summaryrefslogtreecommitdiff
path: root/cli/app
diff options
context:
space:
mode:
Diffstat (limited to 'cli/app')
-rw-r--r--cli/app/commands/biggan/extract_dense_vectors.py49
-rw-r--r--cli/app/commands/biggan/fetch.py4
-rw-r--r--cli/app/commands/biggan/search_class.py9
-rw-r--r--cli/app/search/json.py27
-rw-r--r--cli/app/search/search_class.py11
-rw-r--r--cli/app/search/search_dense.py21
-rw-r--r--cli/app/utils/cortex_utils.py9
7 files changed, 90 insertions, 40 deletions
diff --git a/cli/app/commands/biggan/extract_dense_vectors.py b/cli/app/commands/biggan/extract_dense_vectors.py
new file mode 100644
index 0000000..2436ce6
--- /dev/null
+++ b/cli/app/commands/biggan/extract_dense_vectors.py
@@ -0,0 +1,49 @@
+import click
+import os
+
+from app.utils.cortex_utils import fetch_cortex_folder, find_unprocessed_files
+from app.search.search_class import find_nearest_vector_for_images
+from app.search.search_dense import find_dense_embedding_for_images
+from app.search.json import params_dense_dict
+
+@click.command('')
+@click.option('-f', '--folder_id', 'opt_folder_id', type=int,
+ help='Folder ID to process')
+@click.option('-ls', '--latent_steps', 'opt_latent_steps', default=2000, type=int,
+ help='Number of optimization iterations')
+@click.option('-ds', '--dense_steps', 'opt_dense_steps', default=2000, type=int,
+ help='Number of optimization iterations')
+@click.option('-v', '--video', 'opt_video', is_flag=True,
+ help='Export a video for each dataset')
+@click.pass_context
+def cli(ctx, opt_folder_id, opt_latent_steps, opt_dense_steps, opt_video):
+ """
+ The full process:
+ - Fetch new images from the cortex
+ - Extract labels and base latents
+ - Extract dense embeddings
+ - Upload extract images to the cortex
+ """
+ folder = cortex_folder(opt_folder_id)
+ files = download_cortex_files(opt_folder_id)
+ unprocessed_files = find_unprocessed_files(files)
+ if len(unprocessed_files) == 0:
+ print("All files processed, nothing to do")
+ return
+
+ print("Processing folder {} ({}), {} new files".format(folder['name'], folder['id'], len(unprocessed_files)))
+
+ tag = "folder_{}".format(folder['id'])
+ paths = [file['path'] for file in unprocessed_files]
+
+ find_nearest_vector_for_images(
+ paths=paths,
+ opt_dims=512,
+ opt_steps=opt_dense_steps,
+ opt_video=opt_video,
+ opt_tag=tag,
+ opt_limit=-1
+ )
+
+ params = params_dense_dict(tag)
+ find_dense_embedding_for_images(params)
diff --git a/cli/app/commands/biggan/fetch.py b/cli/app/commands/biggan/fetch.py
index 39f503c..d454633 100644
--- a/cli/app/commands/biggan/fetch.py
+++ b/cli/app/commands/biggan/fetch.py
@@ -9,9 +9,9 @@ from app.utils.cortex_utils import fetch_cortex_folder, find_unprocessed_files
@click.pass_context
def cli(ctx, opt_folder_id):
"""
- Fetch JSON from the server
+ Fetch new images from the server
"""
- files = fetch_cortex_folder(opt_folder_id)
+ files = download_cortex_files(opt_folder_id)
unprocessed_files = find_unprocessed_files(files)
print("Unprocessed files:")
for file in unprocessed_files:
diff --git a/cli/app/commands/biggan/search_class.py b/cli/app/commands/biggan/search_class.py
index 0501729..311dc70 100644
--- a/cli/app/commands/biggan/search_class.py
+++ b/cli/app/commands/biggan/search_class.py
@@ -21,4 +21,11 @@ def cli(ctx, opt_fp_in, opt_dims, opt_steps, opt_limit, opt_video, opt_tag):
"""
Search for an image (class vector) in BigGAN using gradient descent
"""
- find_nearest_vector_for_images(opt_fp_in, opt_dims, opt_steps, opt_limit, opt_video, opt_tag)
+ if os.path.isdir(opt_fp_in):
+ paths = glob(os.path.join(opt_fp_in, '*.jpg')) + \
+ glob(os.path.join(opt_fp_in, '*.jpeg')) + \
+ glob(os.path.join(opt_fp_in, '*.png'))
+ else:
+ paths = [opt_fp_in]
+
+ find_nearest_vector_for_images(paths, opt_dims, opt_steps, opt_video, opt_tag, opt_limit)
diff --git a/cli/app/search/json.py b/cli/app/search/json.py
index beaed3b..b47512d 100644
--- a/cli/app/search/json.py
+++ b/cli/app/search/json.py
@@ -1,4 +1,5 @@
from os.path import join
+from app.settings import app_cfg
from app.utils.file_utils import write_json
from app.search.params import ParamsDict
@@ -10,7 +11,9 @@ def make_params_latent(fp_out_dir, tag):
"clip": 1.0,
"stochastic_clipping": False,
"clipping": False,
- "dataset": "inverses/{}/dataset.hdf5".format(tag),
+ "path": os.path.join(app_cfg.DIR_INVERSES, tag),
+ "dataset": os.path.join(app_cfg.DIR_INVERSES, tag, "dataset.hdf5"),
+ "out_dataset": os.path.join(app_cfg.DIR_INVERSES, tag, "dataset.latent.hdf5"),
"inv_layer": "latent",
"decay_lr": True,
"inv_it": 15000,
@@ -41,19 +44,18 @@ def make_params_latent(fp_out_dir, tag):
"lambda_reg": 0.1,
"dist_loss": False,
"sample_size": 4,
- "dataset": "inverses/{}/dataset.encodings.hdf5".format(tag),
"save_progress": True,
}
-def params_latent(fp_out_dir, tag):
- return ParamsDict(make_params_latent(fp_out_dir, tag))
+def params_latent(tag):
+ return ParamsDict(make_params_latent(tag))
def save_params_latent(fp_out_dir, tag):
- data = make_params_latent(fp_out_dir, tag)
+ data = make_params_latent(tag)
fp_out_fn = join(fp_out_dir, "params_latent.json")
write_json(data, fp_out_fn)
-def make_params_dense(fp_out_dir, tag, folder_id=None):
+def make_params_dense(tag):
return {
"tag": tag,
"folder_id": folder_id,
@@ -62,7 +64,8 @@ def make_params_dense(fp_out_dir, tag, folder_id=None):
"clip": 1.0,
"stochastic_clipping": False,
"clipping": False,
- "dataset": "inverses/{}/dataset.encodings.hdf5".format(tag),
+ "path": os.path.join(app_cfg.DIR_INVERSES, tag),
+ "dataset": os.path.join(app_cfg.DIR_INVERSES, tag, "dataset.latent.hdf5"),
"inv_layer": "Generator_2/G_Z/Reshape:0",
"decay_lr": False,
"inv_it": 6000,
@@ -93,15 +96,15 @@ def make_params_dense(fp_out_dir, tag, folder_id=None):
"lambda_reg": 0.1,
"dist_loss": True,
"sample_size": 4,
- "out_dataset": "inverses/{}/dataset.encodings.dense.hdf5".format(tag),
+ "out_dataset": os.path.join(app_cfg.DIR_INVERSES, tag, "dataset.dense.hdf5"),
"save_progress": True,
"max_batches": 0,
}
-def params_dense_dict(fp_out_dir, tag, folder_id=None):
- return ParamsDict(make_params_dense(fp_out_dir, tag, folder_id))
+def params_dense_dict(tag):
+ return ParamsDict(make_params_dense(tag))
-def save_params_dense(fp_out_dir, tag, folder_id):
- data = make_params_dense(fp_out_dir, tag, folder_id)
+def save_params_dense(fp_out_dir, tag):
+ data = make_params_dense(tag)
fp_out_fn = join(fp_out_dir, "params_dense.json")
write_json(data, fp_out_fn)
diff --git a/cli/app/search/search_class.py b/cli/app/search/search_class.py
index eba61e8..7eab4bc 100644
--- a/cli/app/search/search_class.py
+++ b/cli/app/search/search_class.py
@@ -24,23 +24,16 @@ from app.search.image import image_to_uint8, imconvert_uint8, imconvert_float32,
from app.search.vector import truncated_z_sample, truncated_z_single, \
create_labels, create_labels_uniform
-def find_nearest_vector_for_images(opt_fp_in, opt_dims, opt_steps, opt_limit, opt_video, opt_tag):
+def find_nearest_vector_for_images(paths, opt_dims, opt_steps, opt_video, opt_tag, opt_limit=-1):
sess = tf.compat.v1.Session()
tf.reset_default_graph()
generator = hub.Module('https://tfhub.dev/deepmind/biggan-512/2')
- if os.path.isdir(opt_fp_in):
- paths = glob(os.path.join(opt_fp_in, '*.jpg')) + \
- glob(os.path.join(opt_fp_in, '*.jpeg')) + \
- glob(os.path.join(opt_fp_in, '*.png'))
- else:
- paths = [opt_fp_in]
-
fp_inverses = os.path.join(app_cfg.DIR_INVERSES, opt_tag)
os.makedirs(fp_inverses, exist_ok=True)
save_params_latent(fp_inverses, opt_tag)
save_params_dense(fp_inverses, opt_tag)
- out_file = h5py.File(join(fp_inverses, 'dataset.hdf5'), 'w')
+ out_file = h5py.File(join(fp_inverses, 'dataset.latent.hdf5'), 'w')
out_images = out_file.create_dataset('xtrain', (len(paths), 3, 512, 512,), dtype='float32')
out_labels = out_file.create_dataset('ytrain', (len(paths), 1000,), dtype='float32')
out_latent = out_file.create_dataset('latent', (len(paths), 128,), dtype='float32')
diff --git a/cli/app/search/search_dense.py b/cli/app/search/search_dense.py
index 392fa70..a538d0d 100644
--- a/cli/app/search/search_dense.py
+++ b/cli/app/search/search_dense.py
@@ -72,15 +72,13 @@ def find_dense_embedding_for_images(params):
LATENT_TAG = 'latent' if params.inv_layer == 'latent' else 'dense'
BATCH_SIZE = params.batch_size
SAMPLE_SIZE = params.sample_size
- LOGS_DIR = os.path.join('inverses', params.tag, LATENT_TAG, 'logs')
- SAMPLES_DIR = os.path.join('inverses', params.tag, LATENT_TAG, 'samples')
- INVERSES_DIR = os.path.join('inverses', params.tag)
- if not os.path.exists(LOGS_DIR):
- os.makedirs(LOGS_DIR)
- if not os.path.exists(SAMPLES_DIR):
- os.makedirs(SAMPLES_DIR)
- if not os.path.exists(INVERSES_DIR):
- os.makedirs(INVERSES_DIR)
+ LOGS_DIR = os.path.join(params.path, LATENT_TAG, 'logs')
+ SAMPLES_DIR = os.path.join(params.path, LATENT_TAG, 'samples')
+ VECTOR_DIR = os.path.join(params.path, 'vectors')
+
+ os.makedirs(LOGS_DIR, exist_ok=True)
+ os.makedirs(SAMPLES_DIR, exist_ok=True)
+ os.makedirs(VECTOR_DIR, exist_ok=True)
# --------------------------
# Util functions.
@@ -410,7 +408,7 @@ def find_dense_embedding_for_images(params):
NUM_IMGS_TO_PROCESS = NUM_IMGS
# Output file.
- out_file = h5py.File(os.path.join(INVERSES_DIR, params.out_dataset), 'w')
+ out_file = h5py.File(params.out_dataset, 'w')
out_images = out_file.create_dataset('xtrain', [NUM_IMGS_TO_PROCESS,] + IMG_SHAPE, dtype='float32')
out_enc = out_file.create_dataset('encoding', [NUM_IMGS_TO_PROCESS,] + ENC_SHAPE, dtype='float32')
out_lat = out_file.create_dataset('latent', [NUM_IMGS_TO_PROCESS, Z_DIM], dtype='float32')
@@ -421,9 +419,6 @@ def find_dense_embedding_for_images(params):
out_fns[:] = sample_fns[:NUM_IMGS_TO_PROCESS]
- vector_dir = os.path.join(app_cfg.INVERSES_DIR, "vectors")
- os.makedirs(vector_dir, exist_ok=True)
-
# Gradient descent w.r.t. generator's inputs.
it = 0
out_pos = 0
diff --git a/cli/app/utils/cortex_utils.py b/cli/app/utils/cortex_utils.py
index 8076fda..50e85a4 100644
--- a/cli/app/utils/cortex_utils.py
+++ b/cli/app/utils/cortex_utils.py
@@ -10,7 +10,10 @@ def api_url(path):
"""Generate a base API path"""
return "https://lens.neural.garden/api/{}/".format(path)
-def fetch_cortex_folder(opt_folder_id):
+def cortex_folder(opt_folder_id):
+ return fetch_json(os.path.join(api_url('folder'), str(opt_folder_id) + "/"))
+
+def download_cortex_files(opt_folder_id):
"""Fetch all new, non-generated files in a Cortex folder"""
rows = fetch_json(api_url('file'), folder_id=opt_folder_id)
fp_out_dir = join(app_cfg.DIR_INPUTS, "cortex", str(opt_folder_id))
@@ -31,12 +34,12 @@ def find_unprocessed_files(files):
datasets = {}
unprocessed_files = []
for file in files:
- if file['generated'] == 1:
+ if file['generated'] == 1 and file['type'] == 'image':
fn, ext = os.path.splitext(file['name'])
dataset = fn.split('-')[0]
datasets[dataset] = file['id']
for file in files:
- if file['generated'] == 0 and file['processed'] != 1:
+ if file['generated'] == 0 and file['processed'] == 0 and file['type'] == 'image':
fn, ext = os.path.splitext(file['name'])
dataset = fn.split('-')[0]
if dataset not in datasets:
generated by cgit v1.2.3-70-g09d2 (git 2.51.0) at 2025-12-10 11:54:03 +0000