Skip to content

Instantly share code, notes, and snippets.

Repo

Haven't decided if I am going to submit code to it yet

Questions

👍 - Unlocked & Done 😊 - Locked & Done 🔒 - Locked & Not Done [] - Not yet Done

@AshStuff
AshStuff / train.py
Last active December 26, 2018 10:07
import math
import torch
import torch.nn as nn
import numpy as np
from torch.utils.checkpoint import checkpoint
def convert_x1y1x2y2_to_xywh(box):
"""

#State Farm Distracted Driver Detection

Data Set Information

##1.How many images in total? Training images= 22424 Test images = 79726 ##2.How many images for each class? Aproximately 2200 images in each class. Total 10 classes. ##3.How many drivers are there? 10 drivers. ##4. Is it possible that the driver id is related to the classification accuracy?