generated from mlcommons/mlperf_inference_submissions
-
Notifications
You must be signed in to change notification settings - Fork 4
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Auto-merge updates from auto-update branch
- Loading branch information
Showing
17 changed files
with
464 additions
and
464 deletions.
There are no files selected for viewing
2 changes: 1 addition & 1 deletion
2
...ents/gh_ubuntu-latest_x86-reference-cpu-pytorch_v2.4.0-default_config/README.md
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,3 +1,3 @@ | ||
| Model | Scenario | Accuracy | Throughput | Latency (in ms) | | ||
|---------|------------|------------|--------------|-------------------| | ||
| rgat | offline | 74.8 | 10.178 | - | | ||
| rgat | offline | 75 | 10.287 | - | |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
10 changes: 5 additions & 5 deletions
10
...-latest_x86-reference-cpu-pytorch_v2.4.0-default_config/rgat/offline/accuracy_console.out
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,10 +1,10 @@ | ||
INFO:main:Namespace(dataset='igbh-dgl-tiny', dataset_path='/home/runner/MLC/repos/local/cache/get-dataset-igbh_1f7e3c51', layout='COO', profile='debug-dgl', scenario='Offline', max_batchsize=1, threads=4, accuracy=True, find_peak_performance=False, backend='dgl', model_name='rgat', output='/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_efbaf8d2/test_results/gh_ubuntu-latest_x86-reference-cpu-pytorch-v2.4.0-default_config/rgat/offline/accuracy', qps=None, model_path='/home/runner/MLC/repos/local/cache/download-file_bc73cb67/RGAT/RGAT.pt', dtype='fp32', device='cpu', user_conf='/home/runner/MLC/repos/GATEOverflow@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/a53925dee7e24a7ebb16f9d46ea8a013.conf', audit_conf='audit.config', time=None, count=500, debug=False, performance_sample_count=5000, max_latency=None, samples_per_query=8) | ||
/home/runner/MLC/repos/local/cache/get-git-repo_d6695667/inference/graph/R-GAT/dgl_utilities/feature_fetching.py:231: UserWarning: The given NumPy array is not writable, and PyTorch does not support non-writable tensors. This means writing to this tensor will result in undefined behavior. You may want to copy the array to protect its data or make it writable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at ../torch/csrc/utils/tensor_numpy.cpp:206.) | ||
INFO:main:Namespace(dataset='igbh-dgl-tiny', dataset_path='/home/runner/MLC/repos/local/cache/get-dataset-igbh_0ee7ff03', layout='COO', profile='debug-dgl', scenario='Offline', max_batchsize=1, threads=4, accuracy=True, find_peak_performance=False, backend='dgl', model_name='rgat', output='/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_565c2eab/test_results/gh_ubuntu-latest_x86-reference-cpu-pytorch-v2.4.0-default_config/rgat/offline/accuracy', qps=None, model_path='/home/runner/MLC/repos/local/cache/download-file_f5fe0de2/RGAT/RGAT.pt', dtype='fp32', device='cpu', user_conf='/home/runner/MLC/repos/GATEOverflow@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/d243700881f845acba1015869b5d2d73.conf', audit_conf='audit.config', time=None, count=500, debug=False, performance_sample_count=5000, max_latency=None, samples_per_query=8) | ||
/home/runner/MLC/repos/local/cache/get-git-repo_3979716c/inference/graph/R-GAT/dgl_utilities/feature_fetching.py:231: UserWarning: The given NumPy array is not writable, and PyTorch does not support non-writable tensors. This means writing to this tensor will result in undefined behavior. You may want to copy the array to protect its data or make it writable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at ../torch/csrc/utils/tensor_numpy.cpp:206.) | ||
return edge, torch.from_numpy( | ||
/home/runner/MLC/repos/local/cache/get-git-repo_d6695667/inference/graph/R-GAT/dgl_utilities/feature_fetching.py:312: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. | ||
/home/runner/MLC/repos/local/cache/get-git-repo_3979716c/inference/graph/R-GAT/dgl_utilities/feature_fetching.py:312: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. | ||
torch.load( | ||
/home/runner/MLC/repos/local/cache/get-git-repo_d6695667/inference/graph/R-GAT/dgl_utilities/feature_fetching.py:318: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. | ||
/home/runner/MLC/repos/local/cache/get-git-repo_3979716c/inference/graph/R-GAT/dgl_utilities/feature_fetching.py:318: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. | ||
torch.load( | ||
/home/runner/MLC/repos/local/cache/get-git-repo_d6695667/inference/graph/R-GAT/backend_dgl.py:70: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. | ||
/home/runner/MLC/repos/local/cache/get-git-repo_3979716c/inference/graph/R-GAT/backend_dgl.py:70: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. | ||
ckpt = torch.load(ckpt_path, map_location=self.device) | ||
INFO:main:starting TestScenario.Offline |
Oops, something went wrong.