def test_cluster():
# use API
# test clustering
with ImagedirCtx() as ctx:
ias = ic.image_arrays(ctx.imagedir, size=(224, 224))
model = ic.get_model()
fps = ic.fingerprints(ias, model)
fps = ic.pca(fps, n_components=0.95)
clusters = ic.cluster(fps, sim=0.5)
assert set(clusters.keys()) == set(ctx.clusters.keys())
for nimg in ctx.clusters.keys():
for val_clus, ref_clus in zip(clusters[nimg], ctx.clusters[nimg]):
msg = f"ref_clus: {ref_clus}, val_clus: {val_clus}"
assert set(ref_clus) == set(val_clus), msg
def search_cluster(keyword):
directory = 'downloads/%s' % keyword
print('Starting crawler')
searcher = crawler()
try:
print('Searching for %s' % keyword)
searcher.search(keyword)
print('Downloading')
files = searcher.download(32)
except:
searcher.stop()
sys.exit(0)
# print('Converting pictures into jpg')
# for file in files:
# try:
# if not imghdr.what(file) == 'jpeg':
# im = Image.open(file)
# rgb_im = im.convert('RGB')
# rgb_im.save(file + '.jpg')
# except:
# pass
images = icio.read_images(directory, size=(224, 224))
# Create Keras NN model.
model = calc.get_model()
# Feed images through the model and extract fingerprints (feature vectors).
print('Feeding images to the neural network to extract features')
fingerprints = calc.fingerprints(images, model)
# Optionally run a PCA on the fingerprints to compress the dimensions. Use a
# cumulative explained variance ratio of 0.95.
fingerprints = calc.pca(fingerprints, n_components=0.95)
# Run clustering on the fingerprints. Select clusters with similarity index
clusters = calc.cluster(fingerprints, sim=0.5)
# Create dirs with links to images. Dirs represent the clusters the images
# belong to.
postproc.make_links(clusters, directory + '/imagecluster/clusters')
# Plot images arranged in clusters and save plot.
fig, ax = postproc.plot_clusters(clusters, images)
def test_low_level_api_and_clustering():
# use low level API (same as get_image_data) but call all funcs
# test clustering
with ImagedirCtx() as ctx:
images = icio.read_images(ctx.imagedir, size=(224, 224))
model = ic.get_model()
fingerprints = ic.fingerprints(images, model)
for kk, vv in fingerprints.items():
assert isinstance(vv, np.ndarray)
assert len(vv) == 4096, len(vv)
fingerprints = ic.pca(fingerprints, n_components=0.95)
clusters = ic.cluster(fingerprints, sim=0.5)
assert set(clusters.keys()) == set(ctx.clusters.keys())
assert len(fingerprints.keys()) == len(ctx.image_fns)
assert set(fingerprints.keys()) == set(ctx.image_fns)
for nimg in ctx.clusters.keys():
for val_clus, ref_clus in zip(clusters[nimg], ctx.clusters[nimg]):
msg = f"ref_clus: {ref_clus}, val_clus: {val_clus}"
assert set(ref_clus) == set(val_clus), msg
from imagecluster import calc, io as icio, postproc
##images,fingerprints,timestamps = icio.get_image_data(
## 'pics/',
## pca_kwds=dict(n_components=0.95),
## img_kwds=dict(size=(224,224)))
# Create image database in memory. This helps to feed images to the NN model
# quickly.
images = icio.read_images('pics/', size=(224, 224))
# Create Keras NN model.
model = calc.get_model()
# Feed images through the model and extract fingerprints (feature vectors).
fingerprints = calc.fingerprints(images, model)
# Optionally run a PCA on the fingerprints to compress the dimensions. Use a
# cumulative explained variance ratio of 0.95.
fingerprints = calc.pca(fingerprints, n_components=0.95)
# Read image timestamps. Need that to calculate the time distance, can be used
# in clustering.
timestamps = icio.read_timestamps('pics/')
# Run clustering on the fingerprints. Select clusters with similarity index
# sim=0.5. Mix 80% content distance with 20% timestamp distance (alpha=0.2).
clusters = calc.cluster(fingerprints,
sim=0.5,
timestamps=timestamps,
alpha=0.2)
from imagecluster import calc as ic
from imagecluster import postproc as pp
# Create image database in memory. This helps to feed images to the NN model
# quickly.
ias = ic.image_arrays('pics/', size=(224,224))
# Create Keras NN model.
model = ic.get_model()
# Feed images through the model and extract fingerprints (feature vectors).
fps = ic.fingerprints(ias, model)
# Optionally run a PCA on the fingerprints to compress the dimensions. Use a
# cumulative explained variance ratio of 0.95.
fps = ic.pca(fps, n_components=0.95)
# Run clustering on the fingerprints. Select clusters with similarity index
# sim=0.5
clusters = ic.cluster(fps, sim=0.5)
# Create dirs with links to images. Dirs represent the clusters the images
# belong to.
pp.make_links(clusters, 'pics/imagecluster/clusters')
# Plot images arranged in clusters.
pp.visualize(clusters, ias)
#!/usr/bin/python3
from matplotlib import pyplot as plt
import numpy as np
from scipy.cluster.hierarchy import dendrogram
from imagecluster import calc as ic
from imagecluster import io as icio
images = icio.read_images('pics/', size=(224, 224))
model = ic.get_model()
fingerprints = ic.fingerprints(images, model)
clusters, extra = ic.cluster(fingerprints, sim=0.5, extra_out=True)
# linkage matrix Z
fig, ax = plt.subplots()
dendrogram(extra['Z'], ax=ax)
# Adjust yaxis labels (values from Z[:,2]) to our definition of the `sim`
# parameter.
ymin, ymax = ax.yaxis.get_data_interval()
tlocs = np.linspace(ymin, ymax, 5)
ax.yaxis.set_ticks(tlocs)
tlabels = np.linspace(1, 0, len(tlocs))
ax.yaxis.set_ticklabels(tlabels)
ax.set_xlabel("image index")
ax.set_ylabel("sim")
fig.savefig('dendrogram.png')
plt.show()
def main(imagedir, sim=0.5, layer='fc2', size=(224,224), links=True, vis=False,
max_csize=None, pca=False, pca_params=dict(n_components=0.9)):
"""Example main app using this library.
Upon first invocation, the image and fingerprint databases are built and
written to disk. Each new invocation loads those and only repeats
* clustering
* creation of links to files in clusters
* visualization (if `vis=True`)
This is good for playing around with the `sim` parameter, for
instance, which only influences clustering.
Parameters
----------
imagedir : str
path to directory with images
sim : float (0..1)
similarity index (see :func:`calc.cluster`)
layer : str
which layer to use as feature vector (see
:func:`calc.get_model`)
size : tuple
input image size (width, height), must match `model`, e.g. (224,224)
links : bool
create dirs with links
vis : bool
plot images in clusters
max_csize : max number of images per cluster for visualization (see
:mod:`~postproc`)
pca : bool
Perform PCA on fingerprints before clustering, using `pca_params`.
pca_params : dict
kwargs to sklearn's PCA
Notes
-----
imagedir : To select only a subset of the images, create an `imagedir` and
symlink your selected images there. In the future, we may add support
for passing a list of files, should the need arise. But then again,
this function is only an example front-end.
"""
fps_fn = pj(imagedir, ic_base_dir, 'fingerprints.pk')
ias_fn = pj(imagedir, ic_base_dir, 'images.pk')
ias = None
if not os.path.exists(fps_fn):
print(f"no fingerprints database {fps_fn} found")
os.makedirs(os.path.dirname(fps_fn), exist_ok=True)
model = ic.get_model(layer=layer)
if not os.path.exists(ias_fn):
print(f"create image array database {ias_fn}")
ias = ic.image_arrays(imagedir, size=size)
co.write_pk(ias, ias_fn)
else:
ias = co.read_pk(ias_fn)
print("running all images through NN model ...")
fps = ic.fingerprints(ias, model)
co.write_pk(fps, fps_fn)
else:
print(f"loading fingerprints database {fps_fn} ...")
fps = co.read_pk(fps_fn)
if pca:
fps = ic.pca(fps, **pca_params)
print("pca dims:", list(fps.values())[0].shape[0])
print("clustering ...")
clusters = ic.cluster(fps, sim)
if links:
pp.make_links(clusters, pj(imagedir, ic_base_dir, 'clusters'))
if vis:
if ias is None:
ias = co.read_pk(ias_fn)
pp.visualize(clusters, ias, max_csize=max_csize)
def main_kmeans(imagedir,
n_clusters=5,
layer='fc2',
size=(224, 224),
links=True,
pca=False,
pca_params=dict(n_components=0.9)):
"""Example main app using this library.
Upon first invocation, the image and fingerprint databases are built and
written to disk. Each new invocation loads those and only repeats
* clustering
* creation of links to files in clusters
* visualization (if `vis=True`)
This is good for playing around with the `sim` parameter, for
instance, which only influences clustering.
Parameters
----------
imagedir : str
path to directory with images
n_cluster : int (1...999)
num of kmeans cluster (see :func:`calc.cluster_kmeans`)
layer : str
which layer to use as feature vector (see
:func:`calc.get_model`)
size : tuple
input image size (width, height), must match `model`, e.g. (224,224)
links : bool
create dirs with links
pca : bool
Perform PCA on fingerprints before clustering, using `pca_params`.
pca_params : dict
kwargs to sklearn's PCA
Notes
-----
imagedir : To select only a subset of the images, create an `imagedir` and
symlink your selected images there. In the future, we may add support
for passing a list of files, should the need arise. But then again,
this function is only an example front-end.
"""
fps_fn = pj(imagedir, ic_base_dir, 'fingerprints.pk')
ias_fn = pj(imagedir, ic_base_dir, 'images.pk')
ias = None
logger_kmeans = log(logger_name='kmeans').logger
try:
if not os.path.exists(fps_fn):
print("no fingerprints database {} found".format(fps_fn))
logger_kmeans.info(
"no fingerprints database {} found".format(fps_fn))
os.makedirs(os.path.dirname(fps_fn), exist_ok=True)
try:
model = ic.get_model(layer=layer)
except Exception as e:
logger_kmeans.error(e)
if not os.path.exists(ias_fn):
logger_kmeans.info(
"create image array database {}".format(ias_fn))
print("create image array database {}".format(ias_fn))
ias = ic.image_arrays(imagedir, size=size)
co.write_pk(ias, ias_fn)
else:
ias = co.read_pk(ias_fn)
print("running all images through NN model ...")
fps = ic.fingerprints(ias, model)
co.write_pk(fps, fps_fn)
else:
print("loading fingerprints database {} ...".format(fps_fn))
fps = co.read_pk(fps_fn)
if pca:
fps = ic.pca(fps, **pca_params)
print("pca dims:", list(fps.values())[0].shape[0])
logger_kmeans.info("pca dims: " +
str(list(fps.values())[0].shape[0]))
#将每张图片转换成向量
#进行聚类
print("clustering ...")
logger_kmeans.info("clustering ...")
clusters = ic.cluster_kmeans(fps, n_clusters=n_clusters)
if links:
pp.make_links_v2(clusters, pj(imagedir, ic_base_dir, 'clusters'))
except Exception as e:
logger_kmeans.error(e)