Results from R50 GH action on ubuntu-latest

open/MLCommons/measurements/gh_ubuntu-latest_x86-reference-cpu-onnxruntime_v1.20.1-default_config/README.md

@@ -0,0 +1,3 @@
+| Model     | Scenario   |   Accuracy |   Throughput | Latency (in ms)   |
+|-----------|------------|------------|--------------|-------------------|
+| retinanet | offline    |     76.951 |        0.433 | -                 |

open/MLCommons/measurements/gh_ubuntu-latest_x86-reference-cpu-onnxruntime_v1.20.1-default_config/retinanet/offline/README.md

@@ -0,0 +1,43 @@
+*Check [CM MLPerf docs](https://docs.mlcommons.org/inference) for more details.*
+
+## Host platform
+
+* OS version: Linux-6.8.0-1020-azure-x86_64-with-glibc2.39
+* CPU version: x86_64
+* Python version: 3.12.8 (main, Dec  4 2024, 06:20:31) [GCC 13.2.0]
+* MLC version: unknown
+
+## CM Run Command
+
+See [CM installation guide](https://docs.mlcommons.org/inference/install/).
+
+```bash
+pip install -U mlcflow
+
+mlc rm cache -f
+
+mlc pull repo anandhu-eng@mlperf-automations --checkout=ba4eb1ee4ca39562f3ee55c8e9972f185b2663bc
+
+
+```
+*Note that if you want to use the [latest automation recipes](https://docs.mlcommons.org/inference) for MLPerf,
+ you should simply reload anandhu-eng@mlperf-automations without checkout and clean MLC cache as follows:*
+
+```bash
+mlc rm repo anandhu-eng@mlperf-automations
+mlc pull repo anandhu-eng@mlperf-automations
+mlc rm cache -f
+
+```
+
+## Results
+
+Platform: gh_ubuntu-latest_x86-reference-cpu-onnxruntime_v1.20.1-default_config
+
+Model Precision: fp32
+
+### Accuracy Results 
+`mAP`: `76.951`, Required accuracy for closed division `>= 37.1745`
+
+### Performance Results 
+`Samples per second`: `0.432787`

open/MLCommons/measurements/gh_ubuntu-latest_x86-reference-cpu-onnxruntime_v1.20.1-default_config/retinanet/offline/accuracy_console.out

@@ -0,0 +1,33 @@
+python3 python/main.py --profile retinanet-onnxruntime --model "/home/runner/MLC/repos/local/cache/download-file_bf7e1bfe/resnext50_32x4d_fpn.onnx" --dataset-path /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-openimages_3e01e6f3 --output "/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_d95a775d/test_results/gh_ubuntu-latest_x86-reference-cpu-onnxruntime-v1.20.1-default_config/retinanet/offline/accuracy" --scenario Offline --max-batchsize 1 --count 5 --threads 4 --user_conf /home/runner/MLC/repos/anandhu-eng@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/d193cc498a6847ae99215d8a0cad7470.conf --accuracy --use_preprocessed_dataset --cache_dir /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-openimages_3e01e6f3 --dataset-list /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-openimages_3e01e6f3/annotations/openimages-mlperf.json
+INFO:main:Namespace(dataset='openimages-800-retinanet-onnx', dataset_path='/home/runner/MLC/repos/local/cache/get-preprocessed-dataset-openimages_3e01e6f3', dataset_list='/home/runner/MLC/repos/local/cache/get-preprocessed-dataset-openimages_3e01e6f3/annotations/openimages-mlperf.json', data_format=None, profile='retinanet-onnxruntime', scenario='Offline', max_batchsize=1, model='/home/runner/MLC/repos/local/cache/download-file_bf7e1bfe/resnext50_32x4d_fpn.onnx', output='/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_d95a775d/test_results/gh_ubuntu-latest_x86-reference-cpu-onnxruntime-v1.20.1-default_config/retinanet/offline/accuracy', inputs=['images'], outputs=['boxes', 'labels', 'scores'], backend='onnxruntime', device=None, model_name='retinanet', threads=4, qps=None, cache=0, cache_dir='/home/runner/MLC/repos/local/cache/get-preprocessed-dataset-openimages_3e01e6f3', preprocessed_dir=None, use_preprocessed_dataset=True, accuracy=True, find_peak_performance=False, debug=False, user_conf='/home/runner/MLC/repos/anandhu-eng@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/d193cc498a6847ae99215d8a0cad7470.conf', audit_conf='audit.config', time=None, count=5, performance_sample_count=None, max_latency=None, samples_per_query=8)
+INFO:coco:loaded 5 images, cache=0, already_preprocessed=True, took=0.0sec
+INFO:main:starting TestScenario.Offline
+loading annotations into memory...
+Done (t=0.00s)
+creating index...
+index created!
+Loading and preparing results...
+Converting ndarray to lists...
+(756, 7)
+0/756
+DONE (t=0.00s)
+creating index...
+index created!
+Running per image evaluation...
+Evaluate annotation type *bbox*
+DONE (t=0.04s).
+Accumulating evaluation results...
+DONE (t=0.12s).
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.770
+ Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.982
+ Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.677
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.483
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.850
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.597
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.824
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.831
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.632
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.875
+TestScenario.Offline qps=0.43, mean=9.3842, time=11.666, acc=42.328%, mAP=76.951%, queries=5, tiles=50.0:9.1293,80.0:9.7898,90.0:10.6242,95.0:11.0414,99.0:11.3752,99.9:11.4503

open/MLCommons/measurements/gh_ubuntu-latest_x86-reference-cpu-onnxruntime_v1.20.1-default_config/retinanet/offline/cpu_info.json

@@ -0,0 +1,26 @@
+{
+  "MLC_HOST_CPU_WRITE_PROTECT_SUPPORT": "yes",
+  "MLC_HOST_CPU_MICROCODE": "0xffffffff",
+  "MLC_HOST_CPU_FPU_SUPPORT": "yes",
+  "MLC_HOST_CPU_FPU_EXCEPTION_SUPPORT": "yes",
+  "MLC_HOST_CPU_BUGS": "sysret_ss_attrs null_seg spectre_v1 spectre_v2 spec_store_bypass srso",
+  "MLC_HOST_CPU_TLB_SIZE": "2560 4K pages",
+  "MLC_HOST_CPU_CFLUSH_SIZE": "64",
+  "MLC_HOST_CPU_ARCHITECTURE": "x86_64",
+  "MLC_HOST_CPU_TOTAL_CORES": "4",
+  "MLC_HOST_CPU_ON_LINE_CPUS_LIST": "0-3",
+  "MLC_HOST_CPU_VENDOR_ID": "AuthenticAMD",
+  "MLC_HOST_CPU_MODEL_NAME": "AMD EPYC 7763 64-Core Processor",
+  "MLC_HOST_CPU_FAMILY": "25",
+  "MLC_HOST_CPU_THREADS_PER_CORE": "2",
+  "MLC_HOST_CPU_PHYSICAL_CORES_PER_SOCKET": "2",
+  "MLC_HOST_CPU_SOCKETS": "1",
+  "MLC_HOST_CPU_L1D_CACHE_SIZE": "64 KiB (2 instances)",
+  "MLC_HOST_CPU_L1I_CACHE_SIZE": "64 KiB (2 instances)",
+  "MLC_HOST_CPU_L2_CACHE_SIZE": "1 MiB (2 instances)",
+  "MLC_HOST_CPU_L3_CACHE_SIZE": "32 MiB (1 instance)",
+  "MLC_HOST_CPU_NUMA_NODES": "1",
+  "MLC_HOST_CPU_TOTAL_LOGICAL_CORES": "4",
+  "MLC_HOST_MEMORY_CAPACITY": "16G",
+  "MLC_HOST_DISK_CAPACITY": "159G"
+}

open/MLCommons/measurements/gh_ubuntu-latest_x86-reference-cpu-onnxruntime_v1.20.1-default_config/retinanet/offline/gh_ubuntu-latest_x86-reference-cpu-onnxruntime_v1.20.1-default_config.json

@@ -0,0 +1,7 @@
+{
+  "starting_weights_filename": "resnext50_32x4d_fpn.onnx",
+  "retraining": "no",
+  "input_data_types": "fp32",
+  "weight_data_types": "fp32",
+  "weight_transformations": "no"
+}