-
## 🚀 Feature
Similar to what we did for classification, probably we should provide something for detection.
This will allow to load pretrained weights from Kitty, COCO, etc. datasets.
-
### 🐛 Describe the bug
The enclosed python code (at the end) defines and executes a simplified training loop for a Faster R-CNN model with a ResNet-50 FPN backbone, using the PyTorch and torchvision …
-
There's small nuances in how the dynamo runners benchmark models that can make certain torchbench models fail
Some models might be explicitly skipped, others might fail because of some dtype conve…
-
The train.py file accepts --model and --weights arguments and when I use the --model argument, training is from scratch. And when I use --weights and set the path to a pth file, I am getting this erro…
-
Thanks for sharing the code. I see that the models in the examples in this repo are all for classification. I was wondering if we can compare two models that do different tasks such as one for classif…
-
## 🐛 Bug
I used the torch.jit.trace() in python to trace the fasterrcnn_resnet50_fpn model provided in the latest torchvision (I installed the torchvision from source). However, an unhandled exce…
-
### System Information
opencv-python-rolling-4.7.0.20230520
Windows 10
Python 3.10.4
### Detailed description
While facing the issue described here: https://github.com/opencv/opencv/issues/21634,…
-
### 🐛 Describe the bug
I have a trained fasterRCNN model that I want to load via the libtorch C++ API for deployment. The model can be scripted using the following python code snippet successfully.
…
-
TorchBench CI has detected a performance signal or runtime regression.
Base PyTorch commit: 0200b1106c4fe80ea0884181dc8d649ef6078ea3
Affected PyTorch commit: 806d1a871ddfd2d38e1791489892009feaec842…
-
Hi
Thank you for your team to do such a nice work!
My team have trained a model with **torchvision's faster-rcnn**,and now we have to compress the model.And after some time's struggle,we finally de…