mlcommons / mlcommons/inference
TypeError
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.6k
- Forks
- 650
- Avg merge
- 1d 22h
- Merged PRs (30d)
- 6
Description
python3 -u main.py --scenario Offline --model-path ${CHECKPOINT_PATH} --mlperf-conf mlperf.conf --user-conf user.conf --total-sample-count 24576 --dataset-path ${DATASET_PATH} --output-log-dir offline-logs --dtype float32 --device cuda:0 2>&1 | tee offline_performance_log.log
Traceback (most recent call last):
File "/home/fangtao/inference/language/llama2-70b/main.py", line 96, in
main()
File "/home/fangtao/inference/language/llama2-70b/main.py", line 69, in main
sut = sut_cls(
File "/home/fangtao/inference/language/llama2-70b/SUT.py", line 97, in init
self.data_object = Dataset(self.model_path, dataset_path=self.dataset_path, total_sample_count=total_sample_count)
File "/home/fangtao/inference/language/llama2-70b/dataset.py", line 30, in init
self.load_processed_dataset()
File "/home/fangtao/inference/language/llama2-70b/dataset.py", line 52, in load_processed_dataset
input_tokens = processed_data['tok_input']
File "/root/miniconda3/envs/llama2-70b/lib/python3.9/site-packages/pandas/core/frame.py", line 4078, in getitem
return self._get_item_cache(key)
File "/root/miniconda3/envs/llama2-70b/lib/python3.9/site-packages/pandas/core/frame.py", line 4639, in _get_item_cache
res = self._ixs(loc, axis=1)
File "/root/miniconda3/envs/llama2-70b/lib/python3.9/site-packages/pandas/core/frame.py", line 4010, in _ixs
col_mgr = self._mgr.iget(i)
File "/root/miniconda3/envs/llama2-70b/lib/python3.9/site-packages/pandas/core/internals/managers.py", line 1016, in iget
block = self.blocks[self.blknos[i]]
File "/root/miniconda3/envs/llama2-70b/lib/python3.9/site-packages/pandas/core/internals/managers.py", line 192, in blknos
self._rebuild_blknos_and_blklocs()
File "internals.pyx", line 761, in pandas._libs.internals.BlockManager._rebuild_blknos_and_blklocs
TypeError: Cannot convert numpy.ndarray to numpy.ndarray
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with language/llama2-70b/dataset.py, especially load_processed_dataset() at line 52, then trace its call from SUT.py and main.py. Reproduce the shown Offline command and inspect the pandas access to processed_data['tok_input']; done means the command no longer raises the reported TypeError.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- numpy, pandas, python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100