doc: add machine learning application test usage

Added documentation for Machine Learning test usage.

Made required changes for machine learning documentation

Signed-off-by: Gaurav Shukla <gshukla@marvell.com>
Signed-off-by: Srikanth Yalavarthi <syalavarthi@marvell.com>
Change-Id: I20919edb7f5f7d1e53fdc3e4944ee66ec30a8e06
Reviewed-on: https://sj1git1.cavium.com/c/IP/SW/dataplane/dpu-offload/+/136284
Reviewed-by: Abed Mohammad Kamaluddin <akamaluddin@marvell.com>
Klocwork: Abed Mohammad Kamaluddin <akamaluddin@marvell.com>
Tested-by: sa_ip-toolkits-Jenkins <sa_ip-toolkits-jenkins@marvell.com>

Author: Gaurav Shukla

doc/guides/applications/index.rst

@@ -14,3 +14,4 @@ Application User Guide
     smart-nic
     vpp
     tls-proxy-nginx
+    machine-learning

doc/guides/applications/machine-learning.rst

@@ -0,0 +1,55 @@
+..  SPDX-License-Identifier: Marvell-MIT
+    Copyright (c) 2024 Marvell.
+
+****************
+Machine Learning
+****************
+
+Introduction
+============
+
+The Data Plane Development Kit (DPDK) is an open-source software project managed by the Linux Foundation. It is designed to offload TCP packet processing from the operating system kernel to user-space processes, thereby enhancing computing efficiency and packet throughput.
+
+The ``dpdk-test-mldev`` tool is a DPDK application designed to test various machine learning (mldev) use cases. As part of the DAO package, it provides a way for users to run inference operations with specific inputs. The current DAO release provides int8 ( ``resnet50_int8_t08_b01`` ) and fp16 ( ``resnet50_fp16_t08_b01`` ) quantized versions of Resnet50 models, which can be used for running inference operations.
+
+.. note::
+    For detailed documentation related to dpdk-test-mldev, refer to `documentation <https://doc.dpdk.org/guides/tools/testmldev.html>`_
+
+Preprocessing of Input
+======================
+
+Involves converting the input image format to a binary format that the model can accept as an input. This is done using the ``image2bin.py`` Python script.
+
+.. code-block:: console
+
+    # Convert input in Image format to binary format
+    python image2bin.py \
+    --image_file input.jpeg \
+    --bin_file output.bin
+
+Model Execution
+===============
+
+The preprocessed binary is given as an input to the model. The model processes the input, runs the inference operation, and generates the output in binary format.
+
+.. code-block:: console
+
+    # Run inferences with dpdk-test-mldev application
+    dpdk-test-mldev --lcores=4-23 -a 0000:00:10.0,fw_path=/lib/firmware/mlip-fw.bin -- \
+    --test inference_ordered \
+    --filelist model.tar,input.bin,output.bin,reference.bin \
+    --tolerance 5 \
+    --stats \
+    --repetitions 1000
+
+Postprocessing of Output
+========================
+
+The binary output generated by the model is converted into a JSON file for easier interpretation and analysis. This is done using the ``bin2json.py`` Python script.
+
+.. code-block:: console
+
+    # Convert output in binary format to JSON format
+    python bin2json.py \
+    --bin_file output.bin \
+    --json_file output.json