docs: dx-m1 sdk to v2.1.0（translate）

i18n/en/docusaurus-plugin-content-docs/current/aicore/dx-m1/download.md

@@ -6,10 +6,16 @@ sidebar_position: 15
 
 ## DX-M1 SDK
 
-- [dx_com_M1_v1.60.1](https://dl.radxa.com/aicore/dx_m1/dx_com_M1_v1.60.1.tar.gz)
-- [DX_Tron_v0.0.8](https://dl.radxa.com/aicore/dx_m1/sdk/DX_Tron_v0.0.8.zip)
+**DX-COM**
+
+- [dx_com_M1_v2.1.0](https://dl.radxa.com/aicore/dx_m1/sdk/dx_com_M1_v2.1.0.tar.gz)
+
+**DX-Tron**
+
+- [**Linux:** DXTron-2.0.0.AppImage](https://dl.radxa.com/aicore/dx_m1/sdk/DXTron-2.0.0.AppImage)
+- [**Windows:** DXTron Setup 2.0.0.exe](https://dl.radxa.com/aicore/dx_m1/sdk/DXTron%20Setup%202.0.0.exe)
 
 ## Reference Documents
 
-- [Radxa AICore DX-M1 Product Brief (English)](https://dl.radxa.com/aicore/dx_m1/radxa_aicore_dx_m1_product_brief_en_revision_1.0.pdf)
-- [Radxa AICore DX-M1 Product Brief (Chinese)](https://dl.radxa.com/aicore/dx_m1/radxa_aicore_dx_m1_product_brief_zh_revision_1.0.pdf)
+- [Radxa AI Core DX-M1 Product Brief (English)](https://dl.radxa.com/aicore/dx_m1/radxa_aicore_dx_m1_product_brief_en_revision_1.0.pdf)
+- [Radxa AI Core DX-M1 Product Brief (Chinese)](https://dl.radxa.com/aicore/dx_m1/radxa_aicore_dx_m1_product_brief_zh_revision_1.0.pdf)

i18n/en/docusaurus-plugin-content-docs/current/aicore/dx-m1/dx-sdk/README.md

@@ -4,6 +4,6 @@ sidebar_position: 3
 
 # DX-M1 SDK
 
-Mainly introduces the application development for AI hardware acceleration using DX-M1 SDK on Radxa AICore DX-M1
+This section introduces application development for AI hardware acceleration on the Radxa AI Core DX-M1 using the DX-M1 SDK.
 
 <DocCardList />

i18n/en/docusaurus-plugin-content-docs/current/aicore/dx-m1/dx-sdk/_dx-sim.mdx

@@ -4,13 +4,13 @@ sidebar_position: 3
 
 # DX-SIM Inference Simulator
 
-## Introduction
+## Overview
 
-**DX-SIM (Model Simulator)** simulates the DEEPX NPU hardware functions on an x86 PC, enabling DXNN model inference simulation on an x86 PC.
+**DX-SIM (model simulator)** simulates DEEPX NPU hardware behavior on an x86 PC, enabling you to run inference for DXNN models on an x86 PC.
 
 ## Installation
 
-Download the DX-SIM installation package from the DX-M1 SDK [Resources Download](../download.md) page and extract it.
+Download the DX-SIM package from the DX-M1 SDK [Downloads](../download.md) page and extract it.
 
 <NewCodeBlock tip="X86 PC" type="PC">
 
@@ -21,7 +21,7 @@ tar -xvf dx_simulator_v2.14.5.tar.gz -C dx_simulator && cd dx_simulator
 
 </NewCodeBlock>
 
-Install DX-SIM:
+Install DX-SIM
 
 <NewCodeBlock tip="X86 PC" type="PC">
 
@@ -42,23 +42,23 @@ pip3 install dx_simulator-2.14.5-cp311-cp311-linux_x86_64.whl --force-reinstall
 
 ### Simulator Class
 
-- Use the `Simulator` class to initialize the simulator instance.
+- Use the `Simulator` class to initialize the simulator.
 
 ```python
 from dx_simulator import Simulator
 
 simulator = Simulator(
     model_path="path/to/graph.dxnn",
-    use_gpu=True,  # If you want to run the model with GPU.
+    use_gpu=True, # If you want to run the model with gpu.
 )
 ```
 
-### Inference Simulation
+### Simulated Inference
 
-Use the `Simulator.run()` function to perform inference simulation.
+Use `Simulator.run()` for simulated inference.
 
-- `output_names` is the list of model output names.
-- `input_feed` is a dictionary that contains model input names and input data.
+- `output_names` is a list of model output names.
+- `input_feed` is a dictionary that maps model input names to input data.
 
 ```bash
 outputs = simulator.run(
@@ -67,9 +67,9 @@ outputs = simulator.run(
 )
 ```
 
-### Generating Reference Data
+### Generate Reference Data
 
-If you want to generate reference data to compare with the runtime output on NPU, refer to the following method:
+If you want to generate reference data for comparison with the NPU runtime outputs, use the following method.
 
 ```python
 from dx_simulator import Simulator
@@ -93,14 +93,14 @@ simulator.make_gt_with_image_file(
 
 ### Image Preprocessing
 
-When using the simulator for inference, the input data is the same as on NPU and **must be of type `uint8`**. Therefore, pay attention to the following points during preprocessing:
+When running inference with the simulator, the input data requirements are the same as for the NPU: **the input must be `uint8`**. Therefore, pay attention to the following during preprocessing:
 
-- The simulator input data must be of type `uint8`.
-- Do not use operations such as `Mul` or `Add` (i.e., multiplication or addition) in the preprocessing stage; otherwise, the data format may no longer satisfy the `uint8` requirement.
-- Similar operations (including `Normalize`) should be specified in the configuration file and handled on the **NPU side**.
-- After preprocessing, you **must convert the data type to `np.uint8`** to ensure the simulator can accept the input correctly.
+- The simulator input data must be `uint8`.
+- Do not use operations such as `Mul` or `Add` (i.e., multiplication/addition) during preprocessing; otherwise the data format will not meet the `uint8` requirement.
+- Similar operations (including `Normalize`) should be specified in the configuration file and handled **on the NPU side**.
+- After preprocessing, you **must cast to `np.uint8`** to ensure the simulator can accept the input correctly.
 
-Below is an example code snippet showing how to build the preprocessing pipeline before feeding data into the simulator:
+Below is an example snippet showing how to build the preprocessing pipeline before running the simulator:
 
 ```python
 import cv2
@@ -118,7 +118,7 @@ outputs = simulator.run(
 )
 ```
 
-### Simulator Class Member Functions
+### Simulator Class Methods
 
 ```bash
 from dx_simulator import Simulator
@@ -131,7 +131,7 @@ output_metadata = simulator.get_outputs() # Return model's output names
 
 ### Reference Code
 
-For more examples of using DX-SIM, please refer to the `example` directory in the DX-SIM SDK:
+For more DX-SIM usage examples, refer to the sample code under `example` in the DX-SIM SDK.
 
 ```bash
 .