Keras jobs

...by recall and ROC-AUC • Saved model file plus load-and-predict script Bonus (preferred): wrap the chosen model in a lightweight Streamlit or Flask web app so I can upload a CSV row or enter values manually and see the prediction along with the key probability score. Please outline your proposed methodology, libraries (I mainly use pandas, scikit-learn, imbalanced-learn, XGBoost, TensorFlow/Keras) and any additional steps you find valuable. I am ready to start as soon as I select the right collaborator....

...hit an advanced level of detail: framing member sizing, schedules, dimension strings, call-outs, legends, title blocks, and a basic material take-off table. Typical flow I envision 1. User uploads the 2D floor plan and enters site ZIP/postcode. 2. AI parses geometry with computer-vision (OpenCV or similar) and converts it to a clean parametric model. 3. Generative rules (Python, TensorFlow/Keras, or your preferred stack) combine the parsed model with rule-based logic that encodes IRC 2018. 4. Finished sheets are pushed to a CAD/BIM file (DWG, DXF, or RVT) and a collated PDF set. Acceptance criteria • All five plan types render without manual post-processing. • Each sheet carries correct IRC 2018 citations and site-specific loads. • Output passes an ...

...entirely genomic, the job begins with thoughtful preprocessing and feature engineering (handling high-dimensional SNPs, normalisation, train/validation split, class-imbalance techniques if required). My single, overriding success metric is F1 Score; accuracy alone will not do, so the model must be tuned to balance precision and recall. You may choose the exact framework—PyTorch or TensorFlow/Keras are both fine—as long as the final code is clean, reproducible, and GPU-ready. Deliverables • End-to-end Python code or notebook that loads the raw genetic data, performs preprocessing, trains the deep neural network, and outputs predictions. • Saved, versioned model weights plus a short README on how to retrain or fine-tune. • Evaluation report that...

...entirely genomic, the job begins with thoughtful preprocessing and feature engineering (handling high-dimensional SNPs, normalisation, train/validation split, class-imbalance techniques if required). My single, overriding success metric is F1 Score; accuracy alone will not do, so the model must be tuned to balance precision and recall. You may choose the exact framework—PyTorch or TensorFlow/Keras are both fine—as long as the final code is clean, reproducible, and GPU-ready. Deliverables • End-to-end Python code or notebook that loads the raw genetic data, performs preprocessing, trains the deep neural network, and outputs predictions. • Saved, versioned model weights plus a short README on how to retrain or fine-tune. • Evaluation report that...

...will be able to upload photos from their local drives, and the backend will instantly identify the flower species with high accuracy. Here is the scope I need covered: • Data pipeline – curate or expand an existing public flower dataset, handle cleaning, augmentation, and train/validation/test splits. • Model development – implement a Convolutional Neural Network in Python (TensorFlow / Keras or PyTorch) tuned specifically for multi-class flower classification. I’m open to transfer-learning from ImageNet-based architectures if that speeds convergence. • Evaluation – provide precision, recall, F1, and confusion matrix on the held-out test set, plus brief analysis of misclassifications. • Web interface – a lightweight, r...

...compare ML models for jamming detection, including: * Random Forest * SVM * k-NN (Optional later) * LSTM * CNN * Deep Learning models using TensorFlow/Keras ⸻ 5. Model Evaluation Evaluate the models using: * Accuracy * Precision * Recall * F1-score * Confusion matrix * Detection latency (if possible) ⸻ 6. Deliverables Please provide: * Python source code * Well-commented scripts * Automated dataset generation scripts * CSV dataset generation pipeline * Documentation/explanations * Graphs and visualizations * Model comparison results ⸻ Preferred Tools/Libraries * Python * Pandas * Scikit-learn * Matplotlib * TensorFlow/Keras * Jupyter Notebook ⸻ Important Notes * I have already completed the NS-3 simulation development phase. * I do NOT need help building F...

...compare ML models for jamming detection, including: * Random Forest * SVM * k-NN (Optional later) * LSTM * CNN * Deep Learning models using TensorFlow/Keras ⸻ 5. Model Evaluation Evaluate the models using: * Accuracy * Precision * Recall * F1-score * Confusion matrix * Detection latency (if possible) ⸻ 6. Deliverables Please provide: * Python source code * Well-commented scripts * Automated dataset generation scripts * CSV dataset generation pipeline * Documentation/explanations * Graphs and visualizations * Model comparison results ⸻ Preferred Tools/Libraries * Python * Pandas * Scikit-learn * Matplotlib * TensorFlow/Keras * Jupyter Notebook ⸻ Important Notes * I have already completed the NS-3 simulation development phase. * I do NOT need help building F...

I need a Keras-based sentiment analysis model built from my existing labeled dataset. You will: • Inspect and preprocess the text (tokenization, padding, handling out-of-vocabulary words). • Design an appropriate neural network in Keras—an LSTM, GRU, CNN, or a hybrid architecture that you feel best fits the data. • Train, validate, and fine-tune the model, tracking accuracy, precision, recall, and F1. • Provide clean, well-commented Python code plus a brief README that explains setup, training, and how to make predictions on new text. • Hand over the trained model weights and any scripts/notebooks used. I’m looking for clear, reproducible work that I can continue to build on, delivered through GitHub or a shared drive.

I want a clean-room, from-scratch port of the core TensorFlow + Keras functionality into modern C# so that my team can run experiments entirely inside the .NET ecosystem for research and development purposes. The finished library must run as a self-contained package without requiring any existing C++/Python bindings; think of it as a native-first alternative that feels natural to C# developers yet mirrors the familiar TensorFlow/Keras workflow. Scope of functionality The first milestone centres on the same pillars that make Keras intuitive: • Neural Network Building – an object model that lets me compose layers, define sequential or functional graphs, and introspect parameters. • Data Preprocessing – utilities for batching, shuffling, augme...

...layers perform classification Softmax activation used for multi-class prediction Hyperparameter tuning performed Parameters tuned: Learning rate Epochs Batch size Filter size Number of filters Best performance achieved with low learning rate and more epochs Accuracy achieved above 90% Performance metrics used: Accuracy Precision Recall F1-score Confusion matrix Technologies used: Python TensorFlow Keras OpenCV NumPy Pandas Matplotlib Scikit-learn Platform used: Google Colab Anaconda Model deployment using Hugging Face and Streamlit Upload MRI image to predict disease Fast and automated diagnosis system Reduces manual work for doctors Helps in early treatment planning Non-invasive medical diagnosis method Future scope: Add more diseases Improve accuracy Use larger datasets Clinica...

I already have a complete image-based dataset and now I want a robust Convolutional Neural Network built around it. I need your help choosing or designing the right architecture, training it from scratch or with transfer learning, and then packaging the finished model so I can reuse it easily for inference. You can work in TensorFlow/Keras, PyTorch or any modern deep-learning stack you prefer—as long as the code is clean, well-commented and fully reproducible. At the end I expect: • Source code for preprocessing, training and evaluation • Trained model weights plus a simple predict/inference script • A concise report of the hyper-parameters you settled on and the metrics you achieved on my hold-out data If something in my dataset format needs adjustment...

...a clear rule-based logic tree or a lightweight neural network—that decides when a drone is present. Whichever fusion strategy you implement, the final system must report Accuracy, Precision, Recall and False Alarm Rate on a held-out test split of each dataset. Key technical notes • Vision model: YOLOv8 (PyTorch) fine-tuned on Anti-UAV & VisDrone • RF model: CNN on spectrograms (TensorFlow/Keras or PyTorch, whichever you are faster with) • Fusion: rule engine or small MLP, well-documented so it can be swapped out later Expected deliverables 1. Clean, reproducible training scripts for both branches and the fusion stage 2. Saved model weights and inference scripts capable of running on a single GPU (8 GB VRAM) or CPU-only fallback 3. Evaluati...

...template word-for-word where formatting is concerned. Content must be paraphrased well enough to keep overall plagiarism below 10 % (I run Turnitin). The technical chapter on optimisation should demonstrate how you train, validate and test a neural-network model to predict—or ideally optimise—strength and durability metrics based on graphene dosage and mix parameters. Feel free to employ Python, Keras or TensorFlow; include plots, hyper-parameter tables and model-performance metrics (MAE, RMSE, R²) in the report itself. Deliverables I expect: • Editable Word document (fully formatted, 60–65 pages). • All original figures, tables and Python notebooks/scripts. • A brief “how-to-run” note for the ML code. • Turnitin (...

...Dashboard Visualization Project Structure stock_ai_project │ ├── models │ ├── │ ├── │ ├── │ ├── │ └── │ ├── sentiment │ └── │ ├── data │ └── │ ├── └── Technologies Used Programming Python Libraries Streamlit Pandas NumPy Scikit-learn TensorFlow / Keras Statsmodels Matplotlib yfinance NLTK Tools VS Code GitHub Machine Learning Models Random Forest A supervised machine learning algorithm used for regression that predicts stock prices based on historical features such as: Open price High price Low price Volume ARIMA A time-series forecasting model used for analyzing and predicting future stock prices based on historical closing prices. LSTM A deep

I need assistance setting up an NVIDIA-based Ai rig on for leasing processing power. Key Requirements: - Configure and optimize the rig for machine learning tasks - Ensure the setup is suitable for TensorFlow, PyTorch, or Keras - Focus on high performance, particularly in GPU power Ideal Skills and Experience: - Expertise in NVIDIA hardware and machine learning frameworks - Experience with platform - Strong background in system optimization for ML workloads Looking for a freelancer who can ensure a smooth and efficient setup.

...Cascade, LBPH, and/or CNN - Implementation guidance using Python, OpenCV, and basic deep learning - Flowcharts, system architecture diagrams, and explanations - Sample dataset explanation and training process - Code snippets with explanation - PPT presentation (optional but preferred) Technical Requirements: - Knowledge of AI/ML and Computer Vision - Experience with Python, OpenCV, TensorFlow/Keras - Understanding of academic thesis formatting Important Conditions: - Work must be 100% original (no plagiarism) - Freelancer should explain the project so I can understand and defend it - Proper formatting (fonts, citations, references in IEEE/APA style) Deadline: 24 hours Budget: Will discussed as performance Additional Notes: Preference will be given to freelancers who have...

...ModuleNotFoundError: TensorFlow fails to load () NumPy 2.x incompatibility with TensorFlow _ARRAY_API not found error Uvicorn crashes while importing Project Details: Backend: FastAPI Model: TensorFlow (Keras) Files: (API) (model loading + prediction) dataset/model/ (, , ) dataset/PlantVillage/ (class folders) Requirements: Create a clean working Python environment Fix all dependency issues: TensorFlow compatibility NumPy version compatibility (<2) Keras / model loading issues Ensure model loads correctly using: Fix API endpoint: /disease-detection-file should accept image upload and return prediction Ensure project runs with: uvicorn app:app --reload CPU-only setup

Hi, I need help finalizing my plant disease detection project. Current setup: - Model: CNN + MobileNetV2 (already trained) - Model file: .keras format available - API is already working and giving predictions correctly - Frontend is also working What I need you to do: 1. Create an script that: - Loads the trained model (.keras file) - Loads dataset (PlantVillage / similar structured dataset) - Generates Confusion Matrix - Generates Classification Report (precision, recall, f1-score) 2. Ensure: - Correct class label mapping (no mismatch between dataset and model) - No changes in existing API behavior/output - Dataset should be properly loaded using ImageDataGenerator or 3. Important: - Current prediction output from API should remai...

I already have a well-labeled image set ...pipeline: clean and augment the data, design and train the EfficientNet + ViT architecture, fine-tune it for my three disease classes, then benchmark the results with clear metrics (accuracy, precision, recall, confusion matrix). Deliverables • A fully trained hybrid model (saved weights plus exportable ONNX or TensorFlow format) • A reproducible training notebook or script (Python; TensorFlow/Keras or PyTorch) • An inference script or minimal REST API that takes a new leaf image and returns the predicted class with confidence • Brief documentation so I can retrain or update the model later If you have prior experience blending CNN backbones with transformer heads, particularly on agricultural datasets, I&rsq...

...(ECE) based on Artificial Intelligence and Machine Learning, specifically focused on image classification. The project should involve designing and implementing an intelligent system capable of classifying images into predefined categories using modern ML/DL techniques. Key Requirements: Strong knowledge of Python, Machine Learning, and Deep Learning Experience with frameworks like TensorFlow / Keras / PyTorch Understanding of CNN (Convolutional Neural Networks) for image classification Ability to work with datasets (custom or open-source like Kaggle) Knowledge of data preprocessing, training, validation, and testing Basic understanding of ECE applications (preferred but not mandatory) Project Scope: Dataset selection and preprocessing Model design (preferably CNN-based) Trai...

Please Sign Up or Login to see details.

...learning model that reliably classifies each photo into the correct category. Your job is to design, train, and evaluate the full image-classification pipeline. You may build from scratch or fine-tune a proven architecture such as ResNet, EfficientNet, MobileNet, or a vision transformer—as long as the final model meets the accuracy targets we set together. Feel free to work in PyTorch or TensorFlow/Keras; I’m comfortable deploying either. What I’ll provide • A structured folder of training, validation, and test images • Category labels and a brief data dictionary • Access to a GPU instance if you need it What I need back 1. Clean, well-commented code (Jupyter notebook or Python scripts) that handles preprocessing, augmentation, training, an...

... The missing piece is the generative model that actually predicts depth, completes occluded geometry, and exports the result in a standard 3-D file. You will be working on an NVIDIA A6000 cloud instance that I have ready to go, so you can assume plenty of VRAM for large-scale diffusion, NeRF, or implicit surface models. I am framework-agnostic: if your best solution is PyTorch, TensorFlow, or Keras that’s fine, as long as the code is clean and reproducible. Key goals • Accept a single RGB image as input • Infer depth and surface normals, hallucinate hidden geometry, and rebuild a watertight mesh • Texture the mesh using the original image plus any learned in-painting • Output a common interchange format (OBJ, FBX, or glTF—pick whichever i...

...inconsistencies in the data. Preprocessing steps such as image resizing, normalization, and cleaning will be applied. Additionally, data augmentation techniques (e.g., rotations, flips, and brightness adjustments) will be used to increase variability and improve the model’s ability to generalize. The core of the system will involve developing a Convolutional Neural Network (CNN) using either TensorFlow/Keras or PyTorch. The model will be trained and optimized through experiments with different parameters and configurations. Its performance will be evaluated using commonly used metrics including accuracy, precision, recall, and F1-score, along with a confusion matrix to better understand the model’s performance across individual disease classes. Once a satisfactory m...

I need a full-length research paper prepared and shepherded through publication in a Scopus-indexed Q2 journal. The topic is neural-network-based detection of visual defects in woven or knitted textiles, implemented in Python. I am flexible about the framework—TensorFlow, PyTorch, Keras or a comparable library is fine—so long as the final code is reproducible and well-commented. The paper must include a solid literature review, a clearly explained network architecture, an experimental section using a representative dataset of fabric images, and a results discussion that meets the methodological rigour typical of Q2 outlets. I will supply any proprietary images I have; if additional public datasets are needed, please curate them. Deliverables • Draft manuscript f...

...identify and download a suitable, well-labelled dataset from Kaggle. Feel free to compare a few candidates, but the final choice should give good class balance and enough samples per disease category. Once the data is in place, walk through exploratory data analysis, preprocessing, and augmentation inside a Jupyter notebook. From there, build and tune a convolutional neural network (TensorFlow / Keras or PyTorch are both fine) and report the usual metrics plus a confusion matrix so I can judge class-wise performance. When the model is satisfactory, save it and wrap inference in a clean Streamlit app where a user uploads a single image and instantly sees the predicted disease name along with a confidence score. Additionally, integrate AI-based recommendations (e.g., treatment or...

...reliably detect vehicle licence plates and traffic signs in real-time video or still images. Everything must run locally without any cloud calls, built on TensorFlow and Keras with only open-source components. My goal is to receive a solution that I can drop onto an edge device or standard PC, start a camera feed, and immediately see bounding boxes around plates and recognised traffic signs. Model accuracy must be on par with commonly cited public weights; speed should be good enough for at least 15 fps on a mid-range GPU (CPU-only fallback appreciated). Deliverables • Fully documented source code in Python using TensorFlow + Keras • Pre-trained weights (or clear training script plus instructions to reproduce) for licence-plate and traffic-sign classes &b...

I’m putting together an academic-grade project that demonstrates how supervised learning can spot common w...data 3. A concise PDF explaining logic, workflow, and how to rerun everything (screenshots welcome) 4. Optional extras: a short report (~10 pages) and a slide deck to support a final-year viva—include these if you’re comfortable producing them, otherwise let me know so we can adjust milestones accordingly. Keep the solution native to widely used libraries (pandas, scikit-learn, TensorFlow/Keras or PyTorch) so reviewers can reproduce results without exotic dependencies. Accuracy matters, but clarity and reproducibility are paramount—I want to be able to hand this over, have someone install requirements, press “Run,” and immediately un...

...seasoned statistician who can move comfortably between classical regression techniques and modern Convolutional Neural Networks. The project centres on predictive analytics: you will build, compare and explain regression-based models, explore where a CNN adds value, and present the insights through clear, publication-ready visualisations created in Python (think pandas, scikit-learn, TensorFlow/Keras, matplotlib, seaborn or Plotly—use what fits best). We will begin with a brief video call so I can walk you through the dataset, the business question and the success metrics. After that, you will take full ownership of data preparation, model selection, training, validation and visual storytelling. Expect to hand back clean, well-commented notebooks and graphics that a non-te...

...face against a gallery to decide whether it is an identical match. • Serve three environments without extra rewrites: security-grade CCTV feeds, social-media style mobile uploads, and large photo-management archives. • Deliver low latency on a single modern GPU while still running acceptably on CPU-only hardware for lightweight deployments. I’m comfortable with either PyTorch or TensorFlow/Keras; use the framework you know best. A pre-trained backbone such as ResNet, MobileNet, or Vision Transformer is fine as long as you include the full training pipeline so I can continue to improve the model with fresh data. Deliverables 1. Source code with clear, commented modules for detection, embedding generation, and similarity matching. 2. Pre-trained weights ...

...researcher who can build a production-ready model that listens to a baby’s cry, watches the paired video, and decides—reliably—whether the cause is hunger, discomfort, or simple attention seeking. Audio and video must be fused inside one architecture; running them in parallel but independently will not satisfy our accuracy goals. You may use the deep-learning stack you trust most (PyTorch, TensorFlow, Keras, OpenCV, torchaudio, etc.) provided the final network can run in real time on an edge device and be exported to ONNX or TFLite. I will share product constraints and a small proprietary data set; you will expand it through public sources or augmentation, perform rigorous cross-validation, and refine the model until we consistently exceed 90 % precision and re...

I have a curated dataset of abdominal X-ray images that needs a robust deep-learning model capable of classifying key clinical findings. The end goal is a production-ready Python solution that can consistently score above 90 % accuracy on an unseen validation set. You’ll start with any mainstream framework you prefer—TensorFlow, Keras, or PyTorch—and handle the full pipeline: data preparation and augmentation, model architecture selection, training, hyper-parameter tuning, and evaluation. Please keep the code modular and well-commented so I can retrain or fine-tune later as new data comes in. A concise report that explains your decisions, metrics, and suggestions for future improvements will also be appreciated. To help me choose quickly, focus your proposal on y...

...images—specifically plain-film X-rays—and tell me whether each study is of the chest, abdomen, or an extremity. All input files will be standard hospital exports (mostly DICOM, occasionally PNG/JPEG), so the model must handle typical variations in resolution and contrast. What I’m after is a reproducible, well-documented solution: data preparation, augmentation, model architecture (a CNN in TensorFlow, Keras, or PyTorch is fine), training, and evaluation. Please include class-balanced splits, explain any preprocessing you apply, and show the metrics you achieve on an unseen validation set. Deliverables • Python code with clear comments for preprocessing, training, and inference • Trained model weights ready for deployment • A short report ...

...(e.g., chest PA vs. chest lateral, cervical spine, hand, etc.). The job is strictly about classifying the type of X-ray, not diagnosing any pathology. Here is what I already have and what I expect from you: • A curated folder structure with several thousand labelled PNG and DICOM files that you can download from my secure server. • A preference for Python with either PyTorch or TensorFlow/Keras—use whichever framework you feel will achieve the best accuracy and fastest inference on a modern GPU. • Clean, reproducible code (Jupyter notebook or script) plus a short README that explains environment setup, training commands, and how to run inference on a single file or a batch. • A trained model file and a simple inference function/CLI that returns ...

I need an expert to improve the accuracy of a histopathologic cancer detection model. The current model needs enhancement, and I prefer using algorithm enhancement for this task. Key Requirements: - Improve the model's accur...for this task. Key Requirements: - Improve the model's accuracy in detecting cancerous tissues. - Use advanced techniques and methodologies for algorithm enhancement. Ideal Skills and Experience: - Expertise in machine learning and deep learning - Strong background in medical image analysis - Experience with histopathological images - Proficiency in Python and relevant libraries (TensorFlow, Keras, PyTorch) - Familiarity with model evaluation and performance metrics Please provide examples of similar work and a detailed approach to how you would ...

...lip-sync errors, or artifacts). * Uniform/Badge Recognition: Detect if the person is wearing a police uniform or showing a badge (using object detection like YOLO). * Real-Time Risk Dashboard: * A simple UI that displays a "Trust Score." If the score drops below a threshold, it shows a "SCAM ALERT" warning. Preferred Tech Stack: * Language: Python * ML Frameworks: TensorFlow / PyTorch / Keras * Computer Vision: OpenCV, MediaPipe * NLP: Hugging Face Transformers (BERT/RoBERTa for intent classification) * Interface: Streamlit or Flask (for the demo dashboard) Deliverables: * Source Code (well-commented). * A file for easy installation. * A short demo video showing the system detecting a scam attempt from a sample video file. * Documentation on t...

I need a machine learning algorithm for a regression task using text data. Ideal Skills and Experience: - Proficiency in machine learning techniques, especially regression - Experience with text data processing and natural language processing (NLP) - Strong programming skills in Python or R - Familiarity with ML libraries like TensorFlow, Keras, or scikit-learn - Ability to preprocess, analyze, and model text data

...data-prep workflow, tune the architecture, and ship a repeatable training routine that reaches production-ready performance. What needs to happen • Curate and augment the image dataset, ensuring balanced classes and clear train/validation/test splits. • Redesign or refine the network—think transfer learning with EfficientNet or a custom ResNet variation implemented in PyTorch or TensorFlow/Keras. • Integrate early-stopping, learning-rate scheduling, and experiment tracking (e.g., TensorBoard or Weights & Biases). • Export a lightweight, versioned model file plus a clean inference script that takes a folder of images and returns class labels and confidence scores. • Document the environment setup, dependencies, and training commands ...

...data-prep workflow, tune the architecture, and ship a repeatable training routine that reaches production-ready performance. What needs to happen • Curate and augment the image dataset, ensuring balanced classes and clear train/validation/test splits. • Redesign or refine the network—think transfer learning with EfficientNet or a custom ResNet variation implemented in PyTorch or TensorFlow/Keras. • Integrate early-stopping, learning-rate scheduling, and experiment tracking (e.g., TensorBoard or Weights & Biases). • Export a lightweight, versioned model file plus a clean inference script that takes a folder of images and returns class labels and confidence scores. • Document the environment setup, dependencies, and training commands ...

...“Penghargaan paling tinggi bagi seorang pekerja keras bukanlah apa yang dia peroleh, tapi seberapa berkembang ia dengan kerja kerasnya itu.” What I need is a well-structured, engaging piece—think 800-1,000 words—written in Bahasa Indonesia, vibrant in tone yet grounded with practical take-aways. By the final paragraph, readers should feel eager to open their textbooks, commit to consistent effort, and see learning as personal growth rather than mere grades. Please weave in study-boosting tips (time-blocking, active recall, peer learning, etc.) and sprinkle relatable campus scenarios so the message lands. Key deliverable • One plagiarism-free article (Google Docs or Word) optimised around “motivasi mahasiswa,” “semangat belajar,...

...require a purpose-built deep learning model capable of reliably distinguishing authentic images from manipulated (deepfake) images. The scope is tightly focused on model design, training, and evaluation: developing an effective CNN-based architecture, training it on established deepfake datasets, and tuning it to perform robustly under real-world conditions. The implementation may use TensorFlow / Keras, PyTorch, or an equivalent framework, provided the entire training and inference pipeline is fully reproducible on a single modern GPU. I can supply standard datasets (e.g., FaceForensics++ image frames, DFDC samples) along with additional proprietary images if required. Please indicate if alternative datasets would materially improve performance. Deliverables • Well-docum...

...datasets (for instance, CMU Panoptic, PKU-MMD, Kinetics-Skeleton, or similar) plus any augmentations you create yourself. No private data collection will be possible on my side. • Training & evaluation: deliver clear metrics—accuracy, precision/recall per emotion class and real-time FPS tested on a 1080p classroom-style video. • Inference pipeline: provide Python code (PyTorch or TensorFlow/Keras are both fine), a lightweight REST or gRPC endpoint, and a demo script that ingests an RTSP stream from a classroom CCTV camera and overlays bounding boxes with emotion labels in real time. • Documentation: include setup instructions, environment file or Dockerfile, and a concise report explaining architecture choices, hyper-parameters, final metrics and ho...

I am ready to bekerja keras to turn my training as a dokter, specifically as a Spesialis anak, into reliable income. What I need now is a clear, actionable plan that shows exactly how to translate my pediatric knowledge into profitable services or products—whether that involves launching a private or tele-health clinic, creating parent-focused digital resources, or packaging expert content for online courses and eBooks. Here’s what I’d like from you: • A step-by-step roadmap outlining realistic revenue streams for a pediatric specialist. • Market validation of each idea, including approximate audience size and earning potential. • A marketing blueprint (online and offline) to attract parents and caregivers quickly. • Practical guidance on...

...from real-world projects (e.g., real-time voice assistants, self-healing agents, chatbots for fitness/health/finance, sentiment analysis, and integrations with tools like Azure OpenAI, Mistral/LLAMA, LangGraph, and Chroma). Sessions should cover: • AI & ML Basics: Core concepts, machine learning models, deep learning, NLP, computer vision, and tools like Python (pandas, scikit-learn, TensorFlow/Keras, NLTK, spaCy). • Generative AI: Building chatbots, RAG architecture, document intelligence, natural language interactions, and integrations with Azure OpenAI, Apache NiFi, or similar. • Agentic AI: Autonomous agents for tasks like voice coaching, error handling, API automation, using frameworks like LangGraph, CrewAI, AutoGen, ReAct, and persistent memory (e.g....

...end-to-end in the browser, crop the user’s face in real time, pass that crop to a freshly trained CNN, and immediately forward the model’s decision back to my PAI endpoint. The backbone of the job is the CNN itself. I’ll supply mixed image and video datasets; your task is to design, train, and fine-tune a model that can perform confidently under live-camera conditions. Whether you prefer TensorFlow, Keras, PyTorch, or another deep-learning framework is up to you, as long as the final weights and inference code are portable. On the front end, I need a lightweight web component—WebRTC or similar—that guides users to place their face inside an on-screen box. When the alignment is correct, the component should grab the frame, crop precisely around th...

I need a robust image-recognition system focused purely on object detection. You will take my raw images, prepare and label the dataset, choose the right deep-learning framework—TensorFlow, Keras, or PyTorch is fine—and train a model that reliably spots the target objects in new pictures. Once trained, package the solution so I can run inference locally or on a small cloud instance. That means delivering the cleaned dataset, training scripts, the final weights, and a short README that walks me through setup, retraining, and evaluation commands (preferably in a single or ). Accuracy, speed, and a clear hand-off matter more to me than fancy dashboards, so concentrate on a well-documented, reproducible pipeline and a model that meets the mAP benchmarks we’ll agree

I need to add a reliable mask generator to my ANPR pipeline that pinpoints the license-plate region in still JPEG photographs. The task is limited to detection—no character recognition for now—so the model simply has to return an accurate bounding box or, better, a pixel-level mask for...training steps. Reproducibility is key; I want to be able to retrain the model from scratch on my side. Deliverables (to be accepted): • Clean, well-commented Python code and • Trained weights (.pth, .ckpt, or .h5) • CLI script plus a minimal REST endpoint for batch inference • README explaining data prep, training, and inference commands OpenCV, PyTorch, TensorFlow, or Keras are all acceptable; pick whichever you are most comfortable with, and keep the dep...

I’m working on a personal research project that relies on convolutional neural networks to analyse image data, and I’ve reached the point where the baseline architecture no longer meets my goals. I need the model to be both more accurate and noticeably faster at inference without sacrificing one for the other. You’ll start with my existing checkpoints and training scripts (Python, TensorFlow/Keras—PyTorch equivalents are fine if you would rather port). The task is to redesign or fine-tune the network, apply the right data-augmentation or regularisation tricks, and then compress, prune, quantise, or otherwise accelerate it so that I see measurable gains in both metrics. I’m happy to experiment with advanced techniques such as knowledge distillation or N...

...will receive a folder of cropped and noise-added fingerprint fragments plus their full counterparts for validation. I am open to CNN-based inpainting, hybrid approach, AI and image processing—so long as the final output convincingly restores minutiae and passes a side-by-side comparison against the ground-truth scans. Please work in mainstream, well-documented libraries (PyTorch, TensorFlow or Keras, OpenCV, scikit-image) and keep the environment reproducible through a conda .yml file. Deliverables: • Fully commented Python scripts or notebooks • Trained model weights and instructions for inference on new scans • A concise README outlining setup, training, and evaluation steps • Quantitative report showing reconstruction quality (PSNR/SSIM or sim...

... script that can: Take a live video feed from a webcam, Recognize the gestures in real-time, and Output recognized text (and speak it out using gTTS or Web Speech API). Documentation: A basic README file explaining: How to run the code, How to use the trained model, Simple instructions for setting up and testing. Skills Required: Basic Machine Learning experience (TensorFlow / Keras / PyTorch). Gesture Recognition or Hand Pose Estimation using models like MediaPipe or HandPose. Real-Time Processing (video or webcam input). Familiarity with (optional, if the model needs to be used in a browser). Budget: This is a small project with a limited budget. Please provide an estimate based on basic functionality and a quick turnaround (within 1–2 days). Timeline: