Mathis/CUDANet
1
0
Fork 0
mirror of https://github.com/lordmathis/CUDANet.git synced 2025-11-05 17:34:21 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
7b8c4bd811fcaa636cd1b9018fc8f2073d48d936
CUDANet/examples/inception_v3/README.md
LordMathis 7b8c4bd811 Update inception v3 readme
2024-09-04 21:32:05 +02:00

1.0 KiB
Raw Blame History

Inception v3

Inception v3 Inference on CUDANet

Usage

  1. Export pytorch Inception v3 weights pretrained on ImageNet (requires pytorch and torchvision):
python inception_v3.py

  1. Follow the instructions from the repository root to build the CUDANet library.

  2. Build Inception v3 (requires OpenCV for image loading and preprocessing):

mkdir build
cd build
cmake -S ..
make
  1. (Optional) Run tests

Generate test input/output and resources by running inception_blocks.py in the test folder

Build and run tests (requires Google Test)

cd build
make test_inception_v3
./tests/test_inception_v3
  1. Run Inception v3 inference:
inception_v3 ../inception_v3_weights.bin ../image.jpg

Note on Preprocessing

The image preprocessing in this implementation uses OpenCV, which may produce slightly different results compared to PyTorch's Pillow-based preprocessing due to differences in interpolation methods during resizing.