jetson-examples 0.0.6__tar.gz → 0.0.8__tar.gz

{jetson_examples-0.0.6 → jetson_examples-0.0.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: jetson-examples
-Version: 0.0.6
+Version: 0.0.8
 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
@@ -33,6 +33,7 @@ pip install jetson-examples
 ```
 
 - [more installation methods](./docs/install.md)
+- If you have already installed, you can use `pip install jetson-examples --upgrade` to update.
 
 ## Quickstart
 
@@ -48,15 +49,17 @@ reComputer supports a list of examples from [jetson-ai-lab](https://www.jetson-a
 
 Here are some examples that can be run:
 
-| Example                | Type                     | Model/Data Size | Image Size | Command                                 |
-| ---------------------- | ------------------------ | --------------- | ---------- | --------------------------------------- |
-| text-generation-webui  | Text (LLM)               | 3.9GB           | 14.8GB     | `reComputer run text-generation-webui`  |
-| LLaVA                  | Text + Vision (VLM)      | 13GB            | 14.4GB     | `reComputer run llava`                  |
-| stable-diffusion-webui | Image Generation         | 3.97G           | 7.3GB      | `reComputer run stable-diffusion-webui` |
-| nanoowl                | Vision Transformers(ViT) | 613MB           | 15.1GB     | `reComputer run nanoowl`                |
-| nanodb                 | Vector Database          | 76GB            | 7.0GB      | `reComputer run nanodb`                 |
-| whisper                | Audio                    | 1.5GB           | 6.0GB      | `reComputer run whisper`                |
-
+| Example                                          | Type                     | Model/Data Size | Image Size | Command                                 |
+| ------------------------------------------------ | ------------------------ | --------------- | ---------- | --------------------------------------- |
+| 🆕 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` |
+| nanoowl                                          | Vision Transformers(ViT) | 613MB           | 15.1GB     | `reComputer run nanoowl`                |
+| [nanodb](../reComputer/scripts/nanodb/readme.md) | Vector Database          | 76GB            | 7.0GB      | `reComputer run nanodb`                 |
+| whisper                                          | Audio                    | 1.5GB           | 6.0GB      | `reComputer run whisper`                |
+| [yolov8-counter](/reComputer/scripts/yolov8-counter/readme.md) |Computer Vision | 6M | 13.8GB  | `reComputer run yolov8_counter`  |
 > Note: You should have enough space to run example, like `LLaVA`, at least `27.4GB` totally
 
 More Examples can be found [examples.md](./docs/examples.md)

{jetson_examples-0.0.6 → jetson_examples-0.0.8}/README.md

@@ -18,6 +18,7 @@ pip install jetson-examples
 ```
 
 - [more installation methods](./docs/install.md)
+- If you have already installed, you can use `pip install jetson-examples --upgrade` to update.
 
 ## Quickstart
 
@@ -33,15 +34,17 @@ reComputer supports a list of examples from [jetson-ai-lab](https://www.jetson-a
 
 Here are some examples that can be run:
 
-| Example                | Type                     | Model/Data Size | Image Size | Command                                 |
-| ---------------------- | ------------------------ | --------------- | ---------- | --------------------------------------- |
-| text-generation-webui  | Text (LLM)               | 3.9GB           | 14.8GB     | `reComputer run text-generation-webui`  |
-| LLaVA                  | Text + Vision (VLM)      | 13GB            | 14.4GB     | `reComputer run llava`                  |
-| stable-diffusion-webui | Image Generation         | 3.97G           | 7.3GB      | `reComputer run stable-diffusion-webui` |
-| nanoowl                | Vision Transformers(ViT) | 613MB           | 15.1GB     | `reComputer run nanoowl`                |
-| nanodb                 | Vector Database          | 76GB            | 7.0GB      | `reComputer run nanodb`                 |
-| whisper                | Audio                    | 1.5GB           | 6.0GB      | `reComputer run whisper`                |
-
+| Example                                          | Type                     | Model/Data Size | Image Size | Command                                 |
+| ------------------------------------------------ | ------------------------ | --------------- | ---------- | --------------------------------------- |
+| 🆕 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` |
+| nanoowl                                          | Vision Transformers(ViT) | 613MB           | 15.1GB     | `reComputer run nanoowl`                |
+| [nanodb](../reComputer/scripts/nanodb/readme.md) | Vector Database          | 76GB            | 7.0GB      | `reComputer run nanodb`                 |
+| whisper                                          | Audio                    | 1.5GB           | 6.0GB      | `reComputer run whisper`                |
+| [yolov8-counter](/reComputer/scripts/yolov8-counter/readme.md) |Computer Vision | 6M | 13.8GB  | `reComputer run yolov8_counter`  |
 > Note: You should have enough space to run example, like `LLaVA`, at least `27.4GB` totally
 
 More Examples can be found [examples.md](./docs/examples.md)

{jetson_examples-0.0.6 → jetson_examples-0.0.8}/jetson_examples.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: jetson-examples
-Version: 0.0.6
+Version: 0.0.8
 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
@@ -33,6 +33,7 @@ pip install jetson-examples
 ```
 
 - [more installation methods](./docs/install.md)
+- If you have already installed, you can use `pip install jetson-examples --upgrade` to update.
 
 ## Quickstart
 
@@ -48,15 +49,17 @@ reComputer supports a list of examples from [jetson-ai-lab](https://www.jetson-a
 
 Here are some examples that can be run:
 
-| Example                | Type                     | Model/Data Size | Image Size | Command                                 |
-| ---------------------- | ------------------------ | --------------- | ---------- | --------------------------------------- |
-| text-generation-webui  | Text (LLM)               | 3.9GB           | 14.8GB     | `reComputer run text-generation-webui`  |
-| LLaVA                  | Text + Vision (VLM)      | 13GB            | 14.4GB     | `reComputer run llava`                  |
-| stable-diffusion-webui | Image Generation         | 3.97G           | 7.3GB      | `reComputer run stable-diffusion-webui` |
-| nanoowl                | Vision Transformers(ViT) | 613MB           | 15.1GB     | `reComputer run nanoowl`                |
-| nanodb                 | Vector Database          | 76GB            | 7.0GB      | `reComputer run nanodb`                 |
-| whisper                | Audio                    | 1.5GB           | 6.0GB      | `reComputer run whisper`                |
-
+| Example                                          | Type                     | Model/Data Size | Image Size | Command                                 |
+| ------------------------------------------------ | ------------------------ | --------------- | ---------- | --------------------------------------- |
+| 🆕 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` |
+| nanoowl                                          | Vision Transformers(ViT) | 613MB           | 15.1GB     | `reComputer run nanoowl`                |
+| [nanodb](../reComputer/scripts/nanodb/readme.md) | Vector Database          | 76GB            | 7.0GB      | `reComputer run nanodb`                 |
+| whisper                                          | Audio                    | 1.5GB           | 6.0GB      | `reComputer run whisper`                |
+| [yolov8-counter](/reComputer/scripts/yolov8-counter/readme.md) |Computer Vision | 6M | 13.8GB  | `reComputer run yolov8_counter`  |
 > Note: You should have enough space to run example, like `LLaVA`, at least `27.4GB` totally
 
 More Examples can be found [examples.md](./docs/examples.md)

{jetson_examples-0.0.6 → jetson_examples-0.0.8}/jetson_examples.egg-info/SOURCES.txt

@@ -12,8 +12,6 @@ reComputer/scripts/check.sh
 reComputer/scripts/run.sh
 reComputer/scripts/update.sh
 reComputer/scripts/Sheared-LLaMA-2.7B-ShareGPT/run.sh
-reComputer/scripts/hello-world/readme.md
-reComputer/scripts/hello-world/run.sh
 reComputer/scripts/live-llava/run.sh
 reComputer/scripts/llama3/run.sh
 reComputer/scripts/llava/run.sh
@@ -25,4 +23,6 @@ reComputer/scripts/nanoowl/run.sh
 reComputer/scripts/ollama/run.sh
 reComputer/scripts/stable-diffusion-webui/run.sh
 reComputer/scripts/text-generation-webui/run.sh
-reComputer/scripts/whisper/run.sh
+reComputer/scripts/whisper/run.sh
+reComputer/scripts/yolov8-counter/readme.md
+reComputer/scripts/yolov8-counter/run.sh

{jetson_examples-0.0.6 → jetson_examples-0.0.8}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "jetson-examples"
-version = "0.0.6"
+version = "0.0.8"
 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-0.0.8/reComputer/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.0.7"

{jetson_examples-0.0.6 → jetson_examples-0.0.8}/reComputer/scripts/nanodb/run.sh

@@ -3,6 +3,31 @@
 BASE_PATH=/home/$USER/reComputer
 JETSON_REPO_PATH="$BASE_PATH/jetson-containers"
 
+check_disk_space() {
+    directory="$1"  # a directory
+    required_space_gb="$2"  # how many GB we need
+    
+    # get disk of directory
+    device=$(df -P "$directory" | awk 'NR==2 {print $1}')
+    echo $device
+    
+    # get free space in KB
+    free_space=$(df -P "$device" | awk 'NR==2 {print $4}')
+    echo $free_space
+    
+    # change unit to GB
+    free_space_gb=$(echo "scale=2; $free_space / 1024 / 1024" | bc)
+    echo $free_space_gb
+    
+    # check and fast-fail
+    if (( $(echo "$free_space_gb >= $required_space_gb" | bc -l) )); then
+        echo "disk space ($1) enough, keep going."
+    else
+        echo "disk space ($1) not enough!! we need $2 GB!!"
+        exit 1
+    fi
+}
+
 # check data files TODO: support params to force download
 DATA_PATH="$JETSON_REPO_PATH/data/datasets/coco/2017"
 if [ ! -d $DATA_PATH ]; then

{jetson_examples-0.0.6 → jetson_examples-0.0.8}/reComputer/scripts/run.sh

@@ -18,31 +18,6 @@ check_is_jetson_or_not() {
 }
 check_is_jetson_or_not
 
-check_disk_space() {
-    directory="$1"  # a directory
-    required_space_gb="$2"  # how many GB we need
-    
-    # get disk of directory
-    device=$(df -P "$directory" | awk 'NR==2 {print $1}')
-    echo $device
-    
-    # get free space in KB
-    free_space=$(df -P "$device" | awk 'NR==2 {print $4}')
-    echo $free_space
-    
-    # change unit to GB
-    free_space_gb=$(echo "scale=2; $free_space / 1024 / 1024" | bc)
-    echo $free_space_gb
-    
-    # check and fast-fail
-    if (( $(echo "$free_space_gb >= $required_space_gb" | bc -l) )); then
-        echo "disk space ($1) enough, keep going."
-    else
-        echo "disk space ($1) not enough!! we need $2 GB!!"
-        exit 1
-    fi
-}
-
 echo "run example：$1"
 BASE_PATH=/home/$USER/reComputer
 

jetson_examples-0.0.8/reComputer/scripts/yolov8-counter/readme.md

@@ -0,0 +1,37 @@
+# Abstract
+This script facilitates YOLOv8 in counting retail products, enabling real-time detection of items removed from the shelf by users. 
+The project includes a test video located in the ```/video``` directory within a Docker container, with the test results saved in ```/result``` and subsequently transmitted to the host Home directory via Docker.
+
+## Install
+
+
+PyPI(recommend)
+
+```sh
+pip install jetson-examples
+```
+
+Linux (github trick)
+```sh
+curl -fsSL https://raw.githubusercontent.com/Seeed-Projects/jetson-examples/main/install.sh | sh
+```
+
+Github (for Developer)
+
+```sh
+git clone https://github.com/Seeed-Projects/jetson-examples
+cd jetson-examples
+pip install .
+```
+
+## Quickstart
+```sh
+reComputer run yolov8-counter
+```
+## TODO List
+- [ ] Add a host-side visual terminal interface for yolov8-counter.
+
+## FAQs
+1. The project has been tested on the Jetson Orin platform, and its execution entails the use of Docker; therefore, it is essential to ensure that all necessary Docker components are fully installed and functional.
+2. During program execution, you may encounter an ```ERROR: Could not open requirements file.``` This error message does not impact the normal operation of the program and can be safely ignored.
+3. Currently, real-time visualization of test results from within the Docker container to the host terminal is not supported. However, post-detection outcomes are copied from the container's image to the ```/Home/result``` directory on the host system for review.

jetson_examples-0.0.8/reComputer/scripts/yolov8-counter/run.sh

@@ -0,0 +1,25 @@
+#!/bin/bash
+
+docker pull yaohui1998/yolov8_counter
+
+if [ "$(docker ps -aq -f name=counter)" ]; then
+    echo "Found existing container named counter. Executing Python script inside the container..."
+    docker start counter
+    docker exec counter python3 yolo_counting.py
+    docker cp counter:/usr/src/ultralytics/result/ ~/
+else
+    echo "No existing container named counter found. Pulling image and running container..."
+    docker run -it -d --network host \
+    --ipc=host \
+    --runtime=nvidia \
+    -v /tmp/.X11-unix:/tmp/.X11-unix:ro \
+    -v /home:/home \
+    -e DISPLAY=:0 \
+    --privileged \
+    --name yolov8_counter \
+    --device=/dev/*:/dev/*  \
+    yaohui1998/yolov8_counter
+    docker exec yolov8_counter python3 yolo_counting.py
+    docker cp -r yolov8_counter:/usr/src/ultralytics/result/ ~/
+
+fi

jetson_examples-0.0.6/reComputer/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.0.6"

jetson_examples-0.0.6/reComputer/scripts/hello-world/readme.md

@@ -1,3 +0,0 @@
-# hello-world
-
-- print `hello-world` to show how to add your project into this package

jetson_examples-0.0.6/reComputer/scripts/hello-world/run.sh

@@ -1,9 +0,0 @@
-#!/bin/bash
-./run.sh $(./autotag llava) \
-python3 -m nano_llm.agents.video_query --api=mlc \
---model Efficient-Large-Model/VILA-2.7b \
---max-context-len 768 \
---max-new-tokens 32 \
---video-input /dev/video0 \
---video-output webrtc://@:8554/output \
---nanodb /data/nanodb/coco/2017