Update docs

xmos · Jun 19, 2023 · f494980 · f494980
1 parent 9dc1f0c
commit f494980
Show file tree

Hide file tree

Showing 3 changed files with 12 additions and 12 deletions.
diff --git a/README.md b/README.md
@@ -26,7 +26,7 @@ Perform the following steps once:
 
 * ``pip3 install xmos-ai-tools --upgrade``; use a virtual-environment of your choice.
 
-  Use ``pip install xmos-ai-tools --pre --upgrade`` instead if you want to install the latest development version.
+  Use ``pip3 install xmos-ai-tools --pre --upgrade`` instead if you want to install the latest development version.
 
 ```python
 from xmos_ai_tools import xformer as xf
@@ -66,8 +66,8 @@ xf.convert("example_int8_model.tflite", "xcore_optimised_int8_flash_model.tflite
 from xmos_ai_tools.xinterpreters import xcore_tflm_host_interpreter
 
 ie = xcore_tflm_host_interpreter()
-ie.set_model(model_path=xcore_model, params_path=xcore_params)
-ie.set_tensor(ie.get_input_details()[0]['index'], value=input)
+ie.set_model(model_path='path_to_xcore_model', params_path='path_to_xcore_params')
+ie.set_tensor(ie.get_input_details()[0]['index'], value='input_data')
 ie.invoke()
 
 xformer_outputs = []

diff --git a/docs/rst/flow.rst b/docs/rst/flow.rst
@@ -14,9 +14,9 @@ Perform the following steps once:
 
 * ``pip3 install xmos-ai-tools --upgrade``; use a virtual-environment of your choice. 
 
-  Use ``pip install xmos-ai-tools --pre --upgrade`` instead if you want to install the latest development version.
+  Use ``pip3 install xmos-ai-tools --pre --upgrade`` instead if you want to install the latest development version.
 
-  Installing ``xmos-ai-tools`` will make the xcore-opt binary available in your shell to use directly, or you can use the Python interface as detailed `here <https://github.com/xmos/ai_tools/blob/02cdcf6/docs/rst/python.rst>`_.
+  Installing ``xmos-ai-tools`` will make the xcore-opt binary available in your shell to use directly, or you can use the Python interface as detailed `here <https://github.com/xmos/ai_tools/blob/develop/docs/rst/python.rst>`_.
 
 * Obtain the tool-chain from http://www.xmos.ai/tools and install it
   according to the platform instructions.

diff --git a/docs/rst/python.rst b/docs/rst/python.rst
@@ -15,9 +15,9 @@ of options and their value.
 
 .. code-block:: Python
 
-  xf.convert("example_int8_model.tflite", "xcore_optimized_int8_model.tflite", 
-    {"mlir-disable-threading": None, "xcore-reduce-memory": None,}
-  )
+  xf.convert("example_int8_model.tflite", "xcore_optimised_int8_model.tflite", {
+      "xcore-thread-count": "5",
+  })
 
 The possible options are described below in the command line interface section. If the default operation is intended this third argument can be "None".
 
@@ -40,7 +40,7 @@ To create a parameters file and a tflite model suitable for loading to flash, us
 .. code-block:: Python
 
   xf.convert("example_int8_model.tflite", "xcore_optimised_int8_flash_model.tflite", {
-      "xcore-flash-image-file ": "./xcore_params.params",
+      "xcore-flash-image-file": "./xcore_params.params",
   })
 
 The python interface also contains a host-side interpreter for tflite
@@ -57,10 +57,10 @@ run inference on a model the interpreters can be used as such:
 .. code-block:: Python
 
   ie = xcore_tflm_host_interpreter()
-  ie.set_model(model_path = xcore_model)
-  ie.set_input_tensor(data = input)
+  ie.set_model(model_path='path_to_xcore_model', params_path='path_to_xcore_params')
+  ie.set_tensor(ie.get_input_details()[0]['index'], value='input_data')
   ie.invoke()
 
   xformer_outputs = []
   for i in range(num_of_outputs):
-      xformer_outputs.append(ie.get_output_tensor(output_index = i))
+      xformer_outputs.append(ie.get_tensor(ie.get_output_details()[i]['index']))