mirrors
/
yolov5
mirror of https://github.com/ultralytics/yolov5.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Robust `scipy.cluster.vq.kmeans` too few points (#6668) 

* Handle `scipy.cluster.vq.kmeans` too few points

Resolves #6664

* Update autoanchor.py

* Cleanup
pull/6669/head
Glenn Jocher 2022-02-17 12:55:03 +01:00 committed by GitHub
parent 7b80545e8e
commit 2e5c67e537
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
utils/autoanchor.py
View File

@ -1,6 +1,6 @@
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
Auto-anchor utils
AutoAnchor utils
"""
import random
@ -81,6 +81,7 @@ def kmean_anchors(dataset='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen
"""
from scipy.cluster.vq import kmeans
npr = np.random
thr = 1 / thr
def metric(k, wh): # compute metrics
@ -121,14 +122,15 @@ def kmean_anchors(dataset='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen
if i:
LOGGER.info(f'{PREFIX}WARNING: Extremely small objects found. {i} of {len(wh0)} labels are < 3 pixels in size.')
wh = wh0[(wh0 >= 2.0).any(1)] # filter > 2 pixels
# wh = wh * (np.random.rand(wh.shape[0], 1) * 0.9 + 0.1) # multiply by random scale 0-1
# wh = wh * (npr.rand(wh.shape[0], 1) * 0.9 + 0.1) # multiply by random scale 0-1
# Kmeans calculation
LOGGER.info(f'{PREFIX}Running kmeans for {n} anchors on {len(wh)} points...')
s = wh.std(0) # sigmas for whitening
k, dist = kmeans(wh / s, n, iter=30) # points, mean distance
assert len(k) == n, f'{PREFIX}ERROR: scipy.cluster.vq.kmeans requested {n} points but returned only {len(k)}'
k *= s
k = kmeans(wh / s, n, iter=30)[0] * s # points
if len(k) != n: # kmeans may return fewer points than requested if wh is insufficient or too similar
LOGGER.warning(f'{PREFIX}WARNING: scipy.cluster.vq.kmeans returned only {len(k)} of {n} requested points')
k = np.sort(npr.rand(n * 2)).reshape(n, 2) * img_size # random init
wh = torch.tensor(wh, dtype=torch.float32) # filtered
wh0 = torch.tensor(wh0, dtype=torch.float32) # unfiltered
k = print_results(k, verbose=False)
@ -146,7 +148,6 @@ def kmean_anchors(dataset='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen
# fig.savefig('wh.png', dpi=200)
# Evolve
npr = np.random
f, sh, mp, s = anchor_fitness(k), k.shape, 0.9, 0.1 # fitness, generations, mutation prob, sigma
pbar = tqdm(range(gen), desc=f'{PREFIX}Evolving anchors with Genetic Algorithm:') # progress bar
for _ in pbar: