-
**Describe the bug**
If someone saves a model file using a non-default model type (`Model.MOBILENET` or `Model.MOBILENET_320`) and later tries to load it using `Model.load`, it will cause the followi…
-
When I ran the code:
solver = caffe.SGDSolver(PROTOTXT)
I met the problem as follows:
No module named rcnn_layers.
Can someone point me how to fix it?
Thanks!
wj320 updated
3 years ago
-
Thanks OAID teams grateful works
my platfoms is rk3399 and os is ubuntu 16.04
l run the "./examples/build/faster_rcnn/FASTER_RCNN" , using your provide "VGG16_faster_rcnn.prototxt" and "VGG16_fa…
-
I asked a question on [SO](https://stackoverflow.com/questions/54287231/modifying-loss-function-faster-rcnn-detectron)
Ill paste it here:
For my thesis I am trying to modify the loss function …
-
Hi @naisy ,
Thanks a lot for sharing your work.
In the readme, you have mentioned `Faster R-CNN: PC only`
Were you able to get FasterRCNN+Inception (or) FasterRCNN+ResNet working on TX2 with …
-
Thanks for great work, i have a question, how can i set config file to detect oriention target in faster rcnn or other network?
-
在使用mask-rcnn r101 时报了这个，是因为版本问题吗
-
this seems to work but the results ...are wrong
Ive trained a faster-rcnn model in python and it works.
I'm trying to call it from C# for inclusion in an app...below is my code
```
string test…
-
I have got the error “Gradients do not exist for variables” when training faster rcnn， and the loss is nan.
**log：**
W1108 09:59:39.735346 139647501481728 optimizer_v2.py:1029] Gradients do not e…
-
Update Faster R-CNN constituent networks and example to support mixed precision.
Each model output that feeds a loss needs to output an fp32 float. This can be accomplished by adding a linear activ…