Results from R50 GH action on

Author: mlcommons-bot

open/MLCommons/measurements/gh_ubuntu-latest-reference-cpu-tvm-onnx_v1.19.2-default_config/README.md

@@ -1,3 +1,3 @@
 | Model    | Scenario   |   Accuracy |   Throughput | Latency (in ms)   |
 |----------|------------|------------|--------------|-------------------|
-| resnet50 | offline    |         80 |         1.74 | -                 |
+| resnet50 | offline    |         80 |        1.732 | -                 |

open/MLCommons/measurements/gh_ubuntu-latest-reference-cpu-tvm-onnx_v1.19.2-default_config/resnet50/offline/README.md

@@ -17,7 +17,7 @@ pip install -U mlcflow
 
 mlc rm cache -f
 
-mlc pull repo anandhu-eng@mlperf-automations --checkout=6d159cee2846dc5b384a7d575ad72fed50a5c1cc
+mlc pull repo anandhu-eng@mlperf-automations --checkout=86665a22465de39bcc31a15ed415bb408ba189f6
 
 
 ```
@@ -41,4 +41,4 @@ Model Precision: fp32
 `acc`: `80.0`, Required accuracy for closed division `>= 75.6954`
 
 ### Performance Results 
-`Samples per second`: `1.73971`
+`Samples per second`: `1.73225`

open/MLCommons/measurements/gh_ubuntu-latest-reference-cpu-tvm-onnx_v1.19.2-default_config/resnet50/offline/accuracy_console.out

@@ -1,11 +1,11 @@
-python3 python/main.py --profile resnet50-onnxruntime --model "/home/runner/MLC/repos/local/cache/get-tvm-model_7d79897f/resnet50_v1.onnx" --dataset-path /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_97889e7a --output "/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_1919767e/test_results/gh_ubuntu-latest-reference-cpu-tvm-onnx-v1.19.2-default_config/resnet50/offline/accuracy" --backend tvm --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/077ad488d1ea4507b78621f21468c418.conf --accuracy --use_preprocessed_dataset --cache_dir /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_97889e7a --dataset-list /home/runner/MLC/repos/local/cache/extract-file_imagenet-aux-da_382006aa/val.txt
-INFO:main:Namespace(dataset='imagenet', dataset_path='/home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_97889e7a', dataset_list='/home/runner/MLC/repos/local/cache/extract-file_imagenet-aux-da_382006aa/val.txt', data_format=None, profile='resnet50-onnxruntime', scenario='Offline', max_batchsize=1, model='/home/runner/MLC/repos/local/cache/get-tvm-model_7d79897f/resnet50_v1.onnx', output='/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_1919767e/test_results/gh_ubuntu-latest-reference-cpu-tvm-onnx-v1.19.2-default_config/resnet50/offline/accuracy', inputs=None, outputs=['ArgMax:0'], backend='tvm', device=None, model_name='resnet50', threads=4, qps=None, cache=0, cache_dir='/home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_97889e7a', 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/077ad488d1ea4507b78621f21468c418.conf', audit_conf='audit.config', time=None, count=5, performance_sample_count=None, max_latency=None, samples_per_query=8)
+python3 python/main.py --profile resnet50-onnxruntime --model "/home/runner/MLC/repos/local/cache/get-tvm-model_3d1d526b/resnet50_v1.onnx" --dataset-path /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_4eb63c92 --output "/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_ce790190/test_results/gh_ubuntu-latest-reference-cpu-tvm-onnx-v1.19.2-default_config/resnet50/offline/accuracy" --backend tvm --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/7061e1b4ab12477399033a70375401b5.conf --accuracy --use_preprocessed_dataset --cache_dir /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_4eb63c92 --dataset-list /home/runner/MLC/repos/local/cache/extract-file_imagenet-aux-da_3d891ba6/val.txt
+INFO:main:Namespace(dataset='imagenet', dataset_path='/home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_4eb63c92', dataset_list='/home/runner/MLC/repos/local/cache/extract-file_imagenet-aux-da_3d891ba6/val.txt', data_format=None, profile='resnet50-onnxruntime', scenario='Offline', max_batchsize=1, model='/home/runner/MLC/repos/local/cache/get-tvm-model_3d1d526b/resnet50_v1.onnx', output='/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_ce790190/test_results/gh_ubuntu-latest-reference-cpu-tvm-onnx-v1.19.2-default_config/resnet50/offline/accuracy', inputs=None, outputs=['ArgMax:0'], backend='tvm', device=None, model_name='resnet50', threads=4, qps=None, cache=0, cache_dir='/home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_4eb63c92', 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/7061e1b4ab12477399033a70375401b5.conf', audit_conf='audit.config', time=None, count=5, performance_sample_count=None, max_latency=None, samples_per_query=8)
 INFO:imagenet:Loading 5 preprocessed images using 4 threads
 INFO:imagenet:loaded 5 images, cache=0, already_preprocessed=True, took=0.0sec
-TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_7d79897f/model-tvm.so
+TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_3d1d526b/model-tvm.so
 INFO:main:starting TestScenario.Offline
-TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_7d79897f/model-tvm.so
-TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_7d79897f/model-tvm.so
-TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_7d79897f/model-tvm.so
-TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_7d79897f/model-tvm.so
-TestScenario.Offline qps=1.72, mean=1.7652, time=2.908, acc=80.000%, queries=5, tiles=50.0:1.4780,80.0:1.8009,90.0:2.3386,95.0:2.6074,99.0:2.8225,99.9:2.8709
+TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_3d1d526b/model-tvm.so
+TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_3d1d526b/model-tvm.so
+TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_3d1d526b/model-tvm.so
+TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_3d1d526b/model-tvm.so
+TestScenario.Offline qps=1.72, mean=1.7636, time=2.912, acc=80.000%, queries=5, tiles=50.0:1.4832,80.0:1.7744,90.0:2.3286,95.0:2.6056,99.0:2.8273,99.9:2.8772