Skip to content

Commit b85ece4

Browse files
mlcommons-botmlcommons-bot
committed
Results from R50 GH action on
1 parent f436fcf commit b85ece4

File tree

14 files changed

+502
-556
lines changed

14 files changed

+502
-556
lines changed

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

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,3 @@
11
| Model | Scenario | Accuracy | Throughput | Latency (in ms) |
22
|----------|------------|------------|--------------|-------------------|
3-
| resnet50 | offline | 80 | 1.74 | - |
3+
| resnet50 | offline | 80 | 1.722 | - |

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

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@
44

55
* OS version: Linux-6.11.0-1015-azure-x86_64-with-glibc2.39
66
* CPU version: x86_64
7-
* Python version: 3.9.22 (main, Apr 8 2025, 21:45:32)
7+
* Python version: 3.9.23 (main, Jun 4 2025, 04:11:23)
88
[GCC 13.3.0]
99
* MLC version: unknown
1010

@@ -17,16 +17,16 @@ pip install -U mlcflow
1717

1818
mlc rm cache -f
1919

20-
mlc pull repo anandhu-eng@mlperf-automations --checkout=cd8adc766bf60c024bf9d7dff4f2fba0270e7039
20+
mlc pull repo GATEOverflow@mlperf-automations --checkout=d5fe184c5afb68374c9be5e7e145a4cbe5e6d1be
2121

2222

2323
```
2424
*Note that if you want to use the [latest automation recipes](https://docs.mlcommons.org/inference) for MLPerf,
25-
you should simply reload anandhu-eng@mlperf-automations without checkout and clean MLC cache as follows:*
25+
you should simply reload GATEOverflow@mlperf-automations without checkout and clean MLC cache as follows:*
2626

2727
```bash
28-
mlc rm repo anandhu-eng@mlperf-automations
29-
mlc pull repo anandhu-eng@mlperf-automations
28+
mlc rm repo GATEOverflow@mlperf-automations
29+
mlc pull repo GATEOverflow@mlperf-automations
3030
mlc rm cache -f
3131

3232
```
@@ -41,4 +41,4 @@ Model Precision: fp32
4141
`acc`: `80.0`, Required accuracy for closed division `>= 75.6954`
4242

4343
### Performance Results
44-
`Samples per second`: `1.73989`
44+
`Samples per second`: `1.72184`

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

Lines changed: 8 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -1,10 +1,11 @@
1-
python3 python/main.py --profile resnet50-onnxruntime --model "/home/runner/MLC/repos/local/cache/get-tvm-model_33af9d05/resnet50_v1.onnx" --dataset-path /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_3b1d7672 --output "/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_8019a5b3/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/cbc6d019a8bb4e9692e80a7aa4ae6def.conf --accuracy --use_preprocessed_dataset --cache_dir /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_3b1d7672 --dataset-list /home/runner/MLC/repos/local/cache/extract-file_imagenet-aux-da_719f7495/val.txt
2-
INFO:main:Namespace(dataset='imagenet', dataset_path='/home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_3b1d7672', dataset_list='/home/runner/MLC/repos/local/cache/extract-file_imagenet-aux-da_719f7495/val.txt', data_format=None, profile='resnet50-onnxruntime', scenario='Offline', max_batchsize=1, model='/home/runner/MLC/repos/local/cache/get-tvm-model_33af9d05/resnet50_v1.onnx', output='/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_8019a5b3/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_3b1d7672', 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/cbc6d019a8bb4e9692e80a7aa4ae6def.conf', audit_conf='audit.config', time=None, count=5, performance_sample_count=None, max_latency=None, samples_per_query=8)
1+
python3 python/main.py --profile resnet50-onnxruntime --model "/home/runner/MLC/repos/local/cache/get-tvm-model_fa72ea6c/resnet50_v1.onnx" --dataset-path /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_23fb37fb --output "/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_8bd8b30a/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/1cede6bcc5254c9f9c14bfea970d455a.conf --accuracy --use_preprocessed_dataset --cache_dir /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_23fb37fb --dataset-list /home/runner/MLC/repos/local/cache/extract-file_imagenet-aux-da_b1545dab/val.txt
2+
INFO:main:Namespace(dataset='imagenet', dataset_path='/home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_23fb37fb', dataset_list='/home/runner/MLC/repos/local/cache/extract-file_imagenet-aux-da_b1545dab/val.txt', data_format=None, profile='resnet50-onnxruntime', scenario='Offline', max_batchsize=1, model='/home/runner/MLC/repos/local/cache/get-tvm-model_fa72ea6c/resnet50_v1.onnx', output='/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_8bd8b30a/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_23fb37fb', 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/1cede6bcc5254c9f9c14bfea970d455a.conf', audit_conf='audit.config', time=None, count=5, performance_sample_count=None, max_latency=None, samples_per_query=8)
33
INFO:imagenet:Loading 5 preprocessed images using 4 threads
44
INFO:imagenet:loaded 5 images, cache=0, already_preprocessed=True, took=0.0sec
5-
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_33af9d05/model-tvm.so
5+
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_fa72ea6c/model-tvm.so
66
INFO:main:starting TestScenario.Offline
7-
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_33af9d05/model-tvm.so
8-
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_33af9d05/model-tvm.so
9-
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_33af9d05/model-tvm.so
10-
TestScenario.Offline qps=1.74, mean=1.7449, time=2.881, acc=80.000%, queries=5, tiles=50.0:1.4704,80.0:1.7595,90.0:2.3073,95.0:2.5812,99.0:2.8004,99.9:2.8497
7+
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_fa72ea6c/model-tvm.so
8+
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_fa72ea6c/model-tvm.so
9+
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_fa72ea6c/model-tvm.so
10+
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_fa72ea6c/model-tvm.so
11+
TestScenario.Offline qps=1.71, mean=1.7781, time=2.921, acc=80.000%, queries=5, tiles=50.0:1.5054,80.0:1.7905,90.0:2.3438,95.0:2.6205,99.0:2.8419,99.9:2.8917

0 commit comments

Comments
 (0)