Skip to content

Commit

Permalink
Auto-merge updates from auto-update branch
Browse files Browse the repository at this point in the history
mlcommons-bot committed Jan 29, 2025

Verified

This commit was signed with the committer’s verified signature.
casperdcl Casper da Costa-Luis
2 parents 5e93eb9 + 23f34ab commit 5042839
Showing 33 changed files with 1,008 additions and 984 deletions.
Original file line number Diff line number Diff line change
@@ -1,3 +1,3 @@
| Model | Scenario | Accuracy | Throughput | Latency (in ms) |
|----------|------------|------------|--------------|-------------------|
| resnet50 | offline | 80 | 1.729 | - |
| resnet50 | offline | 80 | 1.732 | - |
Original file line number Diff line number Diff line change
@@ -17,7 +17,7 @@ pip install -U mlcflow

mlc rm cache -f

mlc pull repo GATEOverflow@mlperf-automations --checkout=fe9a774ef04658c8f63f9d98b87e6961ad570525
mlc pull repo GATEOverflow@mlperf-automations --checkout=d086a86ba5e4bfb633128e688bb3140b3d1bf197


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

### Performance Results
`Samples per second`: `1.72882`
`Samples per second`: `1.73159`
Original file line number Diff line number Diff line change
@@ -1,10 +1,11 @@
python3 python/main.py --profile resnet50-onnxruntime --model "/home/runner/MLC/repos/local/cache/get-tvm-model_bdeede81/resnet50_v1.onnx" --dataset-path /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_f327bb58 --output "/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_379fbc5d/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/56e09add5eaa4eeeb4ce01b709d4101a.conf --accuracy --use_preprocessed_dataset --cache_dir /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_f327bb58 --dataset-list /home/runner/MLC/repos/local/cache/extract-file_4d86aeaa/val.txt
INFO:main:Namespace(dataset='imagenet', dataset_path='/home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_f327bb58', dataset_list='/home/runner/MLC/repos/local/cache/extract-file_4d86aeaa/val.txt', data_format=None, profile='resnet50-onnxruntime', scenario='Offline', max_batchsize=1, model='/home/runner/MLC/repos/local/cache/get-tvm-model_bdeede81/resnet50_v1.onnx', output='/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_379fbc5d/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_f327bb58', 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/56e09add5eaa4eeeb4ce01b709d4101a.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_f920ae1c/resnet50_v1.onnx" --dataset-path /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_f2348814 --output "/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_7a1a8244/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/fdbb73e68d2845d98c2cdcc86cad7599.conf --accuracy --use_preprocessed_dataset --cache_dir /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_f2348814 --dataset-list /home/runner/MLC/repos/local/cache/extract-file_1c55ca55/val.txt
INFO:main:Namespace(dataset='imagenet', dataset_path='/home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_f2348814', dataset_list='/home/runner/MLC/repos/local/cache/extract-file_1c55ca55/val.txt', data_format=None, profile='resnet50-onnxruntime', scenario='Offline', max_batchsize=1, model='/home/runner/MLC/repos/local/cache/get-tvm-model_f920ae1c/resnet50_v1.onnx', output='/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_7a1a8244/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_f2348814', 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/fdbb73e68d2845d98c2cdcc86cad7599.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_bdeede81/model-tvm.so
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_f920ae1c/model-tvm.so
INFO:main:starting TestScenario.Offline
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_bdeede81/model-tvm.so
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_bdeede81/model-tvm.so
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_bdeede81/model-tvm.so
TestScenario.Offline qps=1.72, mean=1.7712, time=2.910, acc=80.000%, queries=5, tiles=50.0:1.5033,80.0:1.7809,90.0:2.3314,95.0:2.6067,99.0:2.8269,99.9:2.8764
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_f920ae1c/model-tvm.so
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_f920ae1c/model-tvm.so
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_f920ae1c/model-tvm.so
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_f920ae1c/model-tvm.so
TestScenario.Offline qps=1.71, mean=1.7799, time=2.920, acc=80.000%, queries=5, tiles=50.0:1.5119,80.0:1.7910,90.0:2.3396,95.0:2.6138,99.0:2.8333,99.9:2.8826
Loading

0 comments on commit 5042839

Please sign in to comment.