XMOS 人工智能工具
项目描述
XMOS 人工智能工具
用法
使用 xformer
from xmos_ai_tools import xformer as xf
xf.convert("source model path", "converted model path", params=None)
whereparams是编译器标志和参数及其值的字典。
例如：
from xmos_ai_tools import xformer as xf
xf.convert("example_int8_model.tflite", "xcore_optimised_example_int8_model.tflite", {
"mlir-disable-threading": None,
"xcore-reduce-memory": None,
})
要查看所有可用参数，请调用
from xmos_ai_tools import xformer as xf
xf.print_help()
这将打印所有可传递给 xformer 的选项。要查看隐藏选项，请运行print_help(show_hidden=True)
使用 xcore tflm 主机解释器
from xmos_ai_tools import xcore_tflm_host_interpreter as xtflm
ie = xtflm.XTFLMInterpreter(model_content=xformed_model)
ie.set_input_tensor(0, input_tensor)
ie.invoke()
xformer_outputs = []
for i in range(num_of_outputs):
xformer_outputs.append(ie.get_output_tensor(i))
关
xmos_ai_tools_beta -0.1.5.dev20220320.639da62c-py3-none-macosx_11_0_arm64.whl 的哈希值
| 算法 | 哈希摘要 | |
|---|---|---|
| SHA256 | 7273dd5036fa0c8b85dc78d00fdec8b1f1811872b7764320b5a87d07e9e2fd86 |
|
| MD5 | 047be9a2fca6757407cf6343efff25c4 |
|
| 布莱克2-256 | 4229c861d277593c22939b0baa262c342493deacb9c352bb1f3246565829e5ec |
关
xmos_ai_tools_beta -0.1.5.dev20220320.639da62c-py3-none-macosx_10_9_x86_64.whl 的哈希值
| 算法 | 哈希摘要 | |
|---|---|---|
| SHA256 | d56d5dd81d11117b35665fc55bf37e07041eb9962fceebc577bcde496bec8d09 |
|
| MD5 | 91022bcb8a59063436af2dbe41e77699 |
|
| 布莱克2-256 | 941ed90c9bfbac2a59f8e29d5da7fcbc7ee853314cb3d1a3700708d2805e893b |
关
xmos_ai_tools_beta -0.1.5.dev20220320-py3-none-manylinux_2_12_x86_64.manylinux2010_x86_64.whl 的哈希值
| 算法 | 哈希摘要 | |
|---|---|---|
| SHA256 | bb337dee748090bf853f0c7684f9bcdc920c5a9813217996443441c8361eb7c1 |
|
| MD5 | b674717bbe53590e57d297bb30f79aa8 |
|
| 布莱克2-256 | 5d938d5bf173689c860f7cdd70d7f57d4bc509b8a1e83456adbafc139cb38172 |