-
### 🚀 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…
-
**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…
-
Reproduction:
```python
import torch
from torchvision.models.detection import keypointrcnn_resnet50_fpn
from time import perf_counter
model = keypointrcnn_resnet50_fpn()
scripted_model = tor…
-
## ❓ Questions and Help
Hello! I am trying to learn about about Captum and how to use it. I am trying to use some of the Captum model interpretation tools such as Integrated Gradients (and eventu…
-
Hi,
I want to train a fasterrcnn_resnet50_fpn_v2 model on a custom dataset. I want to start from COCO pre-trained weights. Is that the default behavior?
or Do I need to supply a weights file thru…
-
My initial training command was the ff:
`python train.py --data data_configs/custom_data.yaml --epochs 20 --model fasterrcnn_resnet50_fpn_v2 --name custom_training --batch 4 --imgsz 320`
I want …
-
## Summary of Contributions (9th Feb)
1) **Improve the number of models in TorchBench that work with Dynamo as a tracer:** These passing rates are now comparable to those from torch.compile using I…
-
### 🐛 Describe the bug
I found that running a torchvision model under MPS backend was extremely slow compared to cpu.
I ran the profiler and found that the __vast__ majority of that time was comin…
-
```python
import coremltools as ct
import torch
import torchvision
import torch.nn as nn
class Wrapper(nn.Module):
def __init__(self, model_name):
super(Wrapper, self).__init__()
…
-
Hi, I've read the docs but couldn't find anything on inferencing on images instead of videos. Just wondering if anyone has any pointers? I'd like to get SuperAnimal running, but it seems like SuperAni…