KAIWANG

[Draft] Support DAL model

4

Reproduce codes in mmrotate of DAL——《Dynamic Anchor Learning for Arbitrary-Oriented Object Detection》 paper: https://arxiv.org/abs/2012.04150 origin codes: https://github.com/ming71/DAL ## Motivation There are still some performance gaps with origin codes: 1. Performance...

ERROR - tf2onnx.tfonnx: Failed to convert node 'Mean'

2

When I convert the delf model to onnx in tf2, `python -m tf2onnx.convert --saved-model ./ --opset 11 --output model.onnx --verbose` this error occurs: `2022-06-20 21:18:17,083 - VERBOSE - tf2onnx.tfonnx: Mapping...

I wanna know the batch size of the inference process for results in this implementation. Batch size seems to influence a lot, referring to https://github.com/ultralytics/yolov5/discussions/6649

positive_loss is much larger than negative_loss

1

**Train log:** _2019-10-11_ 16:29:21,673 maskrcnn_benchmark.trainer INFO: eta: 1 day, 0:40:30 iter: 260 loss: 3.8217 (3.8392) negative_loss: 0.0326 (0.0354) positive_loss: 3.7731 (3.8038) time: 1.3759 (1.4870) data: 0.0050 (0.0068) lr: 0.000680 max...

Results are not good for dota dataset

5

The dataset is dota of whu These images are cropped into (1200 x 1200) by step 900, about 8000 images. 1.The total mAP is about 0.38 when the global step...