github/kata-containers
1
0
Fork 1
mirror of https://github.com/kata-containers/kata-containers.git synced 2025-04-28 11:44:38 +00:00
Code Issues Projects Releases Wiki Activity
a556ad7e01
kata-containers/tests/metrics/machine_learning
History
David Esparza facf3c9364
metrics: Add onednn benchmark. 
This PR adds onednn test to exercise additional ML benchmarks.

Onednn is an Intel-optimized library for Deep Neural Networks.

Fixes: #9390

Signed-off-by: David Esparza <david.esparza.borquez@intel.com>
2024-04-09 09:05:51 -06:00
..
mobilenet_v1_bfloat16_fp32_dockerfile metrics: General improvements to mobilenet tensorflow test 2023-08-07 16:50:00 +00:00
onednn-dockerfile metrics: Add onednn benchmark. 2024-04-09 09:05:51 -06:00
openvino-dockerfile metrics: Add openvino benchmark. 2024-04-09 09:05:51 -06:00
pytorch_dockerfile tests: Add Pytorch Dockerfile 2023-07-12 16:34:17 +00:00
resnet50_fp32_dockerfile metrics: Update packages needed for ResNet50 FP32 Dockerfile 2024-01-22 16:15:36 +00:00
resnet50_int8_dockerfile metrics: Update packages for TensorFlow ResNet Int8 Dockerfile 2024-01-29 16:11:09 +00:00
tensorflow_nhwc_dockerfile metrics: Use a specific python version to run tensorflow benchmark 2024-01-11 22:15:31 +00:00
onednn.sh metrics: Add onednn benchmark. 2024-04-09 09:05:51 -06:00
openvino.sh metrics: Add openvino benchmark. 2024-04-09 09:05:51 -06:00
pytorch.sh metrics: Use function from metrics common in pytorch script 2023-08-21 16:12:35 +00:00
README.md metrics: Fix README for pytorch 2023-08-18 20:14:49 +00:00
tensorflow_mobilenet_v1_bfloat16_fp32.sh metrics: Remove unused variable in tensorflow mobilenet script 2023-08-17 16:04:18 +00:00
tensorflow_nhwc.sh metrics: Remove unused variable in tensorflow nhwc script 2023-08-24 15:54:27 +00:00
tensorflow_resnet50_fp32.sh metrics: Update command to run tensorflow resnet fp32 benchmark 2023-12-06 17:02:10 +00:00
tensorflow_resnet50_int8.sh metrics: Update command to run the tensorflow int8 benchmark 2023-12-12 16:24:09 +00:00

README.md

Kata Containers TensorFlow Metrics

Kata Containers provides a series of performance tests using the TensorFlow reference benchmarks (tf_cnn_benchmarks). The tf_cnn_benchmarks containers TensorFlow implementations of several popular convolutional models https://github.com/tensorflow/benchmarks/tree/master/scripts/tf_cnn_benchmarks.

Currently the TensorFlow benchmark on Kata Containers includes test for the AxelNet and ResNet50 models.

Running the test

Individual tests can be run by hand, for example:

$ cd metrics/machine_learning
$ ./tensorflow_nhwc.sh 25 60

Kata Containers Pytorch Metrics

Based on a suite of Python high performance computing benchmarks that uses various popular Python HPC libraries using Python https://github.com/dionhaefner/pyhpc-benchmarks.

Running the Pytorch test

Individual tests can be run by hand, for example:

$ cd metrics/machine_learning
$ ./pytorch.sh 40 100

Kata Containers TensorFlow MobileNet Metrics

MobileNets are small, low-latency, low-power models parameterized to meet the resource constraints of a variety of use cases. They can be built upon for classification, detection, embeddings and segmentation similar to how other popular large scale models, such as Inception, are used. MobileNets can be run efficiently on mobile devices with Tensorflow Lite.

Kata Containers provides a test for running MobileNet V1 inference using Intel-Optimized TensorFlow.

Running the TensorFlow MobileNet test

Individual test can be run by hand, for example:

$ cd metrics/machine_learning
$ ./tensorflow_mobilenet_benchmark.sh 25 60

Kata Containers TensorFlow ResNet50 Metrics

ResNet50 is an image classification model pre-trained on the ImageNet dataset. Kata Containers provides a test for running ResNet50 inference using Intel-Optimized TensorFlow.

Running the TensorFlow ResNet50 test

Individual test can be run by hand, for example:

$ cd metrics/machine_learning
$ ./tensorflow_resnet50_int8.sh 25 60