-
### 🚀 The feature, motivation and pitch
I was trying to export some standard torchvision detection models, but export failed due to
```
torch._dynamo.exc.Unsupported: call_function BuiltinVariabl…
-
```python
import torch
import torchvision
import torch.utils.tensorboard
model = torchvision.models.detection.fasterrcnn_resnet50_fpn()
script = torch.jit.script(model)
script.save('fasterrcnn_r…
-
### System information
- **OS Platform and Distribution (e.g., Linux Ubuntu 16.04)**: Linux Ubuntu 16.04
- **FiftyOne installed from (pip or source)**: pip
- **FiftyOne version (run `fiftyo…
-
### 🐛 Describe the bug
`fasterrcnn_resnet50_fpn()` includes code to edit weights on-the-fly while loading them: https://github.com/pytorch/vision/blob/bf01bab6125c5f1152e4f336b470399e52a8559d/torchvi…
-
I am able to load the custom dataset where **target** contain dict of {boxes, labels}. But, when I try to build **fasterrcnn_resnet50_fpn** model, it is showing **TorchStudio\python\lib\site-packages…
-
**Description**
A onnx model can return empty predictions because it includes certain post-processing internally (faster r-cnn, yolov7). In this case **triton** logs a `Parse error at offset 0: The d…
-
To help users take advantage of rikai for their existing mlflow models, we want to make it easier for them to bring those into the catalog. In particular, we want to allow the user to specify the foll…
-
Hi,
using pytorch 1.11 I get:
` File "/home/.local/lib/python3.10/site-packages/torchvision/models/detection/faster_rcnn.py", line 396, in fasterrcnn_resnet50_fpn
model = FasterRCNN(backbo…
-
**Describe the bug**
FastRCNN based models input is a list (The batch is a list of tensors).
Hence it can not be described using the current API which only let the user set the tensor dimensions.
…
-
Current Orca estimator predict only handles model with one output. Many models have multiple outputs, e.g. image object detection models: detection.fasterrcnn_resnet50_fpn, fasterrcnn_mobilenet_v3_lar…