-
## ❔Question
Hi, I'm training my own dataset for object detection from drone's videos. When I test my video using my trained model I'm getting very low mAP: mAP@.5 0.213 mAP@.5:.95 0.0397 but the…
-
When setting up to run Bert-99 I get the no scripts for the version v4.1 the pytorch install.
INFO:root: * cm run script "get cuda _cudnn"
INFO:root: ! load /root/CM/repos/local/cac…
-
# Abstract
기존의 transformer 성공 뒤에는 attention-based token mixer module이 성능에 가장 많이 기여…
-
Hi,
How can I read/align/prepare face for making predict on trained model?
I made code like this:
```python
model = create_deepface()
model.load_weights('VGGFace2_DeepFace_weights_val…
-
## Instructions To Reproduce the 🐛 Bug:
1. Full changes I have made:
```
def setup(args):
"""
Create configs and perform basic setups.
"""
cfg = get_cfg()
args.config_file …
-
[Onnx Doc](https://onnx.ai/onnx/operators/onnx__NonMaxSuppression.html#l-onnx-doc-nonmaxsuppression)
Found in this model retinanet_resnet50_fpn_vaiq_int8 https://github.com/nod-ai/SHARK-TestSuite/i…
-
您好，请问一下，论文和代码中提到是将同一层的两个检测头数据中取loss较小的那个（min操作），不会造成一个头loss很大一个很小吗？
-
Hi，I get some problems during the reproduction of the results of "cityscapes" to "foggy cityscapes".
During my reproduction, I caught an error as below:
 File "", line 6, in concatenate