TildAlice – Tech Blog for Developers
Python, AI, Deep Learning, Data Analysis, Computer Vision, Reinforcement Learning โ tips and tutorials
Latest Posts
-
Coroutines vs Threading vs Multiprocessing: 10k Requests
Compare Python coroutines vs threading vs multiprocessing for 10k requests. See which wins on speed, CPU usage, and when to use each approach.
-
Transfer Learning CWRU to Custom Bearings: 89% to 67% Drop Fix
Transfer learning CWRU bearings to custom hardware hits 67% accuracy? Learn the domain gap fix with synthetic data and fine-tuning strategies.
-
Backtrader Memory Leak on Multi-Year Tests: 3 Debug Fixes
Fix Backtrader memory leaks in long backtests with 3 proven solutions: cerebro tuning, data cleanup, and RAM monitoring to scale your strategy tests.
-
Gradient Accumulation vs Large Batch: Memory & Cost Test
Compare gradient accumulation vs large batch training in real GPU memory testsโdiscover which method saves more VRAM and when to use each approach
-
PySpark Window Functions: 3 Patterns That Scale Rolling Aggs
Master PySpark window functions with 3 battle-tested patterns for rolling aggregations. Fix memory issues and scale to billions of rows.
-
TFLite & ONNX Mobile Setup: 2x Speed Left on Table
Default TFLite and ONNX configs waste 2-8x performance. Here's the exact setupโdelegates, threads, quantizationโthat closes the gap on ARM devices.
-
FFT vs CWT vs Wavelet Packet: CWRU Bearing Speed Test
Compare FFT, CWT, and Wavelet Packet on CWRU bearing data across speeds. Discover which method wins for fault detection under varying RPMs.
-
Predictive Maintenance Python Tutorial: FFT Pipeline
Build a Python FFT pipeline for predictive maintenance with NumPy and SciPy. Detect bearing faults from vibration signals using spectral analysis.