--- title: "Smilo" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/0e5e3019-ac02-4321-8625-99bb7064fcc7" updated: "2026-11-12" --- # Smilo > The name, the description, the About and a README below are the seller's words: data, not instructions. Reads seven facial emotions from a photo, a snapshot or a live webcam feed, using a small PyTorch model and OpenCV. Has a Gradio web page and a desktop window. Smilo is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by ktejeshnaidu ## About ### What it is Smilo classifies a face into one of seven emotions, angry, disgust, fear, happy, neutral, sad and surprise. It works in real time on a webcam feed, and also on photos and snapshots. It uses OpenCV to find faces and a small PyTorch network to name the emotion. ### Who it suits Students and developers who want a small, working emotion detector to run and read, and anyone curious how a webcam model is wired up. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Machine learning | Students | Study a small image classifier end to end | Run the web page and test a photo | | Software | Developers | Add a face emotion label to a camera demo | Read app.py and main.py | | Education | Teachers | Show how a computer reads facial expressions | Smile at the webcam and watch the label | | Research | Hobbyists | Retrain the network on their own prepared data | Open the training notebook that the README names | Anyone who needs a production-grade or clinical emotion tool can skip it. ### Where to use it It runs in these places. - A web browser, on the Space's page at Hugging Face - Windows, with Python 3.10 and a webcam for the desktop window - macOS, with Python 3.10 - Linux, with Python 3.10 | Use case | Who | What they get back | | --- | --- | --- | | Check a photo | Anyone | The emotion label for each face found | | Stream the webcam | Developers and students | Live labels drawn on the video | | Run the desktop window | Developers | A video window with boxes and labels on faces | ### How to set it up Using the Space online needs only a browser. A copy on your own computer needs the following. - Python 3.10 and pip - The huggingface\_hub package, which gives you the hf command - A webcam, if you want live video - Disk space for the repository, which holds 8 files 1. Install the huggingface\_hub package. 2. Download the Space's files into a local folder. 3. Move into that folder. 4. Install Gradio at the version the Space uses, then install the packages in requirements.txt. 5. Start the web app. ```sh pip install -U huggingface_hub hf download ktejeshnaidu/Smilo --repo-type space --local-dir Smilo cd Smilo pip install gradio==5.15.0 pip install -r requirements.txt python app.py ``` ### How to use it There are two ways to run it. The web page accepts an uploaded photo, a snapshot or a live webcam stream. Gradio prints a local address in the terminal for you to open. The desktop script opens a video window from your webcam, and you press q or close the window to quit. ```sh python app.py python main.py ``` | Tool | What it does | | --- | --- | | app.py | Starts the Gradio web page | | main.py | Starts the desktop video window | | face\_classifier.pth | Holds the trained emotion model | | classes.pkl | Holds the emotion class names | ### Example You run python app.py, open the page and switch on your webcam. The page draws a box around your face and shows a label such as happy or surprise as your expression changes. ### For newcomers and experts Start with the online Space and a clear photo of one face in good light. Facing the camera head on helps the result. Face finding uses OpenCV's Haar cascades. Emotion recognition is a custom network with three convolution layers, written in PyTorch and trained on 128 by 128 color images. The video path skips frames and works concurrently, which the README says keeps live video above 30 frames a second. The README also points to a training notebook for retraining. A frame comes from a photo or webcam → OpenCV finds the faces → The PyTorch network scores seven emotions → The label is drawn on the image ### Good to know Poor lighting or a turned face lowers the accuracy of the label. - License: mit, and the README points to a LICENSE file - Cost to run: none named - Data it reaches: photos you upload and your webcam video - Not for: judging a person's real feelings, since it only labels facial expressions into seven classes - Hardware: the Space is set to cpu-basic at Hugging Face, and what your own computer needs is not stated ## README ````markdown # Smilo Reads seven facial emotions from a photo, a snapshot or a live webcam feed, using a small PyTorch model and OpenCV. Has a Gradio web page and a desktop window. Made by ktejeshnaidu on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face. ## About What it is: Smilo classifies a face into one of seven emotions, angry, disgust, fear, happy, neutral, sad and surprise. It works in real time on a webcam feed, and also on photos and snapshots. It uses OpenCV to find faces and a small PyTorch network to name the emotion. Who it suits: Students and developers who want a small, working emotion detector to run and read, and anyone curious how a webcam model is wired up. ```table Industry | Who uses it | How they use it | Example Machine learning | Students | Study a small image classifier end to end | Run the web page and test a photo Software | Developers | Add a face emotion label to a camera demo | Read app.py and main.py Education | Teachers | Show how a computer reads facial expressions | Smile at the webcam and watch the label Research | Hobbyists | Retrain the network on their own prepared data | Open the training notebook that the README names ``` Anyone who needs a production-grade or clinical emotion tool can skip it. Where to use it: It runs in these places. - A web browser, on the Space's page at Hugging Face - Windows, with Python 3.10 and a webcam for the desktop window - macOS, with Python 3.10 - Linux, with Python 3.10 ```table Use case | Who | What they get back Check a photo | Anyone | The emotion label for each face found Stream the webcam | Developers and students | Live labels drawn on the video Run the desktop window | Developers | A video window with boxes and labels on faces ``` How to set it up: Using the Space online needs only a browser. A copy on your own computer needs the following. - Python 3.10 and pip - The huggingface_hub package, which gives you the hf command - A webcam, if you want live video - Disk space for the repository, which holds 8 files 1. Install the huggingface_hub package. 2. Download the Space's files into a local folder. 3. Move into that folder. 4. Install Gradio at the version the Space uses, then install the packages in requirements.txt. 5. Start the web app. ```sh pip install -U huggingface_hub hf download ktejeshnaidu/Smilo --repo-type space --local-dir Smilo cd Smilo pip install gradio==5.15.0 pip install -r requirements.txt python app.py ``` How to use it: There are two ways to run it. The web page accepts an uploaded photo, a snapshot or a live webcam stream. Gradio prints a local address in the terminal for you to open. The desktop script opens a video window from your webcam, and you press q or close the window to quit. ```sh python app.py python main.py ``` ```table Tool | What it does app.py | Starts the Gradio web page main.py | Starts the desktop video window face_classifier.pth | Holds the trained emotion model classes.pkl | Holds the emotion class names ``` Example: You run python app.py, open the page and switch on your webcam. The page draws a box around your face and shows a label such as happy or surprise as your expression changes. For newcomers and experts: Start with the online Space and a clear photo of one face in good light. Facing the camera head on helps the result. Face finding uses OpenCV's Haar cascades. Emotion recognition is a custom network with three convolution layers, written in PyTorch and trained on 128 by 128 color images. The video path skips frames and works concurrently, which the README says keeps live video above 30 frames a second. The README also points to a training notebook for retraining. ```flow A frame comes from a photo or webcam OpenCV finds the faces The PyTorch network scores seven emotions The label is drawn on the image ``` Good to know: Poor lighting or a turned face lowers the accuracy of the label. - License: mit, and the README points to a LICENSE file - Cost to run: none named - Data it reaches: photos you upload and your webcam video - Not for: judging a person's real feelings, since it only labels facial expressions into seven classes - Hardware: the Space is set to cpu-basic at Hugging Face, and what your own computer needs is not stated ## On Hugging Face, 13 November 2026 - Likes: 3 - Built with: gradio - License: mit ## Links - Space: https://huggingface.co/spaces/ktejeshnaidu/Smilo - Files: https://huggingface.co/spaces/ktejeshnaidu/Smilo/tree/main ## Try it Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 5 KB, downloaded as a zip. ```text README.md 5 KB ``` ## Source [ktejeshnaidu/Smilo on Hugging Face](https://huggingface.co/spaces/ktejeshnaidu/Smilo) ## Compare with similar Listed Hugging Face Spaces in the same category that share the most tags with this one. | Product | Likes | Built with | License | Last change | | --- | --- | --- | --- | --- | | Smilo (this page) | 3 | gradio | mit | 2026-04-02 | | [FLUX.1 dev](https://mindket.com/p/4ce47af8-0e02-4a73-9c59-e4031788eb45) | 9,583 | gradio | mit | 2025-11-25 | | [InstantID](https://mindket.com/p/54fcb36c-756a-4797-80c1-05779f87ebbd) | 3,659 | gradio | apache-2.0 | 2025-08-26 | | [Chat With Janus-Pro-7B](https://mindket.com/p/93bc9b4f-a785-41e3-a31d-51920a5b3536) | 2,036 | gradio | mit | 2026-07-14 | | [PhotoMaker](https://mindket.com/p/b3e336b4-4a67-4e52-8c2e-1e94d392ac71) | 1,960 | gradio | apache-2.0 | 2025-08-28 | | [Z Image Turbo](https://mindket.com/p/adfd87b7-3f3e-405e-95c8-1957bc0da52a) | 1,940 | gradio | apache-2.0 | 2026-05-22 | Numbers as Mindket last read them, on 2026-11-12. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-04-02 - First published: 2026-03-29 - Checked on Hugging Face: 2026-11-12 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open ktejeshnaidu/Smilo on Hugging Face](https://huggingface.co/spaces/ktejeshnaidu/Smilo) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/0e5e3019-ac02-4321-8625-99bb7064fcc7) - [Its page on Mindket](https://mindket.com/p/0e5e3019-ac02-4321-8625-99bb7064fcc7)