Austin Welch

MMDeploy and inference_detector_by_patches

2

Hi, I noticed that RotatedRetinaNet supports TensorRT conversion via MMDeploy. Is it possible to use this with very large images, as with `inference_detector_by_patches`?

FailedPreconditionError when adding callback in Colab

1

Hi, when I add this callback to a simple Keras script in Colab I get the error: > FailedPreconditionError: Error while reading resource variable conv_dw_8_1/depthwise_kernel from Container: localhost. This could...

[Feature Request] AWS Neuron backend

5

**Describe the feature** I'd like to request adding [AWS Neuron](https://aws.amazon.com/machine-learning/neuron/) as a supported backend for deployment to AWS Inferentia chips. **Motivation** Inferentia chips are a new, very fast and cost...

centernet _custom classes

1

Hi, I noticed that the centernet detection model does not have a `_custom` version as the other detection models do. How can I pass a custom `classes` list to `get_model`...

Per class plot

2

How can I modify `tide.plot()` to separate classes? I only have 3 classes in my dataset which differ drastically in difficulty, so would like to see this per-class breakdown.

ValueError on vgg16_bn unless I first train for one epoch

1

I'm able to build and display a graph right away on the torchvision `alexnet` model. But on the torchvision `vgg16_bn` model, if try to graph the model before training I...

[Feature request] Compatibility with iterable-style datasets

6

## 🚀 Feature I'd like to be able to train iterable-style datasets instead of just map-style datasets. (a map-style dataset in PyTorch has `__getitem__` and `__len__`, whereas iterable-style datasets only...

## 🚀 Feature **Is your feature request related to a problem? Please describe.** I'd like to be able to train iterable-style datasets instead of just map-style datasets. (a map-style dataset...

## 🚀 Feature **Is your feature request related to a problem? Please describe.** I'd really like to use mmtracking models for video datasets. **Describe the solution you'd like** Support for...

## 🚀 Feature **Is your feature request related to a problem? Please describe.** For commercial applications, very large datasets are common, yet examples in many vision libraries often do not...