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
#!/usr/bin/env python3
# Detailed API example. We show which functions are called inside
# get_image_data() (read_images(), get_model(), fingerprints(), pca(),
# read_timestamps()) and show more options such as time distance scaling.
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/')
#!/usr/bin/python3
from imagecluster import calc, io as icio, postproc
from ecosia_images import crawler
searcher = crawler(naming='hash')
searcher.search('chilaquiles')
searcher.download(50)
images = icio.read_images('downloads/chilaquiles', 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)
print(fingerprints)
# 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)
print(fingerprints)
# Read image timestamps. Need that to calculate the time distance, can be used
# in clustering.
timestamps = icio.read_timestamps('downloads/chilaquiles')
# Run clustering on the fingerprints. Select clusters with similarity index
# sim=0.5. Mix 80% content distance with 20% timestamp distance (alpha=0.2).