TildAlice – Tech Blog for Developers
Python, AI, Deep Learning, Data Analysis, Computer Vision, Reinforcement Learning โ tips and tutorials
Latest Posts
-
Raspberry Pi 5 vs Jetson Nano: MobileNet Inference 38ms Gap
Pi 5 hits 38ms INT8 inference vs Jetson's 12ms โ but costs $90 less. Real TFLite/ONNX benchmarks reveal when each board wins.
-
Stack vs Recursion for Tree Traversal: 3 Real Reasons
Compare stack vs recursion for tree traversal with 3 performance insights. Which method wins for memory efficiency and speed? Find out here.
-
Whisper Tiny vs faster-whisper: 3x Speed, 12% WER Gap
faster-whisper cuts Jetson Nano latency 68% but WER jumps to 20%. Real benchmarks, memory spikes, and the thermal throttling nobody mentions.
-
YOLO vs SAM Instance Segmentation: GPU Cost per 1M Runs
YOLO vs SAM at 1M inferences: $11 vs $157 GPU cost on V100. Real wall-clock benchmarks, VRAM limits, and when SAM's 14x premium is justified.
-
Kalman vs Particle vs LSTM: Trade Signal Latency Under 5ms
Particle filters hit 47ms latency spikes vs Kalman's 0.02ms. Here's the benchmark code and when each filter actually wins for trade signals.
-
OpenCV Face Detection: 20 Lines That Actually Work
Build real-time face detection in 20 lines of OpenCV Python. Cascade classifiers explained with working code that runs on any webcam today.
-
Factor Models vs ML: Alpha with 200 Samples, Not 200K
Compare factor models and ML for alpha generation in low-data regimes. Learn why traditional quant methods outperform deep learning with limited samples.