TildAlice – Tech Blog for Developers
Python, AI, Deep Learning, Data Analysis, Computer Vision, Reinforcement Learning โ tips and tutorials
Latest Posts
-
Pandas Time Series Resample: OHLC 14x Faster Than Custom
Pandas resample OHLC beats custom groupby 14x faster for time series aggregation. Discover why built-in wins and when to use which method.
-
Python weakref for Cache Systems: Prevent Memory Leaks
Stop cache memory leaks with Python weakref. WeakValueDictionary auto-evicts unused entriesโsee real benchmarks and production patterns.
-
MobileNetV3 vs EfficientNet-Lite: ARM CPU Latency Benchmark
MobileNetV3-Small runs 2.9x faster than EfficientNet-Lite0 on Raspberry Pi 4โ23ms vs 67ms. Here's why paper FLOPs don't match real ARM latency.
-
Pandas vs SQL: 3.2x Speed Gap in Real Data Cleaning Jobs
Compare Pandas vs SQL performance in real data cleaning tasks. Benchmark reveals surprising winner in the 3.2x speed gapโand when to use each tool.
-
PyTorch 2.6 vs TensorFlow 2.18: 5x Faster Training
PyTorch compile mode hit 847 img/s vs TensorFlow XLA's 612 img/s on ResNet-50. Here's when the 5x speedup actually matters โ and when it breaks.
-
PPO Entropy Decay Bug: Why Exploration Dies at 500K Steps
Your PPO agent flatlines at 500K steps because entropy coefficient decay silently kills exploration. Here's the adaptive fix that saved my Ant-v4 runs.
-
Kubernetes HPA + Triton: Custom Metrics Autoscaling Setup
Build Kubernetes HPA autoscaling for Triton Inference Server using custom GPU metrics. Learn Prometheus adapter setup and scaling policies.