-
Hi,
I'm getting this error messagem when runing:
`$ python anchor_optimization\optimize_anchors.py test.csv`
```
Traceback (most recent call last):
File "E:\anchor-optimization\anchor_optim…
-
Hello..
How can we implement a Retinanet with Resnext-152 as backbone on a Darknet Platform..?
(Also using cost function as Focal Loss)
-
this is when using custom dataset with nonuniform image sizes
File "/home/xiangyong/Workbench/RetinaNet-unsky/retinanet/core/metric.py", line 73, in update
cls_loss = np.sum(-1 * alpha * l…
-
Hi. We are testing some models on our CI using 2.4 static/deploy/python/infer.py. Since static is removed in release 2.5, Which app should we use now for testing both **qat** and **fp32** versions of:…
-
Hi! Nice work.
I am wondering that, since you adopted the ATSS which reveals that whether use the anchor (RetinaNet) or not (FCOS) would achieve same performances, then why not just show the perfor…
-
@tianzhi0549 how to train keypoint by FCOS, I get error use this
BACKBONE:
CONV_BODY: "V-39-eSE-FPN-RETINANET"
FREEZE_CONV_BODY_AT: 0
VOVNET:
BACKBONE_OUT_CHANNELS: 128
RPN_O…
-
I got the following MKL linking errors when I try to build the Intel Docker image for retinanet (with applied workaround for the pybind11 problem suggested in #12) using [this](https://github.com/mlco…
-
I want to save the visual img during eval, and I set it like this in the train.py as discribed in `evaluate` func of csv_eval.py (https://github.com/yhenon/pytorch-retinanet/blob/master/retinanet/cs…
-
The original code doesn't consider the gpu situation for loss, and will lead to the problem:
```RuntimeError: Expected object of backend CUDA but got backend CPU for ...```
original code:
https:/…
-
Hi, thanks for your great work. Following your supplementary materials, I use RetinaNet-ResNet101 to distill RetinaNet-ResNet50, and I plot mAP curve as follows, which can be seen that performance of …