PyCon Italia 2025
| title | author | length |
|---|---|---|
| Conference Opening and Welcome | 14m | |
PyCon Italia 2025 opens with a record 1000 attendees and a venue moved from Florence to Bologna, with rooms named Naki, Tatella, passatelli, spaghetti and more… | ||
| Lightning Talks - May 30 | 35m | |
Lightning talks session runs as a rapid lineup with a playful pizza wheel that forces props and constraints; announcements include 50–52 open-source projects… | ||
| Python, Spaghetti and Local Communities | 27m | |
Introduces how local Italian Python communities (from Catania to Milan) grow the ecosystem through meetups, events, talks and networking, emphasizing… | ||
| Lightning Talks - May 31 | 52m | |
Fast, chaotic lightning session mixing demos, community stories and stage gags where a spinning pizza wheel imposes actions like pineapple = fruit of shame… | ||
| How to Improve Your LLM-Based Application? Haystack, LlamaIndex and LangChain Compared | Tommaso Radicioni | 30m |
Compares three Python frameworks for building applications with large language models—Haystack, LlamaIndex, and LangChain—focusing on which fits different… | ||
| The marvelous world of Python in Browser: a nice surprise | Fabio Pliger | 45m |
Pyscript runs real Python in the browser using Pyodide (full CPython with many scientific libs, ~8 MB) or MicroPython (tiny loader ~100–170 KB) and lets code… | ||
| Boosting Python Web Apps performance with Celery and Concurrency | Yash Raj | 28m |
Uses Celery with Django, a broker (Redis or RabbitMQ), and Postgres to move news scraping off the web app and into background jobs; scheduling uses celery beat… | ||
| Best buddies: Django and HTMX | Spela Giacomelli | 30m |
Claim: combine Django and HTMX to build SPA‑like behavior with zero custom JavaScript. Demos show a button-triggered joke (pure HTML response), a click‑to‑edit… | ||
| LLM Revolution: Necessity or Excess? A Study of the Most Efficient Solutions | Giulia De Poli, Giuseppe Lovino | 30m |
Compares large language models (LLMs) with lighter-weight alternatives for text classification, analyzing when LLMs are necessary versus when simpler models… | ||
| Composable Data Systems, the new frontier | Alessandro Molina | 58m |
Argues that replacing monoliths with interoperable pieces yields big wins: storage, planner and engines communicate via Apache Arrow and Substrait… | ||
| Creative Compassionate Code (if Python isn't fun, we're doing it wrong) | Nicholas H. Tollervey | 01h 03m |
Early BBC Micro adventures lead to building a beginner-friendly editor called MW with “millions of downloads,” teacher-driven features like one-click zoom and… | ||
| Accessibility awareness | Sarah Abderemane | 48m |
94.8% of the top 1M sites fail WCAG checks and over 96% of issues cluster in six categories: low contrast text, missing alt text, unlabeled form inputs, empty… | ||
| Data doesn't lie — but it can mislead: How to ensure integrity of your Machine Learning applications | Sofie Van Landeghem | 54m |
A production entity linker is built by harvesting Wikipedia anchor links, encoding mention and candidate page text into embeddings, and scoring with a… | ||
| Lessons from a lifetime of doing, teaching, managing, and leading technical development | Alex Martelli | 01h 01m |
Compresses 50+ years into practical lessons: change is constant, manage it with incremental, auditable steps, and prioritize people over tools. Uses concrete… | ||
| From Struggle to Stardom: The Secret Sauce of High Performance Teams | Seemin Suleri | 52m |
Claims a repeatable "Luminary framework" that uses narrative work, emotional literacy, and mapped workflows to turn low-performing teams into high performers… | ||
| Dipping my toes in metaprogramming | Rodrigo Girão Serrão | 35m |
Shows how Python's __new__ returns arbitrary objects and how it differs from __init__; implements a Number class whose __new__ swaps cls for OddNumber or… | ||
| Pythonistas! Here’s the Perfect Development Environment! 2025 Edition (NixOS) | Peter Bittner | 43m |
Shows how to create a standardized, yet individually customizable, developer workstation using NixOS so onboarding new Python engineers takes minutes rather… | ||
| Post-Training Small Language Models: the adventures of a practitioner | Stefano Fiorucci | 42m |
Practical account of post‑training: uses TRL and DPO/GRPO workflows, applies LoRA and QLoRA for 4‑bit fine‑tuning, and runs spectrum selection or model‑merging… | ||
| Black holes and gravitational waves are discovered (also) with Python! | Davide Gerosa | 43m |
Python drives the analysis pipeline: raw strain access, matched-filter searches, Bayesian parameter estimation and population inference via Bilby/dingo nested… | ||
| Django from the Trenches: Patterns and Practices After 15 Years of Experience with Django | Iacopo Spalletti | 29m |
Practical guidance for architecting Django projects based on 15 years of experience, focusing on concrete patterns and best practices that avoid common… | ||
| Back to Basics: Cutting Through the AI-Generated Code Noise | Archana Vaidheeswaran | 39m |
Claim: AI-generated code often looks correct but misses edge cases, introduces outdated or insecure patterns, and creates hidden costs. Examples: a retailer… | ||
| Bytecode and .pyc files | Konrad Gawda | 32m |
Deep dive into CPython bytecode and .pyc internals: how co_code, co_consts and co_varnames map to evaluation stack operations and instructions like LOAD_CONST… | ||
| Beyond Solo: Enhancing LLMs through Collaborative Dialogue with GAN-Inspired Approaches | Nicola Guglielmi | 29m |
Claim: pairing two LLMs in a generator/discriminator pairing refines outputs by letting a high-temperature model explore creative drafts while a… | ||
| QuerySet.explain(): make it make sense. | Aivars Kalvāns | 30m |
Explains how PostgreSQL chooses index vs sequential scan using the cost model (seq_page_cost=1, random_page_cost=4 by default), shows using EXPLAIN ANALYZE… | ||
| Graph-Based Machine Learning with Python | Pietro Mascolo | 31m |
Covers how graph ML makes node and graph predictions using actual Python code and numbers: uses NetworkX for analysis and PyTorch Geometric to build a… | ||
| Local LLM fine-tuning: a practical example | Daniele Giunta | 29m |
Concrete workflow for fine-tuning a local LLM: load metas lama 3.2.2 3B in Google Collab, attach Laura adapters (LoRA) via the ansloth package, prepare 100… | ||
| AI Intuition: Exploring Language Model Latent Space | Giuseppe Birardi | 44m |
Argues that language-model “intuition” maps to sudden reorganization in latent geometry, cites gamma bursts and induction heads forming during training, and… | ||
| Langfuse, OpenLIT, and Phoenix: Observability for the GenAI Era | Emanuele Fabbiani | 29m |
Demonstrates an end-to-end GenAI observability stack: a movie-search pipeline using LanceDB + Polars, parallel semantic searches (query vs… | ||
| No more Locks! What can we achieve without the GIL | Caio Costa Salgado | 30m |
Live demos measure raw effects not promises: a count to 10 million microbenchmark on a 32‑core laptop shows multithreading on stock CPython stays single‑core… | ||
| Pixels and Particles: When Generative Art Meets Quantum Computing | Juna Salviati | 21m |
Explains how generative art, historically created with computers since the 1960s, can make use of quantum computing by exploiting quantum-generated random… | ||
| Building real-time apps for web, mobile & desktop in Python | Attila Tóth | 25m |
Flet claims to let Python apps target web, desktop and mobile without frontend code by compiling Python UI calls into Flutter widgets via a server model… | ||
| They are not unit tests: a survey of unit-testing anti-patterns | Stanislav Zmiev | 44m |
Defines a unit as the product’s public interface (functions for libs, endpoints for APIs, widgets for GUIs) and shows concrete fixes: replace brittle 300‑line… | ||
| Exploring Functional Options in Python | Rami Awar | 31m |
Starts with a simple get_text function for a document‑analysis client, adds many parameters, and then explores designs: raw expanded signature, a pydantic… | ||
| Understanding Python from the inside: C concepts to dive into CPython fearless | Cristián Maureira-Fredes | 31m |
Shows that CPython is ~35.8% C and walks through compiled binaries to find main -> pybytes_main -> pymain, then inspects PyObject/PyTypeObject structs to… | ||
| The essense of Graceful Shutdown | Andrii Soldatenko | 26m |
Covers how Python apps actually implement graceful shutdown: register signal handlers for SIGINT, SIGTERM, SIGHUP, cancel running asyncio tasks and stop the… | ||
| Don't Panic! A Developer's Guide To Security | Sebastiaan Zeeff | 45m |
Practical roadmap: shift left security by adopting OASP SAM and the OASP DevSecOps maturity model, pin artifacts (versions with hashes), run nightly builds… | ||
| Foundational Models for Time Series Forecasting: are we there yet? | Luca Baggi | 31m |
Explains that transformer-based foundational forecasters are promising but data-limited: teams adapt T5-style and decoder transformers, bin or patch continuous… | ||
| Strawberry Fields Forever: Enjoy building GraphQL Web APIs | Jonathan Marcel Ehwald | 45m |
Shows Strawberry GraphQL doing real work: a code-first Python schema that the CLI can auto-generate from an SDL file, a debug server that serves GraphiQL, and… | ||
| From Cloud to Edge computing - Unleashing the power of WebAssembly at the edge | Alex Casalboni | 32m |
Shows concrete Python+WASM engineering: uses Pyodide, wasmtime-py, componentize tooling and a private registry to build, test and push WASM components that run… | ||
| Understanding geospatial data with duckdb | Jorge Martinez Gomez | 45m |
Shows that DuckDB can store and query vector geodata with the spatial extension and HTTPFS to load GeoJSON from URLs, run ST_Length/ST_Area/ST_Within and… | ||
| Understanding Climate Change with Python: From the IPCC Report to Climate Action | Castellani | 31m |
Uses Python tools to analyze IPCC climate-report data and visualize future climate scenarios, showing how human choices affect outcomes. Covers scientific… | ||
| Domain-driven Data Science | Pietro Peterlongo | 40m |
Argues domain know-how matters more than extra model complexity for supply‑chain forecasting, showing concrete techniques: probabilistic forecasts to size… | ||
| Quantum computing without leaving Python behind | Alessandro Cosentino | 42m |
Survey finds 95% of practitioners use Python for quantum development while Rust rises to ~13%. A C++11 simulator (open source, OpenCL optional) wrapped with… | ||
| Accelerating privacy-enhancing data processing | Florian Stefan | 41m |
Shows a concrete pipeline that turns messy hospital records (free text, scanned documents, multiple standards) into research-grade datasets by chaining an… | ||
| Distributing complexity in huge python projects. | Maxim Danilov | 44m |
Argues that when full redesign is impossible, complexity is best measured and redistributed rather than blindly refactored; uses tools like radon, SonarCloud… | ||
| Fantastic Ciphers and How to Break Them | Luca Di Vita | 43m |
Overview of how classical and modern cryptosystems — from Caesar cipher up to RSA and ElGamal — can be broken using number theory and logical analysis… | ||
| SPy (Static Python) lang: fast as C, Pythonic as Python | Antonio Cuni | 46m |
SPy is a new statically typed Python variant that enforces function signatures at module boundaries and uses red‑shift partial evaluation to precompute… | ||
| Efficient FastAPI testing with pytest, dependency injection and snapshots | Jan Giacomelli | 45m |
Claim: using FastAPI dependency injection, pytest factory fixtures, and snapshot testing cuts maintenance and catches unintended API changes. Demonstration… | ||
| Learning Together, Distributed: An Introduction to Federated Learning | Luca Corbucci | 42m |
Overview of federated learning fundamentals with concrete results: models move instead of raw data, used by Gboard and Apple for on-device language/speech… | ||
| How to build your own Tiny Language Model from scratch | Luca Gilli | 44m |
Shows how to train tiny autoregressive models using the llm.c C/CUDA reference implementation and a fork with a runnable notebook that trains on CPU at ~10,000… | ||
| Writing a scikit-learn compatible estimator in the modern age | Adrin Jalali | 42m |
Live code builds a dummy classifier, a stateless transformer and a meta "timer" wrapper and makes each pass scikit‑learn tests by using check_estimator… | ||
| Hello Bug, My Old Friend | Patrick Deutschmann | 35m |
A demo called Buggy Tasks demo exercises real bugs: an off‑by‑one delete that removes the wrong item and a priority prediction failure where renamed training… | ||
| Italy-Finland climate round trip with Python | Elisa Bestetti | 39m |
Italy and Finland get compared using daily gridded Copernicus reanalysis (0.25°) and SPEI12 from the Crosse store, spanning 1950–2024 for temperature and… | ||
| Behind the Data: Unraveling Leadership Challenges in the LLM Era | Tereza Iofciu | 39m |
Nineteen interviews plus multi-round surveys and a live QR poll using LinkedIn feedback and Perplexity/ChatGPT examples reveal three concrete pain points… | ||
| From hand-down maps to AI/BI: a journey toward Databricks | Giulio Melloni, Andrea Calegari | 45m |
Databricks demonstrates a codeless BI layer called Genie Spaces that turns natural-language prompts (English/Italian) into executable SQL, runs queries on… | ||
| Python, YOLO and Kubernetes: Super-Vision for an Industrial Plant | Michele Zanchi | 40m |
A Python-based computer vision system built with YOLO models and deployed on Kubernetes monitors a critical industrial machine at a Tenaris plant to prevent… | ||
| Is Prompt Engineering Dead? How Auto-Optimization is Changing the Game | Iryna Kondrashchenko, Oleh Kostromin | 30m |
Automatic prompt tuning treats prompts as trainable parameters and shows concrete wins on multi-step pipelines by: using a teacher model to collect… | ||
| How to Learn Python from Scratch with an Evidence-Based Approach | Lisa Di Marco | 26m |
Explains how people with no computer science background can learn Python from zero using evidence-based study methods borrowed from other disciplines… | ||
| Beyond Alembic and Django Migrations | Noam Cattan | 31m |
Compares Alembic/Django migration limits with Atlas, a schema-as-code engine that auto-generates diffs from SQLAlchemy models plus layered SQL and actually… | ||
| Democratizing Data: A deep dive into Eurostat Open Database | Simona Mazzarino | 27m |
Shows how the Eurostat web UI and the JRC-developed eurostat Python library combine: use get_toc/get_toc_df to discover datasets, use get_data_df (with dataset… | ||
| UX is frontend only! Why do I, super ninja backend developer, need to care about it? | Luka Raljević | 29m |
Backend work directly shapes APIs, database schemas and query performance for the product that stores and serves the world's largest malware database built… | ||
| Live audio synthesis with Synchrotron | Andrew Stroev | 31m |
Live synthesiser called Synchrotron runs entirely in pure Python using numpy or plain lists to render audio buffers at standard 44.1 kHz, demonstrates a… | ||
| A love letter to messaging: Celebrating RabbitMQ's journey | Lovisa | 30m |
Covers RabbitMQ's evolution: Celery used for background tasks with RabbitMQ as default broker, hosted on CloudAMQP running 15,000 servers; version 3.6… | ||
| Generative AI Monitoring with PydanticAI and Logfire | Marcelo Trylesinski | 30m |
Demonstrates wiring PydanticAI agents to Logfire for end-to-end observability: agents call tools like get_current_date, HTTP calls via HTTPX are instrumented… | ||
| Python Untethered: Building Robust Embedded Systems | Oliver Rew | 24m |
Modern embedded Linux devices fail mostly from storage wear, unexpected power loss, and bad updates; practical fixes include using an overlay filesystem or RAM… | ||
| Data Morph: A Cautionary Tale of Summary Statistics | Stefanie Molin | 28m |
Summary statistics like mean median std and Pearson r can match wildly different point clouds, so a working counterexample is packaged as Datamorph package… | ||
| Python & Flutter: can birds and snakes really be friends? | Matteo Maria Terzuolo | 24m |
Attempts combine Flutter and Python using Python FFI, pybind11 and build tools show a concrete result: a simple square function called from Flutter via a… | ||
| Autonomous driving, how Python drives Formula Racing cars | Ilyas Timour | 31m |
Team builds autonomous Formula Student cars that run real laps at over 150 km/h and validate Python pipelines on hardware. Perception uses YOLO and LiDAR for… | ||
| Backend-First: Revolutionizing Front-End Development with Django and HTMX | Gianluca Romanin | 26m |
Argues that a Backend-First approach with Django and HTMX moves UI logic to the server, reducing client complexity and enabling faster prototyping and stronger… | ||
| A Pythonic semantic search | Paolo Melchiorre | 29m |
Implements a working semantic search using Django + PostgreSQL + PGVector and Sentence Transformers, with embeddings computed in Python and saved to a PGVector… | ||
| Fast Jigsaw Puzzle Solving with Python: From CV Algorithms to Applications | Peichao Qin | 32m |
A pipeline extracts contours from images with OpenCV and NumPy, smooths and simplifies them (Gaussian + Douglas-Peucker), filters candidates by cosine… | ||
| Demystifying Design Patterns: A Practical Guide for Developers | Tanu Batra | 32m |
Covers UML and SOLID with concrete refactors: split Order/Notification for single responsibility, wrap DB access behind an abstraction for dependency inversion… | ||
| Making EPUBs Accessible with AI: A Serverless Pipeline for Automated Alt Text Generation | Data Office | 30m |
A serverless pipeline generates alt text for EPUB images at scale, handling ~130,000 images from 160 books per year, with editorial review in the loop and… | ||
| RLoop: an AsyncIO event loop implemented in Rust | Giovanni Barillari | 28m |
RLoop is an AsyncIO event loop written in Rust that is usable but in alpha state. It implements selector-based AsyncIO (no Windows proactor) with roughly 1000… | ||
| Supporting Adult Career Switchers: The Unbootcamp Method | Mykalin Jones | 27m |
Introduces a four-pronged Unbootcamp method: tighten fundamentals, design job-relevant portfolio projects, teach technical interview basics, and pair… | ||
| A tour of the module itertools | Rodrigo Girão Serrão | 33m |
The module contains 20 tools and the talk demonstrates roughly 10 of them, claiming many are lazy like range laziness and work on any iterable. Examples… | ||
| Efficient AI with Python: running AI models on CPUs | Michele Mondelli | 29m |
Demonstrates running inference on CPUs using OpenVINO with Python, exporting models to an optimized format and letting the runtime re-optimize per-processor… | ||
| 🤯 No data? No problem! Synthetic data to the rescue | David Berenstein | 30m |
Claims that synthetic data speeds model development and reduces cost and privacy risk by generating training and evaluation sets from prompts. A reproducible… | ||
| uv without sunblock: faster than ever dependency and project management | Vinícius Gubiani Ferreira | 33m |
uv is a Rust tool from Astro that replaces juggling pip, virtualenv, pyenv and packaging by doing dependency resolution, venv management, Python installation… | ||
| Design by Contract: Building Robust Software with Contract-First Development | Antonio Spadaro | 27m |
Explains Design by Contract and Contract-First Development as a way to define explicit requirements and constraints to prevent errors and improve… | ||
| I feel like writing software documentation is like doing my taxes - help! | Maren Westermann | 29m |
Some scikit-learn and NALs docstrings are removed and GitHub Copilot is asked to regenerate examples, parameter docs and method docs; the tool produces a… | ||
| Hot-swapping Symbols During Tests: Demystifying unittest.mock[.patch] | Bryce Beagle | 31m |
Rebuilds how unittest.mock actually works by coding a minimal patcher, context-manager decorator and callable Mock/MagicMock that match stdlib behavior (but… | ||
| So you want a modern frontend for your Python web app? | Sheena | 30m |
Shows that replacing a heavy SPA stack (React + Redux + DRF) with server‑rendered Django plus HTMX and AlpineJS delivers concrete gains: the codebase shrunk… | ||
| Adversarial Intelligence: Using GANs in Cybersecurity | Serena Sensini | 27m |
Covers how generative adversarial networks (GANs) are applied in cybersecurity, specifically for intrusion detection and malware generation. Describes using… | ||
| Programming hardware displays the easy way - using MicroPython and LVGL | Marc-André Lemburg | 30m |
Builds a battery‑powered conference talk timer using MicroPython + LVGL on an ESP32 touchscreen (CYD aka cheap yellow display), costs €8–€23, runs but needs… | ||
| Under the Hood of Python Data Structures | Salvatore Giammanco | 29m |
CPython source code and quick REPL experiments show lists as contiguous dynamic arrays that overallocate (~12.5%) using a shift-and-round formula when append… | ||
| Intuition vs. Reality: Surprising Truths in Python Performance | Arthur Pastel, Adrien Cacciaguerra | 30m |
Interactive benchmarks compare concrete snippets and tools: an async sleep left un-awaited returns immediately; counting evens shows len(listcomprehension)… | ||
| The Art of Data Visualization | Alessandra Bilardi | 30m |
Covers the role of data visualization across a data pipeline, including exploratory analysis, presenting results, and monitoring progress or improvements… | ||
| Accessible components and zero framework | Diana Bernabei | 30m |
Practical guide to building accessible UI components without any framework, using vanilla HTML, CSS and JavaScript. It shows how to implement WCAG 2.2… | ||
| Get Accessibility Right: Shift It Left! | ChiaraCielo Longobardi | 30m |
Tests of two train sites show one is unusable by keyboard while Trenitalia becomes purchasable in March, the other never exposes focus; a weather site forces… | ||
| Postgres Partitioning Best Practices | Karen Jex | 31m |
Partitioning splits a huge table into child tables so operations like purging 2023 become a fast drop partition instead of a slow DELETE; example uses one… | ||
| Typing your Python code like a ninja! | Thiago Bellini Ribeiro | 31m |
Covers concrete typing techniques and shows them working: uses overload with a single implementation to give precise return types (example: get_user with… | ||
| RAG: Tricks from the trenches. | Duarte Carmo | 30m |
Practical RAG lessons: changing one embedding model raises relevant-retrieval from about 16.5% to 62.89% (roughly a 300% gain), so embedding choice matters… | ||
| Hugging Face ecosystem for Local AI/ ML | Vaibhav Srivastav | 31m |
Live demo shows a 1.7B model in browser using WebGPU/TVM and llama.cpp to parse unstructured text into JSON and to call a Hugging Face Space for image… | ||
| Continuous Documentation: basics and advanced techniques | Anastasiia Tymoshchuk | 29m |
A single-source doc site using sphinx and hosting on Read the Docs becomes the canonical place, with CI checks (fail the PR if docstrings or percentage… | ||
| Working with Data Scientists and why I left my job (not) | Francesco Lucantoni | 26m |
Three years of cross‑functional teams at Prima move data scientists from notebook chaos into production-safe workflows using git branches and required one… | ||
| PyPI in the face: running jokes that PyPI download stats can play on you | Loïc Estève | 32m |
scikit-learn maintainers try to use PyPI counts and find BigQuery and clickhouse-backed dashboards misleading: automated cloud workflows dominate downloads… | ||
| Designing and Building Custom Keyboards ⌨️ with Python | Carlos A Aranibar | 29m |
History of QWERTY leads to redesigns and a working build shows the payoff: a pivoted Liy58 58-key build with hot sockets, Pro Micro/RP2040 controller, OLED and… | ||
| Observing Python applications with OpenTelemetry | Riccardo Magliocchetti | 30m |
Compares three concrete ways to add OpenTelemetry to Python without code changes: Kubernetes operator that injects autoinstrumentation into pods and runs a… | ||
| Build, Deploy, Monetize: The Future of the Developer Economy | Saurav Jain | 27m |
Platform converts any input→output program into a serverless “actor” by adding five files (mandatory actor.json and Dockerfile, optional input/output schemas… | ||
| Random stuff about hard problems | Andrea Griffini | 31m |
Examines using random choices to tackle hard computational problems by demonstrating the random walk method in pure Python (no special libraries). Covers… | ||
| Reconstructing Unseen Dimensions in Biophotonics Through Python | Serban Cristian Tudosie | 29m |
Combines a high‑resolution SIMOS intensity volume (up to ~2000×2000 with ~20 z‑slices) and a low‑res single‑pixel camera tensor (32×32 spatial with spectral… | ||
| Private Generative Models: Balancing Privacy and Utility in AI | Navid Nobani | 30m |
Private generative models claim to protect individuals while keeping data useful by using techniques like differential privacy, teacher‑student aggregation… | ||
| Python Containers: Best Practices | Daniel Hervás | 30m |
Recommends Yan Smith’s Dockerfiles, uses multi-stage builds and Trivy scans, and demonstrates that running an OS update during image build fixes 20+… | ||
| Deploy FastAPI to the cloud | Sebastián Ramírez | 29m |
Builds a small FastAPI app locally, runs it with Uvicorn and a virtualenv, then uses the FastAPI Cloud CLI to send code and dependency descriptions and deploys… | ||
| Practical Python parsing with the ast standard module | Domenico Nucera | 28m |
Shows how to use the standard ast library to parse Python code with ast.parse and inspect nodes via ast.walk and NodeVisitor/NodeTransformer. Demonstrates a… | ||
| Crash detector | Daniele Maccagnola, Angela Addesso | 30m |
A crash detector uses a CNN on multivariate time series (time-series treated as images) to filter ~200,000 daily signals down to the ~100 real accidents per… | ||
| Closing | 19m | |
Forty countries attend, with over 1,000 attendees across 120 sessions including three lightning rounds and three social events; organizers count “a lot” of… | ||
| PyCon Italia 2025 Recap — See You in Bologna for PyCon Italia 2026! 🐍 | 01m | |
Video condenses four days of PyCon Italia in Bologna into highlights of deep technical sessions, hands‑on workshops, open source contributor meetups and… | ||
| nothing matches | ||