Skip to content

Commit

Permalink
Auto-merge updates from auto-update branch
Browse files Browse the repository at this point in the history
  • Loading branch information
@mlcommons-bot
mlcommons-bot committed Feb 8, 2025
2 parents efbe000 + 0ce4ca1 commit 2dcf3cd
Show file tree
Hide file tree
Showing 32 changed files with 1,026 additions and 996 deletions.
2 changes: 1 addition & 1 deletion ...ements/gh_ubuntu-latest-reference-cpu-tvm-onnx_v1.19.2-default_config/README.md
View file
Original file line number Diff line number Diff line change
@@ -1,3 +1,3 @@
| Model | Scenario | Accuracy | Throughput | Latency (in ms) |
|----------|------------|------------|--------------|-------------------|
| resnet50 | offline | 80 | 1.741 | - |
| resnet50 | offline | 80 | 1.76 | - |
10 changes: 5 additions & 5 deletions ...latest-reference-cpu-tvm-onnx_v1.19.2-default_config/resnet50/offline/README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -17,16 +17,16 @@ pip install -U mlcflow

mlc rm cache -f

mlc pull repo sujik18@mlperf-automations --checkout=d49ffdad99d90e9df862cef6bc80d631dba2aca0
mlc pull repo GATEOverflow@mlperf-automations --checkout=d8c03b80370b410326753c62c118e37f68fd7d25


```
*Note that if you want to use the [latest automation recipes](https://docs.mlcommons.org/inference) for MLPerf,
you should simply reload sujik18@mlperf-automations without checkout and clean MLC cache as follows:*
you should simply reload GATEOverflow@mlperf-automations without checkout and clean MLC cache as follows:*

```bash
mlc rm repo sujik18@mlperf-automations
mlc pull repo sujik18@mlperf-automations
mlc rm repo GATEOverflow@mlperf-automations
mlc pull repo GATEOverflow@mlperf-automations
mlc rm cache -f

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

### Performance Results
`Samples per second`: `1.74129`
`Samples per second`: `1.75985`
16 changes: 8 additions & 8 deletions ...atest-reference-cpu-tvm-onnx_v1.19.2-default_config/resnet50/offline/accuracy_console.out
View file
Original file line number Diff line number Diff line change
@@ -1,11 +1,11 @@
python3 python/main.py --profile resnet50-onnxruntime --model "/home/runner/MLC/repos/local/cache/get-tvm-model_167e4a91/resnet50_v1.onnx" --dataset-path /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_aa275843 --output "/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_dda6a2c1/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/sujik18@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/69da754000874929a9db4383d9019958.conf --accuracy --use_preprocessed_dataset --cache_dir /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_aa275843 --dataset-list /home/runner/MLC/repos/local/cache/extract-file_0b9989cb/val.txt
INFO:main:Namespace(dataset='imagenet', dataset_path='/home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_aa275843', dataset_list='/home/runner/MLC/repos/local/cache/extract-file_0b9989cb/val.txt', data_format=None, profile='resnet50-onnxruntime', scenario='Offline', max_batchsize=1, model='/home/runner/MLC/repos/local/cache/get-tvm-model_167e4a91/resnet50_v1.onnx', output='/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_dda6a2c1/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_aa275843', preprocessed_dir=None, use_preprocessed_dataset=True, accuracy=True, find_peak_performance=False, debug=False, user_conf='/home/runner/MLC/repos/sujik18@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/69da754000874929a9db4383d9019958.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_c3bcc3a8/resnet50_v1.onnx" --dataset-path /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_279aabcc --output "/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_25d5d806/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/3ab847eaff3f43918cda302af8fbaacc.conf --accuracy --use_preprocessed_dataset --cache_dir /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_279aabcc --dataset-list /home/runner/MLC/repos/local/cache/extract-file_7f556bd6/val.txt
INFO:main:Namespace(dataset='imagenet', dataset_path='/home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_279aabcc', dataset_list='/home/runner/MLC/repos/local/cache/extract-file_7f556bd6/val.txt', data_format=None, profile='resnet50-onnxruntime', scenario='Offline', max_batchsize=1, model='/home/runner/MLC/repos/local/cache/get-tvm-model_c3bcc3a8/resnet50_v1.onnx', output='/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_25d5d806/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_279aabcc', 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/3ab847eaff3f43918cda302af8fbaacc.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_167e4a91/model-tvm.so
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_c3bcc3a8/model-tvm.so
INFO:main:starting TestScenario.Offline
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_167e4a91/model-tvm.so
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_167e4a91/model-tvm.so
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_167e4a91/model-tvm.so
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_167e4a91/model-tvm.so
TestScenario.Offline qps=1.74, mean=1.7544, time=2.880, acc=80.000%, queries=5, tiles=50.0:1.4731,80.0:1.7929,90.0:2.3219,95.0:2.5864,99.0:2.7979,99.9:2.8456
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_c3bcc3a8/model-tvm.so
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_c3bcc3a8/model-tvm.so
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_c3bcc3a8/model-tvm.so
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_c3bcc3a8/model-tvm.so
TestScenario.Offline qps=1.73, mean=1.7416, time=2.882, acc=80.000%, queries=5, tiles=50.0:1.4664,80.0:1.7558,90.0:2.3058,95.0:2.5807,99.0:2.8007,99.9:2.8502
Loading

0 comments on commit 2dcf3cd

Please sign in to comment.