-
````
2020-05-26 23:48:12,707-INFO: Save model to output/faster_rcnn_r50_vd_fpn_ciou_loss_1x/10000.
I0526 23:48:15.279527 24507 parallel_executor.cc:440] The Program will be executed on CUDA using …
-
There is no detailed documentation on loading fasterrcnn_resnet50_fpn by libtorch.
I change the c++ code by following [[1407]](https://github.com/pytorch/vision/pull/1407#issuecomment-562096191)
```…
ljd16 updated
4 years ago
-
Hello, i met a question when i train fasterRCNN.
Some training config: 8 2080Ti , 2 imgs per gpu, and 600:800 img scale.
I find 1gpu may use 11Gb memory, and others use 5Gb. I think the gpus are n…
-
Is possible to initialize core.Model() without initialize pretrained model? I using this following code to load model weights:
self.model = core.Model(self.labels, device = torch.device('cp…
-
Hi Everyone,
I am training the **pretrained Faster RCNN model** on PASCAL VOC 2010 dataset for Object Detection by following this pyTorch finetuning tutorial: [pytorch.org/tutorials/intermediate/to…
-
## 🐛 Bug
TorchVision's pre-trained object detection model like FasterRCNN and MaskRCNN return different output on different cuda device in multi-GPU environment.
## To Reproduce
Execute follo…
-
## 🐛 Bug
I am using a model for Faster RCNN `torchvision.models.detection`. The problem is the value of the target bounding boxes keeps getting altered The operation being performed is just a sim…
chkda updated
4 years ago
-
Hi, I finetuned a pretrained Faster RCNN model.
I used the instance segmentation Mask RCNN pytorch tutorial as a guide.
I finished training and can't figure out how to look at bbox predictions.
…
-
## 🐛 Bug
using the latest installations from the pytorch recommended conda line, along with the following required libraries
```
cython
pycocotools
matplotlib
```
I was able to hit an err…
-
Hello, when using the fasterrcnn_resnet50_fpn model, I noticed I got an error when training on the GPU then running it, in eval mode, on the CPU.
```
Traceback (most recent call last):
File "/hom…