mindspore_lite.Context
- class mindspore_lite.Context(thread_num=None, inter_op_parallel_num=None, thread_affinity_mode=None, \ thread_affinity_core_list=None, enable_parallel=False)[source]
Context is used to store environment variables during execution.
The context should be configured before running the program. If it is not configured, it will be automatically set according to the device target by default.
Note
If core_list and mode are set by SetThreadAffinity at the same time, the core_list is effective, but the mode is not effective. If the default value of the parameter is none, it means the parameter is not set.
- Parameters
thread_num (int, optional) – Set the number of threads at runtime. Default: None.
inter_op_parallel_num (int, optional) – Set the parallel number of operators at runtime. Default: None.
thread_affinity_mode (int, optional) –
Set the thread affinity to CPU cores. Default: None.
0: no affinities.
1: big cores first.
2: little cores first.
thread_affinity_core_list (list[int], optional) – Set the thread lists to CPU cores. Default: None.
enable_parallel (bool, optional) – Set the status whether to perform model inference or training in parallel. Default: False.
- Raises
TypeError – thread_num is neither an int nor None.
TypeError – inter_op_parallel_num is neither an int nor None.
TypeError – thread_affinity_mode is neither an int nor None.
TypeError – thread_affinity_core_list is neither a list nor None.
TypeError – thread_affinity_core_list is a list, but the elements are neither int nor None.
TypeError – enable_parallel is not a bool.
ValueError – thread_num is less than 0.
ValueError – inter_op_parallel_num is less than 0.
Examples
>>> import mindspore_lite as mslite >>> context = mslite.Context(thread_num=1, inter_op_parallel_num=1, thread_affinity_mode=1, ... enable_parallel=False) >>> print(context) thread_num: 1, inter_op_parallel_num: 1, thread_affinity_mode: 1, thread_affinity_core_list: [], enable_parallel: False, device_list: .
- append_device_info(device_info)[source]
Append one user-defined device info to the context.
Note
After gpu device info is added, cpu device info must be added before call context. Because when ops are not supported on GPU, The system will try whether the CPU supports it. At that time, need to switch to the context with cpu device info.
After Ascend device info is added, cpu device info must be added before call context. Because when ops are not supported on Ascend, The system will try whether the CPU supports it. At that time, need to switch to the context with cpu device info.
- Parameters
device_info (DeviceInfo) – the instance of device info.
- Raises
TypeError – device_info is not a DeviceInfo.
Examples
>>> import mindspore_lite as mslite >>> context = mslite.Context() >>> context.append_device_info(mslite.CPUDeviceInfo()) >>> print(context) thread_num: 0, inter_op_parallel_num: 0, thread_affinity_mode: 0, thread_affinity_core_list: [], enable_parallel: False, device_list: 0, .