Update vision README.md, split the frameworks into separate rows

GATEOverflow · Jul 9, 2024 · 35e3bbd · 35e3bbd
1 parent d3cbc48
commit 35e3bbd
Showing 1 changed file with 5 additions and 2 deletions.
diff --git a/vision/classification_and_detection/README.md b/vision/classification_and_detection/README.md
@@ -9,7 +9,9 @@ Please see the [new docs site](https://docs.mlcommons.org/inference/benchmarks)
 
 | Implementation | Framework | Supported Devices | Supported Precision |
 | -------------- | --------- | ----------------- | ------------------- |
-| [Reference](https://docs.mlcommons.org/inference/benchmarks/image_classification/resnet50/#__tabbed_1_1) | Onnxruntime, Tensorflow, Deepsparse | CPU, CUDA, ROCm | fp32 |
+| [Reference](https://docs.mlcommons.org/inference/benchmarks/image_classification/resnet50/#__tabbed_1_1) | Onnxruntime | CPU, CUDA, ROCm | fp32 |
+| [Reference](https://docs.mlcommons.org/inference/benchmarks/image_classification/resnet50/#__tabbed_1_1) | Tensorflow | CPU, CUDA, ROCm | fp32 |
+| [Reference](https://docs.mlcommons.org/inference/benchmarks/image_classification/resnet50/#__tabbed_1_1) | Deepsparse | CPU | fp32, int8 |
 | [Nvidia](https://docs.mlcommons.org/inference/benchmarks/image_classification/resnet50/#__tabbed_1_2) | TensorRT | CUDA | int8 |
 | [Intel](https://docs.mlcommons.org/inference/benchmarks/image_classification/resnet50/#__tabbed_1_3) | PyTorch | CPU | int8 |
 | [MLCommons C++](https://docs.mlcommons.org/inference/benchmarks/image_classification/resnet50/#__tabbed_1_5) | Onnxruntime | CPU, CUDA | fp32 |
@@ -18,7 +20,8 @@ Please see the [new docs site](https://docs.mlcommons.org/inference/benchmarks)
 
 | Implementation | Framework | Supported Devices | Supported Precision |
 | -------------- | --------- | ----------------- | ------------------- |
-| [Reference](https://docs.mlcommons.org/inference/benchmarks/object_detection/retinanet/#__tabbed_1_1) | Onnxruntime, PyTorch | CPU, CUDA, ROCm | fp32 |
+| [Reference](https://docs.mlcommons.org/inference/benchmarks/object_detection/retinanet/#__tabbed_1_1) | Onnxruntime | CPU, CUDA, ROCm | fp32 |
+| [Reference](https://docs.mlcommons.org/inference/benchmarks/object_detection/retinanet/#__tabbed_1_1) | PyTorch | CPU, CUDA, ROCm | fp32 |
 | [Nvidia](https://docs.mlcommons.org/inference/benchmarks/object_detection/retinanet/#__tabbed_1_2) | TensorRT | CUDA | int8 |
 | [Intel](https://docs.mlcommons.org/inference/benchmarks/object_detection/retinanet/#__tabbed_1_3) | PyTorch | CPU | int8 |
 | [MLCommons C++](https://docs.mlcommons.org/inference/benchmarks/object_detection/retinanet/#__tabbed_1_5) | Onnxruntime | CPU, CUDA | fp32 |