def load_images(images, data):
"""
Load all of the specified images from the data folder.
:param images: A list of strings that contains the
image name and folder name but not the entire path.
:param data: A base directory to load images from.
:return: A list of numpy array images.
"""
return [load_image(os.path.join(data,image)).reshape(224,224,3) \
for image in images]
def main(args):
print('[INFO] Starting clustering...')
# Setup weights and biases
setup_wandb(args)
# Setup the pre-trained backbone for our model. This is
# done first to get the preprocessing function for the net.
encoder, preprocess = model_factory(args.backbone, pooling=args.pooling)
# Load the images into memory. Right now
# I am not supporting loading from disk.
train, dev = load_dataframes(args.base_dir, args.min_samples)
# Load the features for the dev set which we
# are going to cluster up.
features = np.zeros(shape=(len(train) + len(dev), encoder.output.shape[1]))
for i, imagefile in enumerate(train['file']):
img = load_image(image_path=os.path.join(args.base_dir,
'train/' + imagefile),
preprocess_input=preprocess)
features[i, :] = encoder.predict(img)
for i, imagefile in enumerate(dev['file']):
img = load_image(image_path=os.path.join(args.base_dir,
'dev/' + imagefile),
preprocess_input=preprocess)
features[i + len(train), :] = encoder.predict(img)
# Scale before doing PCA, which
# expects to have standardized
# features.
scaler = StandardScaler()
features = scaler.fit_transform(features)
if args.pca_components > 0:
pca = PCA(n_components=args.pca_components)
features = pca.fit_transform(features)
# Setup clustering
agglom = AgglomerativeClustering(n_clusters=args.clusters,
affinity=args.affinity)
print('[INFO] Running clustering...')
agglom.fit(features)
# Save the dataframe of validation predictions and labels
df = pd.DataFrame({
'file': dev['file'],
'label': dev['label'],
'pred': agglom.labels_[len(train):]
})
df.to_csv('dev_agglom_pca_ms{}_{}.csv'.format(args.min_samples,
wandb.run.id),
index=False)
# A quick performance estimate.
ar_score = adjusted_rand_score(dev['label'], agglom.labels_[len(train):])
wandb.log({'ari': ar_score})
wandb.log({
'nmi':
normalized_mutual_info_score(dev['label'], agglom.labels_[len(train):])
})
if args.pca_components > 0:
wandb.log(
{'explained_variance': np.sum(pca.explained_variance_ratio_)})
else:
wandb.log({'explained_variance': 0.00})
# if the number of clusters is the same as
# the true labels, we can do hungarian
if args.clusters == dev['label'].nunique():
hba = hungarian_balanced_accuracy(
LabelEncoder().fit_transform(df['label']), df['pred'])
wandb.log({'balanced_accuracy': hba})
hba = hungarian_accuracy(LabelEncoder().fit_transform(df['label']),
df['pred'])
wandb.log({'accuracy': hba})
print('[INFO] Finished!')
def main(args):
print('[INFO] Starting clustering...')
# Setup weights and biases
setup_wandb(args)
# Setup the pre-trained backbone for our model. This is
# done first to get the preprocessing function for the net.
encoder, preprocess = model_factory(args.backbone, pooling=args.pooling)
# Load the images into memory. Right now
# I am not supporting loading from disk.
train, dev = load_dataframes(args.base_dir, args.min_samples)
# Load the features for the dev set which we
# are going to cluster up.
features = np.zeros(shape=(len(train) + len(dev), encoder.output.shape[1]))
for i, imagefile in enumerate(train['file']):
img = load_image(image_path=os.path.join(args.base_dir,
'train/' + imagefile),
preprocess_input=preprocess)
features[i, :] = encoder.predict(img)
for i, imagefile in enumerate(dev['file']):
img = load_image(image_path=os.path.join(args.base_dir,
'dev/' + imagefile),
preprocess_input=preprocess)
features[i + len(train), :] = encoder.predict(img)
# Scale before doing PCA, which
# expects to have standardized
# features.
scaler = StandardScaler()
features = scaler.fit_transform(features)
if args.pca_components > 0:
pca = PCA(n_components=args.pca_components)
features = pca.fit_transform(features)
# Setup DBSCAN
dbscan = DBSCAN(eps=args.eps,
min_samples=args.min_dbscan_samples,
n_jobs=-1)
print('[INFO] Running DBSCAN...')
dbscan.fit(features)
# Save the dataframe of validation predictions and labels
pd.DataFrame({
'file': dev['file'],
'label': dev['label'],
'pred': dbscan.labels_[len(train):]
}).to_csv('dev_dbscan_pca_ms{}_{}.csv'.format(args.min_samples,
wandb.run.id),
index=False)
# A quick performance estimate.
ar_score = adjusted_rand_score(dev['label'], dbscan.labels_[len(train):])
wandb.log({'ari': ar_score})
wandb.log({
'nmi':
normalized_mutual_info_score(dev['label'], dbscan.labels_[len(train):])
})
if args.pca_components > 0:
wandb.log(
{'explained_variance': np.sum(pca.explained_variance_ratio_)})
else:
wandb.log({'explained_variance': 0.00})
# Log the number of empty clusters
# on the dev set.
nunique = len(np.unique(dbscan.labels_))
wandb.log({'dev_clusters': nunique})
print('[INFO] Finished!')