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 |        1.753 | -                 |
+| resnet50 | offline    |         80 |        1.725 | -                 |

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 GATEOverflow@mlperf-automations --checkout=85ae32f3d6aec5e2b1a03cf032d05ccf77a8133c
+mlc pull repo GATEOverflow@mlperf-automations --checkout=70c941bfd49c78b2e1d8343350a580cf73226f2d
 
 
 ```
@@ -41,4 +41,4 @@ Model Precision: fp32
 `acc`: `80.0`, Required accuracy for closed division `>= 75.6954`
 
 ### Performance Results 
-`Samples per second`: `1.75313`
+`Samples per second`: `1.72502`

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

@@ -1,10 +1,11 @@
-python3 python/main.py --profile resnet50-onnxruntime --model "/home/runner/MLC/repos/local/cache/get-tvm-model_fc53d890/resnet50_v1.onnx" --dataset-path /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_f6cd337d --output "/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_2fe4283e/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/GATEOverflow@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/48a0907163b14b47badb1488aaef59d7.conf --accuracy --use_preprocessed_dataset --cache_dir /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_f6cd337d --dataset-list /home/runner/MLC/repos/local/cache/extract-file_imagenet-aux-da_fe3ad174/val.txt
-INFO:main:Namespace(dataset='imagenet', dataset_path='/home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_f6cd337d', dataset_list='/home/runner/MLC/repos/local/cache/extract-file_imagenet-aux-da_fe3ad174/val.txt', data_format=None, profile='resnet50-onnxruntime', scenario='Offline', max_batchsize=1, model='/home/runner/MLC/repos/local/cache/get-tvm-model_fc53d890/resnet50_v1.onnx', output='/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_2fe4283e/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_f6cd337d', preprocessed_dir=None, use_preprocessed_dataset=True, accuracy=True, find_peak_performance=False, debug=False, user_conf='/home/runner/MLC/repos/GATEOverflow@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/48a0907163b14b47badb1488aaef59d7.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_b1c5a49b/resnet50_v1.onnx" --dataset-path /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_225525d1 --output "/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_45ddf402/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/GATEOverflow@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/bc1b7bc1a364484782bd5327129c363a.conf --accuracy --use_preprocessed_dataset --cache_dir /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_225525d1 --dataset-list /home/runner/MLC/repos/local/cache/extract-file_imagenet-aux-da_174b37c6/val.txt
+INFO:main:Namespace(dataset='imagenet', dataset_path='/home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_225525d1', dataset_list='/home/runner/MLC/repos/local/cache/extract-file_imagenet-aux-da_174b37c6/val.txt', data_format=None, profile='resnet50-onnxruntime', scenario='Offline', max_batchsize=1, model='/home/runner/MLC/repos/local/cache/get-tvm-model_b1c5a49b/resnet50_v1.onnx', output='/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_45ddf402/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_225525d1', preprocessed_dir=None, use_preprocessed_dataset=True, accuracy=True, find_peak_performance=False, debug=False, user_conf='/home/runner/MLC/repos/GATEOverflow@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/bc1b7bc1a364484782bd5327129c363a.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_fc53d890/model-tvm.so
+TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_b1c5a49b/model-tvm.so
 INFO:main:starting TestScenario.Offline
-TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_fc53d890/model-tvm.so
-TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_fc53d890/model-tvm.so
-TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_fc53d890/model-tvm.so
-TestScenario.Offline qps=1.72, mean=1.7559, time=2.899, acc=80.000%, queries=5, tiles=50.0:1.4702,80.0:1.7735,90.0:2.3251,95.0:2.6008,99.0:2.8214,99.9:2.8710
+TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_b1c5a49b/model-tvm.so
+TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_b1c5a49b/model-tvm.so
+TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_b1c5a49b/model-tvm.so
+TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_b1c5a49b/model-tvm.so
+TestScenario.Offline qps=1.70, mean=1.7837, time=2.939, acc=80.000%, queries=5, tiles=50.0:1.5025,80.0:1.7861,90.0:2.3490,95.0:2.6304,99.0:2.8556,99.9:2.9062