Skip to content

Instantly share code, notes, and snippets.

View GuruMulay's full-sized avatar
🎯
Focusing

Guru GuruMulay

🎯
Focusing
View GitHub Profile
@GuruMulay
GuruMulay / video_to_frames_writer.py
Last active January 11, 2023 03:53
A script to read a video using PyAV and write its individual frames using PIL or skimage.
import av
import PIL
import skimage.io
from skimage.transform import resize, pyramid_reduce
import numpy as np
import os
import argparse
"""
@GuruMulay
GuruMulay / model.py
Created March 4, 2018 18:23 — forked from ndronen/model.py
Semantic segmentation with ENet in PyTorch
#!/usr/bin/env python
"""
A quick, partial implementation of ENet (https://arxiv.org/abs/1606.02147) using PyTorch.
The original Torch ENet implementation can process a 480x360 image in ~12 ms (on a P2 AWS
instance). TensorFlow takes ~35 ms. The PyTorch implementation takes ~25 ms, an improvement
over TensorFlow, but worse than the original Torch.
"""
from __future__ import absolute_import