def setup_sampler(config):
workdir = nh.configure_workdir(config,
workdir=join('~/work/siam-ibeis2',
config['dbname']))
# TODO: cleanup and hook into ibeis AI
if config['dbname'] == 'ggr2':
print('Creating torch CocoDataset')
root = ub.expandpath('~/data/')
print('root = {!r}'.format(root))
train_dset = ndsampler.CocoDataset(
data=join(root, 'ggr2-coco/annotations/instances_train2018.json'),
img_root=join(root, 'ggr2-coco/images/train2018'),
)
train_dset.hashid = 'ggr2-coco-train2018'
vali_dset = ndsampler.CocoDataset(
data=join(root, 'ggr2-coco/annotations/instances_val2018.json'),
img_root=join(root, 'ggr2-coco/images/val2018'),
)
vali_dset.hashid = 'ggr2-coco-val2018'
print('Creating samplers')
samplers = {
'train': ndsampler.CocoSampler(train_dset, workdir=workdir),
'vali': ndsampler.CocoSampler(vali_dset, workdir=workdir),
}
if config['dbname'] == 'ggr2-revised':
print('Creating torch CocoDataset')
root = ub.expandpath('~/data/ggr2.coco.revised')
print('root = {!r}'.format(root))
train_dset = ndsampler.CocoDataset(
data=join(root, 'annotations/instances_train2019.json'),
img_root=join(root, 'images/train2019'),
)
train_dset.hashid = 'ggr2-coco-revised-train2019'
vali_dset = ndsampler.CocoDataset(
data=join(root, 'annotations/instances_val2019.json'),
img_root=join(root, 'images/val2019'),
)
vali_dset.hashid = 'ggr2-coco-revised-val2019'
print('Creating samplers')
samplers = {
'train': ndsampler.CocoSampler(train_dset, workdir=workdir),
'vali': ndsampler.CocoSampler(vali_dset, workdir=workdir),
}
else:
raise KeyError(config['dbname'])
return samplers, workdir
def demo(cls, **kwargs):
from netharn.data.grab_camvid import grab_coco_camvid
import ndsampler
dset = grab_coco_camvid()
sampler = ndsampler.CocoSampler(dset, workdir=None, backend='npy')
self = cls(sampler, **kwargs)
return self
def demo(WindowedSamplerDataset, key='habcam', **kwargs):
import ndsampler
if key == 'habcam':
dset_fpath = ub.expandpath('~/data/noaa/Habcam_2015_g027250_a00102917_c0001_v2_vali.mscoco.json')
workdir = ub.expandpath('~/work/bioharn')
dset = ndsampler.CocoDataset(dset_fpath)
sampler = ndsampler.CocoSampler(dset, workdir=workdir, backend=None)
else:
sampler = ndsampler.CocoSampler.demo(key)
self = WindowedSamplerDataset(sampler, **kwargs)
return self
def grab_camvid_sampler():
"""
Grab a ndsampler.CocoSampler object for the CamVid dataset.
Returns:
ndsampler.CocoSampler: sampler
Example:
>>> # xdoctest: +REQUIRES(--download)
>>> sampler = grab_camvid_sampler()
>>> print('sampler = {!r}'.format(sampler))
>>> # sampler.load_sample()
>>> for gid in ub.ProgIter(sampler.image_ids, desc='load image'):
>>> img = sampler.load_image(gid)
"""
import ndsampler
dset = grab_coco_camvid()
workdir = ub.ensure_app_cache_dir('camvid')
sampler = ndsampler.CocoSampler(dset, workdir=workdir)
return sampler
def __init__(self, storage_mode='numpy', return_mode='tensor', total=24e7):
self.return_mode = return_mode
self.storage_mode = storage_mode
assert self.return_mode in {'tensor', 'dict', 'tuple', 'list'}
if storage_mode == 'numpy':
self.data = np.array([x for x in range(int(total))])
elif storage_mode == 'python':
self.data = [x for x in range(int(total))]
elif storage_mode == 'ndsampler-sql':
import ndsampler
import kwcoco
from kwcoco.coco_sql_dataset import ensure_sql_coco_view
dset = kwcoco.CocoDataset.demo('vidshapes',
num_videos=1,
num_frames=total,
gsize=(64, 64))
dset = ensure_sql_coco_view(dset)
print('dset.uri = {!r}'.format(dset.uri))
dset.hashid = 'fake-hashid'
sampler = ndsampler.CocoSampler(dset, backend=None)
self.data = sampler
# sampler.load_item(0)
# tr = sampler.regions.get_item(0)
# sampler.load_sample(tr)
# assert total <= 1000
# sampler = ndsampler.CocoSampler.demo('shapes{}'.format(total))
# sampler = ndsampler.CocoSampler.demo('shapes{}'.format(total))
elif storage_mode == 'ndsampler':
import ndsampler
# assert total <= 10000
sampler = ndsampler.CocoSampler.demo('vidshapes',
num_videos=1,
num_frames=total,
gsize=(64, 64))
self.data = sampler
else:
raise KeyError(storage_mode)
def detect_cli(config={}):
"""
CommandLine:
python -m bioharn.detect_predict --help
CommandLine:
python -m bioharn.detect_predict \
--dataset=~/data/noaa/Habcam_2015_g027250_a00102917_c0001_v2_test.mscoco.json \
--deployed=/home/joncrall/work/bioharn/fit/runs/bioharn-det-v11-test-cascade/myovdqvi/deploy_MM_CascadeRCNN_myovdqvi_035_MVKVVR.zip \
--out_dpath=~/work/bioharn/habcam_test_out \
--draw=100 \
--input_dims=512,512 \
--xpu=0 --batch_size=1
Ignore:
>>> config = {}
>>> config['dataset'] = '~/data/noaa/Habcam_2015_g027250_a00102917_c0001_v2_vali.mscoco.json'
>>> config['deployed'] = '/home/joncrall/work/bioharn/fit/runs/bioharn-det-v11-test-cascade/myovdqvi/deploy_MM_CascadeRCNN_myovdqvi_035_MVKVVR.zip'
>>> config['out_dpath'] = 'out'
"""
import kwarray
import ndsampler
from os.path import basename, join, exists, isfile, isdir # NOQA
config = DetectPredictCLIConfig(config, cmdline=True)
print('config = {}'.format(ub.repr2(config.asdict())))
out_dpath = ub.expandpath(config.get('out_dpath'))
import six
if isinstance(config['dataset'], six.string_types):
if config['dataset'].endswith('.json'):
dataset_fpath = ub.expandpath(config['dataset'])
coco_dset = ndsampler.CocoDataset(dataset_fpath)
# Running prediction is much faster if you can build a sampler.
sampler_backend = {
'type': 'cog',
'config': {
'compress': 'JPEG',
},
'_hack_old_names': False, # flip to true to use legacy caches
}
sampler_backend = None
print('coco hashid = {}'.format(coco_dset._build_hashid()))
else:
sampler_backend = None
if exists(config['dataset']) and isfile(config['dataset']):
# Single image case
image_fpath = ub.expandpath(config['dataset'])
coco_dset = ndsampler.CocoDataset()
coco_dset.add_image(image_fpath)
elif isinstance(config['dataset'], list):
# Multiple image case
gpaths = config['dataset']
gpaths = [ub.expandpath(g) for g in gpaths]
coco_dset = ndsampler.CocoDataset()
for gpath in gpaths:
coco_dset.add_image(gpath)
else:
raise TypeError(config['dataset'])
draw = config.get('draw')
workdir = ub.expandpath(config.get('workdir'))
det_outdir = ub.ensuredir((out_dpath, 'pred'))
pred_config = ub.dict_subset(config, DetectPredictConfig.default)
print('Create sampler')
sampler = ndsampler.CocoSampler(coco_dset, workdir=workdir,
backend=sampler_backend)
print('prepare frames')
sampler.frames.prepare(workers=config['workers'])
print('Create predictor')
predictor = DetectPredictor(pred_config)
print('Ensure model')
predictor._ensure_model()
pred_dataset = coco_dset.dataset.copy()
pred_dataset['annotations'] = []
pred_dset = ndsampler.CocoDataset(pred_dataset)
# self = predictor
predictor.config['verbose'] = 1
pred_gen = predictor.predict_sampler(sampler)
buffered_gen = AsyncBufferedGenerator(pred_gen, size=coco_dset.n_images)
gid_to_pred = {}
prog = ub.ProgIter(buffered_gen, total=coco_dset.n_images,
desc='buffered detect')
for img_idx, (gid, dets) in enumerate(prog):
gid_to_pred[gid] = dets
for ann in dets.to_coco():
ann['image_id'] = gid
try:
catname = ann['category_name']
ann['category_id'] = pred_dset._resolve_to_cid(catname)
except KeyError:
if 'category_id' not in ann:
cid = pred_dset.add_category(catname)
ann['category_id'] = cid
pred_dset.add_annotation(**ann)
single_img_coco = pred_dset.subset([gid])
single_pred_dpath = ub.ensuredir((det_outdir, 'single_image'))
single_pred_fpath = join(single_pred_dpath, 'detections_gid_{:08d}.mscoco.json'.format(gid))
single_img_coco.dump(single_pred_fpath, newlines=True)
if draw is True or (draw and img_idx < draw):
draw_outdir = ub.ensuredir((out_dpath, 'draw'))
img_fpath = coco_dset.load_image_fpath(gid)
gname = basename(img_fpath)
viz_fname = ub.augpath(gname, prefix='detect_', ext='.jpg')
viz_fpath = join(draw_outdir, viz_fname)
image = kwimage.imread(img_fpath)
flags = dets.scores > .2
flags[kwarray.argmaxima(dets.scores, num=10)] = True
top_dets = dets.compress(flags)
toshow = top_dets.draw_on(image, alpha=None)
# kwplot.imshow(toshow)
kwimage.imwrite(viz_fpath, toshow, space='rgb')
pred_fpath = join(det_outdir, 'detections.mscoco.json')
print('Dump detections to pred_fpath = {!r}'.format(pred_fpath))
pred_dset.dump(pred_fpath, newlines=True)
def _coerce_datasets(config):
import netharn as nh
import ndsampler
import numpy as np
from torchvision import transforms
coco_datasets = nh.api.Datasets.coerce(config)
print('coco_datasets = {}'.format(ub.repr2(coco_datasets, nl=1)))
for tag, dset in coco_datasets.items():
dset._build_hashid(hash_pixels=False)
workdir = ub.ensuredir(ub.expandpath(config['workdir']))
samplers = {
tag: ndsampler.CocoSampler(dset, workdir=workdir, backend=config['sampler_backend'])
for tag, dset in coco_datasets.items()
}
for tag, sampler in ub.ProgIter(list(samplers.items()), desc='prepare frames'):
sampler.frames.prepare(workers=config['workers'])
# TODO: basic ndsampler torch dataset, likely has to support the transforms
# API, bleh.
transform = transforms.Compose([
transforms.Resize(config['input_dims']),
transforms.CenterCrop(config['input_dims']),
transforms.ToTensor(),
transforms.Lambda(lambda x: x.mul(255))
])
torch_datasets = {
key: SamplerDataset(
sapmler, transform=transform,
# input_dims=config['input_dims'],
# augmenter=config['augmenter'] if key == 'train' else None,
)
for key, sapmler in samplers.items()
}
# self = torch_dset = torch_datasets['train']
if config['normalize_inputs']:
# Get stats on the dataset (todo: turn off augmentation for this)
import kwarray
_dset = torch_datasets['train']
stats_idxs = kwarray.shuffle(np.arange(len(_dset)), rng=0)[0:min(1000, len(_dset))]
stats_subset = torch.utils.data.Subset(_dset, stats_idxs)
cacher = ub.Cacher('dset_mean', cfgstr=_dset.input_id + 'v3')
input_stats = cacher.tryload()
from netharn.data.channel_spec import ChannelSpec
channels = ChannelSpec.coerce(config['channels'])
if input_stats is None:
# Use parallel workers to load data faster
from netharn.data.data_containers import container_collate
from functools import partial
collate_fn = partial(container_collate, num_devices=1)
loader = torch.utils.data.DataLoader(
stats_subset,
collate_fn=collate_fn,
num_workers=config['workers'],
shuffle=True,
batch_size=config['batch_size'])
# Track moving average of each fused channel stream
channel_stats = {key: nh.util.RunningStats()
for key in channels.keys()}
assert len(channel_stats) == 1, (
'only support one fused stream for now')
for batch in ub.ProgIter(loader, desc='estimate mean/std'):
if isinstance(batch, (tuple, list)):
inputs = {'rgb': batch[0]} # make assumption
else:
inputs = batch['inputs']
for key, val in inputs.items():
try:
for part in val.numpy():
channel_stats[key].update(part)
except ValueError: # final batch broadcast error
pass
perchan_input_stats = {}
for key, running in channel_stats.items():
running = ub.peek(channel_stats.values())
perchan_stats = running.simple(axis=(1, 2))
perchan_input_stats[key] = {
'std': perchan_stats['mean'].round(3),
'mean': perchan_stats['std'].round(3),
}
input_stats = ub.peek(perchan_input_stats.values())
cacher.save(input_stats)
else:
input_stats = {}
torch_loaders = {
tag: dset.make_loader(
batch_size=config['batch_size'],
num_batches=config['num_batches'],
num_workers=config['workers'],
shuffle=(tag == 'train'),
balance=(config['balance'] if tag == 'train' else None),
pin_memory=True)
for tag, dset in torch_datasets.items()
}
dataset_info = {
'torch_datasets': torch_datasets,
'torch_loaders': torch_loaders,
'input_stats': input_stats
}
return dataset_info
def setup_harn(cmdline=True, **kw):
"""
Ignore:
>>> from object_detection import * # NOQA
>>> cmdline = False
>>> kw = {
>>> 'train_dataset': '~/data/VOC/voc-trainval.mscoco.json',
>>> 'vali_dataset': '~/data/VOC/voc-test-2007.mscoco.json',
>>> }
>>> harn = setup_harn(**kw)
"""
import ndsampler
from ndsampler import coerce_data
# Seed other global rngs just in case something uses them under the hood
kwarray.seed_global(1129989262, offset=1797315558)
config = DetectFitConfig(default=kw, cmdline=cmdline)
nh.configure_hacks(config) # fix opencv bugs
ub.ensuredir(config['workdir'])
# Load ndsampler.CocoDataset objects from info in the config
subsets = coerce_data.coerce_datasets(config)
samplers = {}
for tag, subset in subsets.items():
print('subset = {!r}'.format(subset))
sampler = ndsampler.CocoSampler(subset, workdir=config['workdir'])
samplers[tag] = sampler
torch_datasets = {
tag: DetectDataset(
sampler,
input_dims=config['input_dims'],
augment=config['augment'] if (tag == 'train') else False,
)
for tag, sampler in samplers.items()
}
print('make loaders')
loaders_ = {
tag:
torch.utils.data.DataLoader(dset,
batch_size=config['batch_size'],
num_workers=config['workers'],
shuffle=(tag == 'train'),
collate_fn=nh.data.collate.padded_collate,
pin_memory=True)
for tag, dset in torch_datasets.items()
}
# for x in ub.ProgIter(loaders_['train']):
# pass
if config['normalize_inputs']:
# Get stats on the dataset (todo: turn off augmentation for this)
_dset = torch_datasets['train']
stats_idxs = kwarray.shuffle(np.arange(len(_dset)),
rng=0)[0:min(1000, len(_dset))]
stats_subset = torch.utils.data.Subset(_dset, stats_idxs)
cacher = ub.Cacher('dset_mean', cfgstr=_dset.input_id + 'v2')
input_stats = cacher.tryload()
if input_stats is None:
# Use parallel workers to load data faster
loader = torch.utils.data.DataLoader(
stats_subset,
collate_fn=nh.data.collate.padded_collate,
num_workers=config['workers'],
shuffle=True,
batch_size=config['batch_size'])
# Track moving average
running = nh.util.RunningStats()
for batch in ub.ProgIter(loader, desc='estimate mean/std'):
try:
running.update(batch['im'].numpy())
except ValueError: # final batch broadcast error
pass
input_stats = {
'std': running.simple(axis=None)['mean'].round(3),
'mean': running.simple(axis=None)['std'].round(3),
}
cacher.save(input_stats)
else:
input_stats = None
print('input_stats = {!r}'.format(input_stats))
initializer_ = nh.Initializer.coerce(config, leftover='kaiming_normal')
print('initializer_ = {!r}'.format(initializer_))
arch = config['arch']
if arch == 'yolo2':
if False:
dset = samplers['train'].dset
print('dset = {!r}'.format(dset))
# anchors = yolo2.find_anchors(dset)
anchors = np.array([(1.3221, 1.73145), (3.19275, 4.00944),
(5.05587, 8.09892), (9.47112, 4.84053),
(11.2364, 10.0071)])
classes = samplers['train'].classes
model_ = (yolo2.Yolo2, {
'classes': classes,
'anchors': anchors,
'conf_thresh': 0.001,
'nms_thresh': 0.5 if not ub.argflag('--eav') else 0.4
})
model = model_[0](**model_[1])
model._initkw = model_[1]
criterion_ = (
yolo2.YoloLoss,
{
'coder': model.coder,
'seen': 0,
'coord_scale': 1.0,
'noobject_scale': 1.0,
'object_scale': 5.0,
'class_scale': 1.0,
'thresh': 0.6, # iou_thresh
# 'seen_thresh': 12800,
})
else:
raise KeyError(arch)
scheduler_ = nh.Scheduler.coerce(config)
print('scheduler_ = {!r}'.format(scheduler_))
optimizer_ = nh.Optimizer.coerce(config)
print('optimizer_ = {!r}'.format(optimizer_))
dynamics_ = nh.Dynamics.coerce(config)
print('dynamics_ = {!r}'.format(dynamics_))
xpu = nh.XPU.coerce(config['xpu'])
print('xpu = {!r}'.format(xpu))
import sys
hyper = nh.HyperParams(
**{
'nice':
config['nice'],
'workdir':
config['workdir'],
'datasets':
torch_datasets,
'loaders':
loaders_,
'xpu':
xpu,
'model':
model,
'criterion':
criterion_,
'initializer':
initializer_,
'optimizer':
optimizer_,
'dynamics':
dynamics_,
# 'optimizer': (torch.optim.SGD, {
# 'lr': lr_step_points[0],
# 'momentum': 0.9,
# 'dampening': 0,
# # multiplying by batch size was one of those unpublished details
# 'weight_decay': decay * simulated_bsize,
# }),
'scheduler':
scheduler_,
'monitor': (
nh.Monitor,
{
'minimize': ['loss'],
# 'maximize': ['mAP'],
'patience': config['patience'],
'max_epoch': config['max_epoch'],
'smoothing': .6,
}),
'other': {
# Other params are not used internally, so you are free to set any
# extra params specific to your algorithm, and still have them
# logged in the hyperparam structure. For YOLO this is `ovthresh`.
'batch_size': config['batch_size'],
'nice': config['nice'],
'ovthresh': config['ovthresh'], # used in mAP computation
},
'extra': {
'config': ub.repr2(config.asdict()),
'argv': sys.argv,
}
})
print('hyper = {!r}'.format(hyper))
print('make harn')
harn = DetectHarn(hyper=hyper)
harn.preferences.update({
'num_keep': 2,
'keep_freq': 30,
'export_modules': ['netharn'], # TODO
'prog_backend': 'progiter', # alternative: 'tqdm'
'keyboard_debug': True,
})
harn.intervals.update({
'log_iter_train': 50,
})
harn.fit_config = config
print('harn = {!r}'.format(harn))
print('samplers = {!r}'.format(samplers))
return harn
def setup_harness(**kwargs):
"""
CommandLine:
python ~/code/netharn/netharn/examples/ggr_matching.py setup_harness
Example:
>>> harn = setup_harness(dbname='PZ_MTEST')
>>> harn.initialize()
"""
nice = kwargs.get('nice', 'untitled')
batch_size = int(kwargs.get('batch_size', 6))
bstep = int(kwargs.get('bstep', 1))
workers = int(kwargs.get('workers', 0))
decay = float(kwargs.get('decay', 0.0005))
lr = float(kwargs.get('lr', 0.001))
dim = int(kwargs.get('dim', 416))
xpu = kwargs.get('xpu', 'argv')
workdir = kwargs.get('workdir', None)
dbname = kwargs.get('dbname', 'ggr2')
if workdir is None:
workdir = ub.truepath(os.path.join('~/work/siam-ibeis2', dbname))
ub.ensuredir(workdir)
if dbname == 'ggr2':
print('Creating torch CocoDataset')
train_dset = ndsampler.CocoDataset(
data=
'/media/joncrall/raid/data/ggr2-coco/annotations/instances_train2018.json',
img_root='/media/joncrall/raid/data/ggr2-coco/images/train2018',
)
train_dset.hashid = 'ggr2-coco-train2018'
vali_dset = ndsampler.CocoDataset(
data=
'/media/joncrall/raid/data/ggr2-coco/annotations/instances_val2018.json',
img_root='/media/joncrall/raid/data/ggr2-coco/images/val2018',
)
vali_dset.hashid = 'ggr2-coco-val2018'
print('Creating samplers')
train_sampler = ndsampler.CocoSampler(train_dset, workdir=workdir)
vali_sampler = ndsampler.CocoSampler(vali_dset, workdir=workdir)
print('Creating torch Datasets')
datasets = {
'train':
MatchingCocoDataset(train_sampler,
train_dset,
workdir,
dim=dim,
augment=True),
'vali':
MatchingCocoDataset(vali_sampler, vali_dset, workdir, dim=dim),
}
else:
from ibeis_utils import randomized_ibeis_dset
datasets = randomized_ibeis_dset(dbname, dim=dim)
for k, v in datasets.items():
print('* len({}) = {}'.format(k, len(v)))
if workers > 0:
import cv2
cv2.setNumThreads(0)
loaders = {
key: torch.utils.data.DataLoader(dset,
batch_size=batch_size,
num_workers=workers,
shuffle=(key == 'train'),
pin_memory=True)
for key, dset in datasets.items()
}
xpu = nh.XPU.cast(xpu)
hyper = nh.HyperParams(
**{
'nice':
nice,
'workdir':
workdir,
'datasets':
datasets,
'loaders':
loaders,
'xpu':
xpu,
'model': (MatchingNetworkLP, {
'p': 2,
'input_shape': (1, 3, dim, dim),
}),
'criterion': (nh.criterions.ContrastiveLoss, {
'margin': 4,
'weight': None,
}),
'optimizer': (torch.optim.SGD, {
'lr': lr,
'weight_decay': decay,
'momentum': 0.9,
'nesterov': True,
}),
'initializer': (nh.initializers.NoOp, {}),
'scheduler': (nh.schedulers.Exponential, {
'gamma': 0.99,
'stepsize': 2,
}),
# 'scheduler': (nh.schedulers.ListedLR, {
# 'points': {
# 1: lr * 1.0,
# 19: lr * 1.1,
# 20: lr * 0.1,
# },
# 'interpolate': True
# }),
'monitor': (nh.Monitor, {
'minimize': ['loss', 'pos_dist', 'brier'],
'maximize': ['accuracy', 'neg_dist', 'mcc'],
'patience': 40,
'max_epoch': 40,
}),
# 'augment': datasets['train'].augmenter,
'dynamics': {
# Controls how many batches to process before taking a step in the
# gradient direction. Effectively simulates a batch_size that is
# `bstep` times bigger.
'batch_step': bstep,
},
'other': {
'n_classes': 2,
},
})
harn = MatchingHarness(hyper=hyper)
harn.config['prog_backend'] = 'progiter'
harn.intervals['log_iter_train'] = 1
harn.intervals['log_iter_test'] = None
harn.intervals['log_iter_vali'] = None
return harn
def setup_harn(cmdline=True, **kw):
"""
Example:
>>> # xdoctest: +REQUIRES(--download)
>>> import sys, ubelt
>>> sys.path.append(ubelt.expandpath('~/code/netharn/examples'))
>>> from sseg_camvid import * # NOQA
>>> kw = {'workers': 0, 'xpu': 'cpu', 'batch_size': 2}
>>> cmdline = False
>>> # Just sets up the harness, does not do any heavy lifting
>>> harn = setup_harn(cmdline=cmdline, **kw)
>>> #
>>> harn.initialize()
>>> #
>>> batch = harn._demo_batch(tag='train')
>>> epoch_metrics = harn._demo_epoch(tag='vali', max_iter=4)
"""
import sys
import ndsampler
config = SegmentationConfig(default=kw)
config.load(cmdline=cmdline)
nh.configure_hacks(config) # fix opencv bugs
assert config['datasets'] == 'special:camvid'
coco_datasets = setup_coco_datasets()
workdir = ub.ensuredir(ub.expandpath(config['workdir']))
samplers = {
# tag: ndsampler.CocoSampler(dset, workdir=workdir, backend='cog')
tag: ndsampler.CocoSampler(dset, workdir=workdir, backend='npy')
for tag, dset in coco_datasets.items()
}
torch_datasets = {
tag: SegmentationDataset(
sampler,
config['input_dims'],
input_overlap=((tag == 'train') and config['input_overlap']),
augment=((tag == 'train') and config['augment']),
)
for tag, sampler in samplers.items()
}
torch_loaders = {
tag: torch_data.DataLoader(dset,
batch_size=config['batch_size'],
num_workers=config['workers'],
shuffle=(tag == 'train'),
drop_last=True, pin_memory=True)
for tag, dset in torch_datasets.items()
}
if config['class_weights']:
mode = config['class_weights']
dset = torch_datasets['train']
class_weights = _precompute_class_weights(dset, mode=mode)
class_weights = torch.FloatTensor(class_weights)
class_weights[dset.classes.index('background')] = 0
else:
class_weights = None
initializer_ = nh.Initializer.coerce(config)
if config['arch'] == 'unet':
# Note: UNet can get through 256x256 images at a rate of ~17Hz with
# batch_size=8. This is pretty slow and can likely be improved by fixing
# some of the weird padding / mirror stuff I have to do in unet to get
# output_dims = input_dims.
from netharn.models.unet import UNet
model_ = (UNet, {
'classes': torch_datasets['train'].classes,
'in_channels': 3,
})
elif config['arch'] == 'segnet':
from netharn.models.segnet import Segnet
model_ = (Segnet, {
'classes': torch_datasets['train'].classes,
'in_channels': 3,
})
elif config['arch'] == 'psp':
from netharn.models.psp import PSPNet_Resnet50_8s
model_ = (PSPNet_Resnet50_8s, {
'classes': torch_datasets['train'].classes,
'in_channels': 3,
})
elif config['arch'] == 'deeplab':
from netharn.models.deeplab import DeepLab_ASPP
model_ = (DeepLab_ASPP, {
'classes': torch_datasets['train'].classes,
'in_channels': 3,
})
else:
raise KeyError(config['arch'])
if config['init'] == 'cls':
initializer_ = model_[0]._initializer_cls()
# Create hyperparameters
hyper = nh.HyperParams(
nice=config['nice'],
workdir=config['workdir'],
xpu=nh.XPU.coerce(config['xpu']),
datasets=torch_datasets,
loaders=torch_loaders,
model=model_,
initializer=initializer_,
scheduler=nh.Scheduler.coerce(config),
optimizer=nh.Optimizer.coerce(config),
dynamics=nh.Dynamics.coerce(config),
criterion=(nh.criterions.FocalLoss, {
'focus': config['focus'],
'weight': class_weights,
# 'reduction': 'none',
}),
monitor=(nh.Monitor, {
'minimize': ['loss'],
'patience': config['patience'],
'max_epoch': config['max_epoch'],
'smoothing': .6,
}),
other={
'batch_size': config['batch_size'],
},
extra={
'argv': sys.argv,
'config': ub.repr2(config.asdict()),
}
)
# Create harness
harn = SegmentationHarn(hyper=hyper)
harn.classes = torch_datasets['train'].classes
harn.preferences.update({
'num_keep': 5,
'keyboard_debug': True,
# 'export_modules': ['netharn'],
})
harn.intervals.update({
'vali': 1,
'test': 10,
})
harn.script_config = config
return harn
def setup_harn(cmdline=True, **kw):
"""
CommandLine:
xdoctest -m netharn.examples.segmentation setup_harn
Example:
>>> # xdoctest: +REQUIRES(--slow)
>>> kw = {'workers': 0, 'xpu': 'cpu', 'batch_size': 2}
>>> cmdline = False
>>> # Just sets up the harness, does not do any heavy lifting
>>> harn = setup_harn(cmdline=cmdline, **kw)
>>> #
>>> harn.initialize()
>>> #
>>> batch = harn._demo_batch(tag='train')
>>> epoch_metrics = harn._demo_epoch(tag='vali', max_iter=2)
"""
import sys
import ndsampler
import kwarray
# kwarray.seed_global(2108744082)
config = SegmentationConfig(default=kw)
config.load(cmdline=cmdline)
nh.configure_hacks(config) # fix opencv bugs
coco_datasets = nh.api.Datasets.coerce(config)
print('coco_datasets = {}'.format(ub.repr2(coco_datasets)))
for tag, dset in coco_datasets.items():
dset._build_hashid(hash_pixels=False)
workdir = ub.ensuredir(ub.expandpath(config['workdir']))
samplers = {
tag: ndsampler.CocoSampler(dset,
workdir=workdir,
backend=config['backend'])
for tag, dset in coco_datasets.items()
}
for tag, sampler in ub.ProgIter(list(samplers.items()),
desc='prepare frames'):
try:
sampler.frames.prepare(workers=config['workers'])
except AttributeError:
pass
torch_datasets = {
tag: SegmentationDataset(
sampler,
config['input_dims'],
input_overlap=((tag == 'train') and config['input_overlap']),
augmenter=((tag == 'train') and config['augmenter']),
)
for tag, sampler in samplers.items()
}
torch_loaders = {
tag: torch_data.DataLoader(dset,
batch_size=config['batch_size'],
num_workers=config['workers'],
shuffle=(tag == 'train'),
drop_last=True,
pin_memory=True)
for tag, dset in torch_datasets.items()
}
if config['class_weights']:
mode = config['class_weights']
dset = torch_datasets['train']
class_weights = _precompute_class_weights(dset,
mode=mode,
workers=config['workers'])
class_weights = torch.FloatTensor(class_weights)
class_weights[dset.classes.index('background')] = 0
else:
class_weights = None
if config['normalize_inputs']:
stats_dset = torch_datasets['train']
stats_idxs = kwarray.shuffle(np.arange(len(stats_dset)),
rng=0)[0:min(1000, len(stats_dset))]
stats_subset = torch.utils.data.Subset(stats_dset, stats_idxs)
cacher = ub.Cacher('dset_mean', cfgstr=stats_dset.input_id + 'v3')
input_stats = cacher.tryload()
if input_stats is None:
loader = torch.utils.data.DataLoader(
stats_subset,
num_workers=config['workers'],
shuffle=True,
batch_size=config['batch_size'])
running = nh.util.RunningStats()
for batch in ub.ProgIter(loader, desc='estimate mean/std'):
try:
running.update(batch['im'].numpy())
except ValueError: # final batch broadcast error
pass
input_stats = {
'std': running.simple(axis=None)['mean'].round(3),
'mean': running.simple(axis=None)['std'].round(3),
}
cacher.save(input_stats)
else:
input_stats = {}
print('input_stats = {!r}'.format(input_stats))
# TODO: infer numbr of channels
model_ = (SegmentationModel, {
'arch': config['arch'],
'input_stats': input_stats,
'classes': torch_datasets['train'].classes.__json__(),
'in_channels': 3,
})
initializer_ = nh.Initializer.coerce(config)
# if config['init'] == 'cls':
# initializer_ = model_[0]._initializer_cls()
# Create hyperparameters
hyper = nh.HyperParams(
nice=config['nice'],
workdir=config['workdir'],
xpu=nh.XPU.coerce(config['xpu']),
datasets=torch_datasets,
loaders=torch_loaders,
model=model_,
initializer=initializer_,
scheduler=nh.Scheduler.coerce(config),
optimizer=nh.Optimizer.coerce(config),
dynamics=nh.Dynamics.coerce(config),
criterion=(
nh.criterions.FocalLoss,
{
'focus': config['focus'],
'weight': class_weights,
# 'reduction': 'none',
}),
monitor=(nh.Monitor, {
'minimize': ['loss'],
'patience': config['patience'],
'max_epoch': config['max_epoch'],
'smoothing': .6,
}),
other={
'batch_size': config['batch_size'],
},
extra={
'argv': sys.argv,
'config': ub.repr2(config.asdict()),
})
# Create harness
harn = SegmentationHarn(hyper=hyper)
harn.classes = torch_datasets['train'].classes
harn.preferences.update({
'num_keep': 2,
'keyboard_debug': True,
# 'export_modules': ['netharn'],
})
harn.intervals.update({
'vali': 1,
'test': 10,
})
harn.script_config = config
return harn
def setup_harn(cmdline=True, **kw):
"""
This creates the "The Classification Harness" (i.e. core ClfHarn object).
This is where we programmatically connect our program arguments with the
netharn HyperParameter standards. We are using :module:`scriptconfig` to
capture these, but you could use click / argparse / etc.
This function has the responsibility of creating our torch datasets,
lazy computing input statistics, specifying our model architecture,
schedule, initialization, optimizer, dynamics, XPU etc. These can usually
be coerced using netharn API helpers and a "standardized" config dict. See
the function code for details.
Args:
cmdline (bool, default=True):
if True, behavior will be modified based on ``sys.argv``.
Note this will activate the scriptconfig ``--help``, ``--dump`` and
``--config`` interactions.
Kwargs:
**kw: the overrides the default config for :class:`ClfConfig`.
Note, command line flags have precedence if cmdline=True.
Returns:
ClfHarn: a fully-defined, but uninitialized custom :class:`FitHarn`
object.
Example:
>>> # xdoctest: +SKIP
>>> kw = {'datasets': 'special:shapes256'}
>>> cmdline = False
>>> harn = setup_harn(cmdline, **kw)
>>> harn.initialize()
"""
import ndsampler
config = ClfConfig(default=kw)
config.load(cmdline=cmdline)
print('config = {}'.format(ub.repr2(config.asdict())))
nh.configure_hacks(config)
coco_datasets = nh.api.Datasets.coerce(config)
print('coco_datasets = {}'.format(ub.repr2(coco_datasets, nl=1)))
for tag, dset in coco_datasets.items():
dset._build_hashid(hash_pixels=False)
workdir = ub.ensuredir(ub.expandpath(config['workdir']))
samplers = {
tag: ndsampler.CocoSampler(dset,
workdir=workdir,
backend=config['sampler_backend'])
for tag, dset in coco_datasets.items()
}
for tag, sampler in ub.ProgIter(list(samplers.items()),
desc='prepare frames'):
sampler.frames.prepare(workers=config['workers'])
torch_datasets = {
'train':
ClfDataset(
samplers['train'],
input_dims=config['input_dims'],
augmenter=config['augmenter'],
),
'vali':
ClfDataset(samplers['vali'],
input_dims=config['input_dims'],
augmenter=False),
}
if config['normalize_inputs']:
# Get stats on the dataset (todo: turn off augmentation for this)
_dset = torch_datasets['train']
stats_idxs = kwarray.shuffle(np.arange(len(_dset)),
rng=0)[0:min(1000, len(_dset))]
stats_subset = torch.utils.data.Subset(_dset, stats_idxs)
cacher = ub.Cacher('dset_mean', cfgstr=_dset.input_id + 'v3')
input_stats = cacher.tryload()
channels = ChannelSpec.coerce(config['channels'])
if input_stats is None:
# Use parallel workers to load data faster
from netharn.data.data_containers import container_collate
from functools import partial
collate_fn = partial(container_collate, num_devices=1)
loader = torch.utils.data.DataLoader(
stats_subset,
collate_fn=collate_fn,
num_workers=config['workers'],
shuffle=True,
batch_size=config['batch_size'])
# Track moving average of each fused channel stream
channel_stats = {
key: nh.util.RunningStats()
for key in channels.keys()
}
assert len(channel_stats) == 1, (
'only support one fused stream for now')
for batch in ub.ProgIter(loader, desc='estimate mean/std'):
for key, val in batch['inputs'].items():
try:
for part in val.numpy():
channel_stats[key].update(part)
except ValueError: # final batch broadcast error
pass
perchan_input_stats = {}
for key, running in channel_stats.items():
running = ub.peek(channel_stats.values())
perchan_stats = running.simple(axis=(1, 2))
perchan_input_stats[key] = {
'std': perchan_stats['mean'].round(3),
'mean': perchan_stats['std'].round(3),
}
input_stats = ub.peek(perchan_input_stats.values())
cacher.save(input_stats)
else:
input_stats = {}
torch_loaders = {
tag: dset.make_loader(
batch_size=config['batch_size'],
num_batches=config['num_batches'],
num_workers=config['workers'],
shuffle=(tag == 'train'),
balance=(config['balance'] if tag == 'train' else None),
pin_memory=True)
for tag, dset in torch_datasets.items()
}
initializer_ = None
classes = torch_datasets['train'].classes
modelkw = {
'arch': config['arch'],
'input_stats': input_stats,
'classes': classes.__json__(),
'channels': channels,
}
model = ClfModel(**modelkw)
model._initkw = modelkw
if initializer_ is None:
initializer_ = nh.Initializer.coerce(config)
hyper = nh.HyperParams(name=config['name'],
workdir=config['workdir'],
xpu=nh.XPU.coerce(config['xpu']),
datasets=torch_datasets,
loaders=torch_loaders,
model=model,
criterion=None,
optimizer=nh.Optimizer.coerce(config),
dynamics=nh.Dynamics.coerce(config),
scheduler=nh.Scheduler.coerce(config),
initializer=initializer_,
monitor=(nh.Monitor, {
'minimize': ['loss'],
'patience': config['patience'],
'max_epoch': config['max_epoch'],
'smoothing': 0.0,
}),
other={
'name': config['name'],
'batch_size': config['batch_size'],
'balance': config['balance'],
},
extra={
'argv': sys.argv,
'config': ub.repr2(config.asdict()),
})
harn = ClfHarn(hyper=hyper)
harn.preferences.update({
'num_keep': 3,
'keep_freq': 10,
'tensorboard_groups': ['loss'],
'eager_dump_tensorboard': True,
})
harn.intervals.update({})
harn.script_config = config
return harn
def setup_harn(cmdline=True, **kwargs):
"""
cmdline, kwargs = False, {}
"""
import sys
import ndsampler
config = ImageClfConfig(default=kwargs)
config.load(cmdline=cmdline)
nh.configure_hacks(config) # fix opencv bugs
cacher = ub.Cacher('tiny-imagenet', cfgstr='v4', verbose=3)
data = cacher.tryload()
if data is None:
data = grab_tiny_imagenet_as_coco()
cacher.save(data)
coco_datasets = data # setup_coco_datasets()
dset = coco_datasets['train']
print('train dset = {!r}'.format(dset))
workdir = ub.ensuredir(ub.expandpath(config['workdir']))
samplers = {
# tag: ndsampler.CocoSampler(dset, workdir=workdir, backend='cog')
tag: ndsampler.CocoSampler(dset, workdir=workdir, backend='npy')
for tag, dset in coco_datasets.items()
}
torch_datasets = {
tag: ImagClfDataset(
sampler, config['input_dims'],
augmenter=((tag == 'train') and config['augmenter']),
)
for tag, sampler in samplers.items()
}
torch_loaders = {
tag: torch_data.DataLoader(dset,
batch_size=config['batch_size'],
num_workers=config['workers'],
shuffle=(tag == 'train'),
pin_memory=True)
for tag, dset in torch_datasets.items()
}
import torchvision
# TODO: netharn should allow for this
model_ = torchvision.models.resnet50(pretrained=False)
# model_ = (, {
# 'classes': torch_datasets['train'].classes,
# 'in_channels': 3,
# })
initializer_ = nh.Initializer.coerce(config)
hyper = nh.HyperParams(
nice=config['nice'],
workdir=config['workdir'],
xpu=nh.XPU.coerce(config['xpu']),
datasets=torch_datasets,
loaders=torch_loaders,
model=model_,
initializer=initializer_,
scheduler=nh.Scheduler.coerce(config),
optimizer=nh.Optimizer.coerce(config),
dynamics=nh.Dynamics.coerce(config),
criterion=(nh.criterions.FocalLoss, {
'focus': 0.0,
}),
monitor=(nh.Monitor, {
'minimize': ['loss'],
'patience': config['patience'],
'max_epoch': config['max_epoch'],
'smoothing': .6,
}),
other={
'batch_size': config['batch_size'],
},
extra={
'argv': sys.argv,
'config': ub.repr2(config.asdict()),
}
)
# Create harness
harn = ImageClfHarn(hyper=hyper)
harn.classes = torch_datasets['train'].classes
harn.preferences.update({
'num_keep': 5,
'keyboard_debug': True,
# 'export_modules': ['netharn'],
})
harn.intervals.update({
'vali': 1,
'test': 10,
})
harn.script_config = config
return harn
def test_variable_backend():
"""
CommandLine:
xdoctest -m $HOME/code/ndsampler/tests/tests_frame_backends.py test_variable_backend
--debug-validate-cog --debug-load-cog
"""
try:
import gdal # NOQA
except ImportError:
import pytest
pytest.skip('cog requires gdal')
import ndsampler
import kwcoco
import ubelt as ub
dpath = ub.ensure_app_cache_dir('ndsampler/tests/test_variable_backend')
ub.delete(dpath)
ub.ensuredir(dpath)
fnames = [
'test_rgb_255.jpg',
'test_gray_255.jpg',
'test_rgb_255.png',
'test_rgba_255.png',
'test_gray_255.png',
'test_rgb_01.tif',
'test_rgb_255.tif',
'test_rgba_01.tif',
'test_rgba_255.tif',
'test_gray_01.tif',
'test_gray_255.tif',
]
import kwarray
import kwimage
fpaths = []
rng = kwarray.ensure_rng(0)
h, w = 1200, 1055
for fname in ub.ProgIter(fnames, desc='create test data'):
if 'rgb_' in fname:
data = rng.rand(h, w, 3)
elif 'rgba_' in fname:
data = rng.rand(h, w, 4)
elif 'gray_' in fname:
data = rng.rand(h, w, 1)
if '01' in fname:
pass
elif '255' in fname:
data = (data * 255).astype(np.uint8)
fpath = join(dpath, fname)
fpaths.append(fpath)
kwimage.imwrite(fpath, data)
for fpath in fpaths:
data = kwimage.imread(fpath)
print(
ub.repr2(
{
'fname': basename(fpath),
'data.shape': data.shape,
'data.dtype': data.dtype,
},
nl=0))
dset = kwcoco.CocoDataset.from_image_paths(fpaths)
sampler = ndsampler.CocoSampler(dset, backend='cog', workdir=dpath)
frames = sampler.frames
# frames.prepare()
if 1:
for gid in frames.image_ids:
print('======== < START IMAGE ID > ===============')
gpath, cache_gpath = frames._gnames(gid)
print('gpath = {!r}'.format(gpath))
print('cache_gpath = {!r}'.format(cache_gpath))
image = frames.load_image(gid)
print('image = {!r}'.format(image))
print('image.shape = {!r}'.format(image.shape))
print('image.dtype = {!r}'.format(image.dtype))
subdata = image[0:8, 0:8]
print('subdata.dtype = {!r}'.format(subdata.dtype))
print('subdata.shape = {!r}'.format(subdata.shape))
# info = ub.cmd('gdalinfo ' + cache_gpath, verbose=0)
# print('GDAL INFO:')
# print(ub.indent(info['out']))
# assert info['ret'] == 0
# dataset = gdal.OpenEx(cache_gpath)
dataset = gdal.Open(cache_gpath, gdal.GA_ReadOnly)
md = dataset.GetMetadata('IMAGE_STRUCTURE')
print('md = {!r}'.format(md))
# Use dict.get method in case the metadata dict does not have a 'COMPRESSION' key
compression = md.get('COMPRESSION', 'RAW')
print('compression = {!r}'.format(compression))
print('======== < END IMAGE ID > ===============')
