-
# Prerequisites
Please answer the following questions for yourself before submitting an issue.
- [efficientdet_d4_coco17_tpu-32 ] I am using the latest TensorFlow Model Garden release and Tensor…
-
请问一下，Faster R-CNN里FPN特征融合的代码在哪里，是在ppdet/modeling/anchor_heads/rpn_head.py里吗，没看见对特征图上采样以及特征图相加的代码
-
I am training on my own datasets using the code of April version,the loss is very low than previous version, but the mAP is always 0.
Using the same config,Feb. code version has a high loss, but mAP …
-
I think I've reached the final boss of issues: everything runs smoothly from training to inference, but resulting boxes are empty `[]` and scores are:
```
[-1. -1. -1. -1. -1. -1. -1. -1. -1. -1. -1…
-
This isn't so much a bug report as a general request for advice.
Here's my problem set-up. I want to detect humans (and no other classes) from overhead images. I have a dataset of these images wi…
-
Traceback (most recent call last):
File "efficientdet_test.py", line 71, in
features, regression, classification, anchors = model(x)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/m…
-
You said that Efficient Det is performing well in semantic segmentation. We did not see how it works in semantic segmentation or instance segmentation? Is this intended to be delivered?
-
Dear author,
When I try to inference with the following command `python apply_net.py show configs/densepose_rcnn_R_50_FPN_s1x.yaml densepose_rcnn_R_50_FPN_s1x.pkl image.jpg dp_contour,bbox --output…
-
单独执行python import albumentations没有问题
在程序中执行CDA_VISIBLE_DEVICES=0 python tools/test.py configs/SKU_fusion_bifpn_x101_32x4d.py DenseDet.pth
就报错：
[log.txt](https://github.com/Media-Smart/SKU110K-Dense…
-
Learning Spatial Fusion for Single-Shot Object Detection
* paper [https://arxiv.org/pdf/1911.09516.pdf](https://arxiv.org/pdf/1911.09516.pdf)
* code [https://github.com/ruinmessi/ASFF](https://gith…