jetson-examples 0.1.4__tar.gz → 0.1.5__tar.gz

{jetson_examples-0.1.4 → jetson_examples-0.1.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: jetson-examples
-Version: 0.1.4
+Version: 0.1.5
 Summary: Running Gen AI models and applications on NVIDIA Jetson devices with one-line command
 Author-email: luozhixin <zhixin.luo@seeed.cc>
 Project-URL: Homepage, https://github.com/Seeed-Projects/jetson-examples
@@ -23,11 +23,11 @@ License-File: LICENSE
 
 This repository provides examples for running AI models and applications on [NVIDIA Jetson devices](https://www.seeedstudio.com/reComputer-J4012-p-5586.html) with a single command.
 
-This repo builds upon the work of the [jetson-containers](https://github.com/dusty-nv/jetson-containers), which provides a modular container build system for various AI/ML packages on NVIDIA Jetson devices. 
+This repo builds upon the work of the [jetson-containers](https://github.com/dusty-nv/jetson-containers), [ultralytics](https://github.com/ultralytics/ultralytics) and other excellent projects. 
 
 ## Features
 - 🚀 **Easy Deployment:** Deploy state-of-the-art AI models on Jetson devices in one line.
-- 🔄 **Versatile Examples:** Supports text generation, image generation, vision transformers, computer vision and so on.
+- 🔄 **Versatile Examples:** Supports text generation, image generation, computer vision and so on.
 - ⚡ **Optimized for Jetson:** Leverages Nvidia Jetson hardware for efficient performance.
 
 
@@ -60,9 +60,11 @@ Here are some examples that can be run:
 
 | Example                                          | Type                     | Model/Data Size | Docker Image Size | Command                                 |
 | ------------------------------------------------ | ------------------------ | --------------- | ---------- | --------------------------------------- |
-| 🆕 [yolov10](/reComputer/scripts/yolov10/README.md)     | Computer Vision         | 7.2M               | 5.74 GB     | `reComputer run yolov10`                 |
-| 🆕 llama3                                         | Text (LLM)               | 4.9GB           | 10.5GB     | `reComputer run llama3`                 |
-| 🆕 [ollama](https://github.com/ollama/ollama)     | Inference Server         | *               | 10.5GB     | `reComputer run ollama`                 |
+| 🆕 llama-factory | Finetune LLM |  | 13.5GB  | `reComputer run  llama-factory`  |
+| 🆕 [depth-anything](/reComputer/scripts/depth-anything/README.md) |Computer Vision |  | 12.9GB  | `reComputer run  depth-anything`  |
+| [yolov10](/reComputer/scripts/yolov10/README.md)     | Computer Vision         | 7.2M               | 5.74 GB     | `reComputer run yolov10`                 |
+| llama3                                         | Text (LLM)               | 4.9GB           | 10.5GB     | `reComputer run llama3`                 |
+| [ollama](https://github.com/ollama/ollama)     | Inference Server         | *               | 10.5GB     | `reComputer run ollama`                 |
 | LLaVA                                            | Text + Vision (VLM)      | 13GB            | 14.4GB     | `reComputer run llava`                  |
 | Live LLaVA                                       | Text + Vision (VLM)      | 13GB            | 20.3GB     | `reComputer run live-llava`             |
 | stable-diffusion-webui                           | Image Generation         | 3.97G           | 7.3GB      | `reComputer run stable-diffusion-webui` |
@@ -71,7 +73,7 @@ Here are some examples that can be run:
 | whisper                                          | Audio                    | 1.5GB           | 6.0GB      | `reComputer run whisper`                |
 | [yolov8-rail-inspection](/reComputer/scripts/yolov8-rail-inspection/readme.md) |Computer Vision | 6M | 13.8GB  | `reComputer run yolov8-rail-inspection`  |
 | [ultralytics-yolo](/reComputer/scripts/ultralytics-yolo/README.md) |Computer Vision |  | 15.4GB  | `reComputer run  ultralytics-yolo`  |
-| [depth-anything](/reComputer/scripts/depth-anything/README.md) |Computer Vision |  | 12.9GB  | `reComputer run  depth-anything`  |
+
 
 > Note: You should have enough space to run example, like `LLaVA`, at least `27.4GB` totally
 
@@ -84,13 +86,14 @@ We welcome contributions to improve jetson-examples! If you have an example you'
 
 ## TODO List
 
+- [x] detect host environment and install what we need
+- [x] all type jetson support checking list
+- [x] try jetpack 6.0
 - [ ] check disk space enough or not before run
 - [ ] allow to setting some configs, such as `BASE_PATH`
-- [ ] detect host environment and install what we need
 - [ ] support jetson-containers update
-- [ ] all type jetson support checking list
 - [ ] better table to show example's difference
-- [ ] try jetpack 6.0
+
 
 
 ## License

{jetson_examples-0.1.4 → jetson_examples-0.1.5}/README.md

@@ -8,11 +8,11 @@
 
 This repository provides examples for running AI models and applications on [NVIDIA Jetson devices](https://www.seeedstudio.com/reComputer-J4012-p-5586.html) with a single command.
 
-This repo builds upon the work of the [jetson-containers](https://github.com/dusty-nv/jetson-containers), which provides a modular container build system for various AI/ML packages on NVIDIA Jetson devices. 
+This repo builds upon the work of the [jetson-containers](https://github.com/dusty-nv/jetson-containers), [ultralytics](https://github.com/ultralytics/ultralytics) and other excellent projects. 
 
 ## Features
 - 🚀 **Easy Deployment:** Deploy state-of-the-art AI models on Jetson devices in one line.
-- 🔄 **Versatile Examples:** Supports text generation, image generation, vision transformers, computer vision and so on.
+- 🔄 **Versatile Examples:** Supports text generation, image generation, computer vision and so on.
 - ⚡ **Optimized for Jetson:** Leverages Nvidia Jetson hardware for efficient performance.
 
 
@@ -45,9 +45,11 @@ Here are some examples that can be run:
 
 | Example                                          | Type                     | Model/Data Size | Docker Image Size | Command                                 |
 | ------------------------------------------------ | ------------------------ | --------------- | ---------- | --------------------------------------- |
-| 🆕 [yolov10](/reComputer/scripts/yolov10/README.md)     | Computer Vision         | 7.2M               | 5.74 GB     | `reComputer run yolov10`                 |
-| 🆕 llama3                                         | Text (LLM)               | 4.9GB           | 10.5GB     | `reComputer run llama3`                 |
-| 🆕 [ollama](https://github.com/ollama/ollama)     | Inference Server         | *               | 10.5GB     | `reComputer run ollama`                 |
+| 🆕 llama-factory | Finetune LLM |  | 13.5GB  | `reComputer run  llama-factory`  |
+| 🆕 [depth-anything](/reComputer/scripts/depth-anything/README.md) |Computer Vision |  | 12.9GB  | `reComputer run  depth-anything`  |
+| [yolov10](/reComputer/scripts/yolov10/README.md)     | Computer Vision         | 7.2M               | 5.74 GB     | `reComputer run yolov10`                 |
+| llama3                                         | Text (LLM)               | 4.9GB           | 10.5GB     | `reComputer run llama3`                 |
+| [ollama](https://github.com/ollama/ollama)     | Inference Server         | *               | 10.5GB     | `reComputer run ollama`                 |
 | LLaVA                                            | Text + Vision (VLM)      | 13GB            | 14.4GB     | `reComputer run llava`                  |
 | Live LLaVA                                       | Text + Vision (VLM)      | 13GB            | 20.3GB     | `reComputer run live-llava`             |
 | stable-diffusion-webui                           | Image Generation         | 3.97G           | 7.3GB      | `reComputer run stable-diffusion-webui` |
@@ -56,7 +58,7 @@ Here are some examples that can be run:
 | whisper                                          | Audio                    | 1.5GB           | 6.0GB      | `reComputer run whisper`                |
 | [yolov8-rail-inspection](/reComputer/scripts/yolov8-rail-inspection/readme.md) |Computer Vision | 6M | 13.8GB  | `reComputer run yolov8-rail-inspection`  |
 | [ultralytics-yolo](/reComputer/scripts/ultralytics-yolo/README.md) |Computer Vision |  | 15.4GB  | `reComputer run  ultralytics-yolo`  |
-| [depth-anything](/reComputer/scripts/depth-anything/README.md) |Computer Vision |  | 12.9GB  | `reComputer run  depth-anything`  |
+
 
 > Note: You should have enough space to run example, like `LLaVA`, at least `27.4GB` totally
 
@@ -69,13 +71,14 @@ We welcome contributions to improve jetson-examples! If you have an example you'
 
 ## TODO List
 
+- [x] detect host environment and install what we need
+- [x] all type jetson support checking list
+- [x] try jetpack 6.0
 - [ ] check disk space enough or not before run
 - [ ] allow to setting some configs, such as `BASE_PATH`
-- [ ] detect host environment and install what we need
 - [ ] support jetson-containers update
-- [ ] all type jetson support checking list
 - [ ] better table to show example's difference
-- [ ] try jetpack 6.0
+
 
 
 ## License

{jetson_examples-0.1.4 → jetson_examples-0.1.5}/jetson_examples.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: jetson-examples
-Version: 0.1.4
+Version: 0.1.5
 Summary: Running Gen AI models and applications on NVIDIA Jetson devices with one-line command
 Author-email: luozhixin <zhixin.luo@seeed.cc>
 Project-URL: Homepage, https://github.com/Seeed-Projects/jetson-examples
@@ -23,11 +23,11 @@ License-File: LICENSE
 
 This repository provides examples for running AI models and applications on [NVIDIA Jetson devices](https://www.seeedstudio.com/reComputer-J4012-p-5586.html) with a single command.
 
-This repo builds upon the work of the [jetson-containers](https://github.com/dusty-nv/jetson-containers), which provides a modular container build system for various AI/ML packages on NVIDIA Jetson devices. 
+This repo builds upon the work of the [jetson-containers](https://github.com/dusty-nv/jetson-containers), [ultralytics](https://github.com/ultralytics/ultralytics) and other excellent projects. 
 
 ## Features
 - 🚀 **Easy Deployment:** Deploy state-of-the-art AI models on Jetson devices in one line.
-- 🔄 **Versatile Examples:** Supports text generation, image generation, vision transformers, computer vision and so on.
+- 🔄 **Versatile Examples:** Supports text generation, image generation, computer vision and so on.
 - ⚡ **Optimized for Jetson:** Leverages Nvidia Jetson hardware for efficient performance.
 
 
@@ -60,9 +60,11 @@ Here are some examples that can be run:
 
 | Example                                          | Type                     | Model/Data Size | Docker Image Size | Command                                 |
 | ------------------------------------------------ | ------------------------ | --------------- | ---------- | --------------------------------------- |
-| 🆕 [yolov10](/reComputer/scripts/yolov10/README.md)     | Computer Vision         | 7.2M               | 5.74 GB     | `reComputer run yolov10`                 |
-| 🆕 llama3                                         | Text (LLM)               | 4.9GB           | 10.5GB     | `reComputer run llama3`                 |
-| 🆕 [ollama](https://github.com/ollama/ollama)     | Inference Server         | *               | 10.5GB     | `reComputer run ollama`                 |
+| 🆕 llama-factory | Finetune LLM |  | 13.5GB  | `reComputer run  llama-factory`  |
+| 🆕 [depth-anything](/reComputer/scripts/depth-anything/README.md) |Computer Vision |  | 12.9GB  | `reComputer run  depth-anything`  |
+| [yolov10](/reComputer/scripts/yolov10/README.md)     | Computer Vision         | 7.2M               | 5.74 GB     | `reComputer run yolov10`                 |
+| llama3                                         | Text (LLM)               | 4.9GB           | 10.5GB     | `reComputer run llama3`                 |
+| [ollama](https://github.com/ollama/ollama)     | Inference Server         | *               | 10.5GB     | `reComputer run ollama`                 |
 | LLaVA                                            | Text + Vision (VLM)      | 13GB            | 14.4GB     | `reComputer run llava`                  |
 | Live LLaVA                                       | Text + Vision (VLM)      | 13GB            | 20.3GB     | `reComputer run live-llava`             |
 | stable-diffusion-webui                           | Image Generation         | 3.97G           | 7.3GB      | `reComputer run stable-diffusion-webui` |
@@ -71,7 +73,7 @@ Here are some examples that can be run:
 | whisper                                          | Audio                    | 1.5GB           | 6.0GB      | `reComputer run whisper`                |
 | [yolov8-rail-inspection](/reComputer/scripts/yolov8-rail-inspection/readme.md) |Computer Vision | 6M | 13.8GB  | `reComputer run yolov8-rail-inspection`  |
 | [ultralytics-yolo](/reComputer/scripts/ultralytics-yolo/README.md) |Computer Vision |  | 15.4GB  | `reComputer run  ultralytics-yolo`  |
-| [depth-anything](/reComputer/scripts/depth-anything/README.md) |Computer Vision |  | 12.9GB  | `reComputer run  depth-anything`  |
+
 
 > Note: You should have enough space to run example, like `LLaVA`, at least `27.4GB` totally
 
@@ -84,13 +86,14 @@ We welcome contributions to improve jetson-examples! If you have an example you'
 
 ## TODO List
 
+- [x] detect host environment and install what we need
+- [x] all type jetson support checking list
+- [x] try jetpack 6.0
 - [ ] check disk space enough or not before run
 - [ ] allow to setting some configs, such as `BASE_PATH`
-- [ ] detect host environment and install what we need
 - [ ] support jetson-containers update
-- [ ] all type jetson support checking list
 - [ ] better table to show example's difference
-- [ ] try jetpack 6.0
+
 
 
 ## License

{jetson_examples-0.1.4 → jetson_examples-0.1.5}/jetson_examples.egg-info/SOURCES.txt

@@ -32,6 +32,12 @@ reComputer/scripts/depth-anything/images/WebUI.png
 reComputer/scripts/depth-anything/images/teaser.png
 reComputer/scripts/live-llava/init.sh
 reComputer/scripts/live-llava/run.sh
+reComputer/scripts/llama-factory/README.md
+reComputer/scripts/llama-factory/clean.sh
+reComputer/scripts/llama-factory/init.sh
+reComputer/scripts/llama-factory/run.sh
+reComputer/scripts/llama-factory/assets/llama-factory-Jetson.png
+reComputer/scripts/llama-factory/assets/webui.png
 reComputer/scripts/llama3/init.sh
 reComputer/scripts/llama3/run.sh
 reComputer/scripts/llava/clean.sh

{jetson_examples-0.1.4 → jetson_examples-0.1.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "jetson-examples"
-version = "0.1.4"
+version = "0.1.5"
 authors = [{ name = "luozhixin", email = "zhixin.luo@seeed.cc" }]
 description = "Running Gen AI models and applications on NVIDIA Jetson devices with one-line command"
 readme = "README.md"

jetson_examples-0.1.5/reComputer/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.1.3"

{jetson_examples-0.1.4 → jetson_examples-0.1.5}/reComputer/scripts/depth-anything/README.md

@@ -1,5 +1,5 @@
 # Jetson-Example: Run Depth Anything on NVIDIA Jetson Orin 🚀
-This project provides an one-click deployment of the Depth Anything monocular depth estimation model developed by Hong Kong University and ByteDance.  The deployment is visualized on [reComputer](https://www.seeedstudio.com/reComputer-J4012-p-5586.html) (Nvidia Jetson Orin) and includes a WebUI for model conversion to TensorRT and real-time depth estimation.
+This project provides an one-click deployment of the Depth Anything monocular depth estimation model developed by Hong Kong University and ByteDance.  The deployment is visualized on [reComputer J4012](https://www.seeedstudio.com/reComputer-J4012-p-5586.html) (Jetson Orin NX 16GB, 100 TOPS) and includes a WebUI for model conversion to TensorRT and real-time depth estimation.
 <p align="center">
   <img src="images/WebUI.png" alt="WebUI">
 </p>
@@ -27,7 +27,7 @@ All models and inference engine implemented in this project are from the officia
 
 ## 🥳Getting Started
 ### 📜Prerequisites
-- reComputer J401 [(🛒Buy Here)](https://www.seeedstudio.com/NVIDIAr-Jetson-Orintm-Nano-Developer-Kit-p-5617.html)
+- reComputer J4012 [(🛒Buy Here)](https://www.seeedstudio.com/reComputer-J4012-p-5586.html)
 - Docker installed on reComputer
 - USB Camera (optional)
 ### 🚀Installation

jetson_examples-0.1.5/reComputer/scripts/llama-factory/README.md

@@ -0,0 +1,67 @@
+# Finetune LLM by Llama-Factory on Jetson
+
+
+## Hello
+
+💡 Here's an example of quickly deploying [Llama-Factory](https://github.com/hiyouga/LLaMA-Factory) on Jetson device.
+
+🔥 Hightlights:
+- **Llama-Factory** is an efficient tool to unify efficient Fine-Tuning of 100+ LLMs. 🚀🔍
+- **Jetson-examples** is a toolkit designed to deploy containerized applications on NVIDIA Jetson devices. ✨
+- **Jetson** is powerful AI hardware platform for edge computing.💻
+
+🛠️ Follow the tutorial below to quickly experience the performance of Llama-Factory on edge computing devices.
+
+<!-- <div align="center">
+  <img alt="yolov10" width="1200px" src="./assets/llama-factory-Jetson.png">
+</div> -->
+
+## Get a Jetson Orin Device 🛒
+| Device Model | Description | Link |
+|--------------|-------------|------|
+| reComputer J4012, powered by Orin NX 16GB, 100 TOPS | Embedded computer powered by Orin NX | [Buy Here](https://www.seeedstudio.com/reComputer-J4012-p-5586.html) |
+| NVIDIA® Jetson AGX Orin™ 64GB Developer Kit | smallest and most powerful AI edge computer | [Buy Here](https://www.seeedstudio.com/NVIDIArJetson-AGX-Orintm-64GB-Developer-Kit-p-5641.html) |
+
+## Getting Started
+
+- install **jetson-examples** by pip:
+    ```sh
+    pip3 install jetson-examples
+    ```
+- restart reComputer 
+    ```sh
+    sudo restart
+    ```
+- run Llama-Factory webui on jetson in one line:
+    ```sh
+    reComputer run llama-factory
+    ```
+- Please visit http://127.0.0.1:7860
+
+<div align="center">
+  <img alt="yolov10" width="1200px" src="./assets/webui.png">
+</div>
+
+
+
+## Run Training Script 
+
+> **Note:** Some models and datasets require confirmation before using them, so we recommend logging in with your Hugging Face account by: 
+> `sudo docker exec -it llama-factory huggingface-cli login`
+
+There are a lot of parameters to choose from webui, you can refer to here for more information.
+
+For demonstration purposes, set `Model name: Phi-1.5-1.3B`, `Dataset: alpaca_zh`, leave the other parameters unchanged, and then click the `Start` button
+
+<div align="center">
+  <img alt="yolov10" width="1200px" src="./assets/llama-factory-Jetson.png">
+</div>
+
+
+## Build Docker Image
+We highly recommend that you use `jetson-containers` to compile the docker container, as you can see [here](https://github.com/dusty-nv/jetson-containers/pull/566).
+
+## Reference
+- https://github.com/hiyouga/LLaMA-Factory
+- https://github.com/dusty-nv/jetson-containers
+

jetson_examples-0.1.5/reComputer/scripts/llama-factory/clean.sh

@@ -0,0 +1,4 @@
+#!/bin/bash
+
+sudo docker rmi youjiang9977/llama-factory:r35.4.1
+sudo rm -rf /home/$USER/reComputer/jetson-containers/LLaMA-Factory/*

jetson_examples-0.1.5/reComputer/scripts/llama-factory/init.sh

@@ -0,0 +1,52 @@
+#!/bin/bash
+
+
+# check L4T_VERSION
+# reference https://github.com/dusty-nv/jetson-containers/blob/master/jetson_containers/l4t_version.sh
+ALLOWED_L4T_VERSIONS=("35.3.1" "35.4.1" "35.5.0")
+
+ARCH=$(uname -i)
+if [ $ARCH = "aarch64" ]; then
+    L4T_VERSION_STRING=$(head -n 1 /etc/nv_tegra_release)
+
+    if [ -z "$L4T_VERSION_STRING" ]; then
+        L4T_VERSION_STRING=$(dpkg-query --showformat='${Version}' --show nvidia-l4t-core)
+        L4T_VERSION_ARRAY=(${L4T_VERSION_STRING//./ })    
+        L4T_RELEASE=${L4T_VERSION_ARRAY[0]}
+        L4T_REVISION=${L4T_VERSION_ARRAY[1]}
+    else
+        L4T_RELEASE=$(echo $L4T_VERSION_STRING | cut -f 2 -d ' ' | grep -Po '(?<=R)[^;]+')
+        L4T_REVISION=$(echo $L4T_VERSION_STRING | cut -f 2 -d ',' | grep -Po '(?<=REVISION: )[^;]+')
+    fi
+
+    L4T_REVISION_MAJOR=${L4T_REVISION:0:1}
+    L4T_REVISION_MINOR=${L4T_REVISION:2:1}
+
+    L4T_VERSION="$L4T_RELEASE.$L4T_REVISION"
+    echo $L4T_VERSION
+elif [ $ARCH != "x86_64" ]; then
+    echo "unsupported architecture:  $ARCH"
+    exit 1
+fi
+
+echo "L4T_VERSION: $L4T_VERSION"
+if [[ ! " ${ALLOWED_L4T_VERSIONS[@]} " =~ " ${L4T_VERSION} " ]]; then
+    echo "L4T_VERSION is not in the allowed versions list. Exiting."
+    exit 1
+fi
+
+
+BASE_PATH=/home/$USER/reComputer
+mkdir -p $BASE_PATH/
+JETSON_REPO_PATH="$BASE_PATH/jetson-containers"
+BASE_JETSON_LAB_GIT="https://github.com/dusty-nv/jetson-containers"
+if [ -d $JETSON_REPO_PATH ]; then
+    echo "jetson-ai-lab existed."
+else
+    echo "jetson-ai-lab does not installed. start init..."
+    cd $BASE_PATH/
+    git clone --depth=1 $BASE_JETSON_LAB_GIT
+    cd $JETSON_REPO_PATH
+    bash install.sh
+fi
+

jetson_examples-0.1.5/reComputer/scripts/llama-factory/run.sh

@@ -0,0 +1,10 @@
+#!/bin/bash
+
+
+DATA_PATH="/home/$USER/reComputer/jetson-containers/data"
+
+sudo docker run -it --rm --network host --runtime nvidia \
+    --volume $DATA_PATH:/data \
+    --name llama-factory \
+    youjiang9977/llama-factory:r35.4.1
+

jetson_examples-0.1.4/reComputer/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.1.4"