` results in an error & the installation fails.
However, using `python install.py --continue_on_fail…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues
### Bug description
My training dataset consists of 338 images with 1-10 mice, 6 bodyparts were annotated.
…
-
环境是用dockerfile 构建的，应该没问题。
我要训练faster-rcnn模型，这是我的数据目录，
```
my_faster_rcnn_data/
├── train
……
│ ├── aafa46eb-99b9-499f-ad82-6c23270cc923.jpg
│ ├── aafa46eb-99b9-499f-ad82-6c23270cc923.tx…