Articles about random stuff I find interesting.
MNIST Benchmarks (CPU vs GPU / Tensorflow vs Pytorch)
I got ROCm to work on my laptop and guess what that means, benchmarks! Hardware Form factor: Laptop Model: Asus G513QY CPU: AMD Ryzen 5900HX (83rd percentile on cpu.userbenchmark.com, ~ 10% slower than a desktop 5500) GPU: AMD Radeon 6800m (91st percentile on gpu.userbenchmark.com, ~15% slower than a desktop 3060, 1/5th the power of a desktop 4090) Tensorflow Model Summary Model: "sequential" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= conv2d (Conv2D) (None, 26, 26, 32) 320 conv2d_1 (Conv2D) (None, 24, 24, 64) 18496 max_pooling2d (MaxPooling2D (None, 12, 12, 64) 0 ) dropout (Dropout) (None, 12, 12, 64) 0 flatten (Flatten) (None, 9216) 0 dense (Dense) (None, 128) 1179776 dense_1 (Dense) (None, 10) 1290 ================================================================= Total params: 1,199,882 Trainable params: 1,199,882 Non-trainable params: 0 _________________________________________________________________ Code can be found here ...