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 _to_coco(dmet):
"""
Convert to a coco representation of truth and predictions
"""
import ndsampler
true = ndsampler.CocoDataset()
pred = ndsampler.CocoDataset()
for node in dmet.classes:
# cid = dmet.classes.graph.node[node]['id']
cid = dmet.classes.index(node)
supercategory = list(dmet.classes.graph.pred[node])
if len(supercategory) == 0:
supercategory = None
else:
assert len(supercategory) == 1
supercategory = supercategory[0]
true.add_category(node, id=cid, supercategory=supercategory)
pred.add_category(node, id=cid, supercategory=supercategory)
for imgname, gid in dmet._imgname_to_gid.items():
true.add_image(imgname, id=gid)
pred.add_image(imgname, id=gid)
idx_to_id = {
idx: dmet.classes.index(node)
for idx, node in enumerate(dmet.classes.idx_to_node)
}
for gid, pred_dets in dmet.gid_to_pred_dets.items():
pred_boxes = pred_dets.boxes
if 'scores' in pred_dets.data:
pred_scores = pred_dets.scores
else:
pred_scores = np.ones(len(pred_dets))
pred_cids = list(ub.take(idx_to_id, pred_dets.class_idxs))
pred_xywh = pred_boxes.to_xywh().data.tolist()
for bbox, cid, score in zip(pred_xywh, pred_cids, pred_scores):
pred.add_annotation(gid, cid, bbox=bbox, score=score)
for gid, true_dets in dmet.gid_to_true_dets.items():
true_boxes = true_dets.boxes
if 'weights' in true_dets.data:
true_weights = true_dets.weights
else:
true_weights = np.ones(len(true_boxes))
true_cids = list(ub.take(idx_to_id, true_dets.class_idxs))
true_xywh = true_boxes.to_xywh().data.tolist()
for bbox, cid, weight in zip(true_xywh, true_cids, true_weights):
true.add_annotation(gid, cid, bbox=bbox, weight=weight)
return pred, true
def parse_mscoco():
# Test that our implementation can handle the real mscoco data
root = ub.expandpath('~/data/standard_datasets/mscoco/')
fpath = join(root, 'annotations/instances_val2014.json')
img_root = normpath(ub.ensuredir((root, 'images', 'val2014')))
# fpath = join(root, 'annotations/stuff_val2017.json')
# img_root = normpath(ub.ensuredir((root, 'images', 'val2017')))
import ujson
dataset = ujson.load(open(fpath, 'rb'))
import ndsampler
dset = ndsampler.CocoDataset(dataset)
dset.img_root = img_root
gid_iter = iter(dset.imgs.keys())
gid = ub.peek(gid_iter)
for gid in ub.ProgIter(gid_iter):
img = dset.imgs[gid]
ub.grabdata(img['coco_url'], dpath=img_root, verbose=0)
anns = [dset.anns[aid] for aid in dset.gid_to_aids[gid]]
dset.show_image(gid=gid)
ann = anns[0]
segmentation = ann['segmentation']
from PIL import Image
gpath = join(dset.img_root, img['file_name'])
with Image.open(gpath) as pil_img:
np_img = np.array(pil_img)
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 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 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 eval_detections_cli(**kw):
"""
CommandLine:
xdoctest -m ~/code/netharn/netharn/metrics/detect_metrics.py eval_detections_cli
"""
import scriptconfig as scfg
import ndsampler
class EvalDetectionCLI(scfg.Config):
default = {
'true': scfg.Path(None, help='true coco dataset'),
'pred': scfg.Path(None, help='predicted coco dataset'),
'out_dpath': scfg.Path('./out', help='output directory')
}
pass
config = EvalDetectionCLI()
cmdline = kw.pop('cmdline', True)
config.load(kw, cmdline=cmdline)
true_coco = ndsampler.CocoDataset(config['true'])
pred_coco = ndsampler.CocoDataset(config['pred'])
from netharn.metrics.detect_metrics import DetectionMetrics
dmet = DetectionMetrics.from_coco(true_coco, pred_coco)
voc_info = dmet.score_voc()
cls_info = voc_info['perclass'][0]
tp = cls_info['tp']
fp = cls_info['fp']
fn = cls_info['fn']
tpr = cls_info['tpr']
ppv = cls_info['ppv']
fp = cls_info['fp']
# Compute the MCC as TN->inf
thresh = cls_info['thresholds']
# https://erotemic.wordpress.com/2019/10/23/closed-form-of-the-mcc-when-tn-inf/
mcc_lim = tp / (np.sqrt(fn + tp) * np.sqrt(fp + tp))
f1 = 2 * (ppv * tpr) / (ppv + tpr)
draw = False
if draw:
mcc_idx = mcc_lim.argmax()
f1_idx = f1.argmax()
import kwplot
plt = kwplot.autoplt()
kwplot.multi_plot(
xdata=thresh,
ydata=mcc_lim,
xlabel='threshold',
ylabel='mcc*',
fnum=1,
pnum=(1, 4, 1),
title='MCC*',
color=['blue'],
)
plt.plot(thresh[mcc_idx], mcc_lim[mcc_idx], 'r*', markersize=20)
plt.plot(thresh[f1_idx], mcc_lim[f1_idx], 'k*', markersize=20)
kwplot.multi_plot(
xdata=fp,
ydata=tpr,
xlabel='fp (fa)',
ylabel='tpr (pd)',
fnum=1,
pnum=(1, 4, 2),
title='ROC',
color=['blue'],
)
plt.plot(fp[mcc_idx], tpr[mcc_idx], 'r*', markersize=20)
plt.plot(fp[f1_idx], tpr[f1_idx], 'k*', markersize=20)
kwplot.multi_plot(
xdata=tpr,
ydata=ppv,
xlabel='tpr (recall)',
ylabel='ppv (precision)',
fnum=1,
pnum=(1, 4, 3),
title='PR',
color=['blue'],
)
plt.plot(tpr[mcc_idx], ppv[mcc_idx], 'r*', markersize=20)
plt.plot(tpr[f1_idx], ppv[f1_idx], 'k*', markersize=20)
kwplot.multi_plot(
xdata=thresh,
ydata=f1,
xlabel='threshold',
ylabel='f1',
fnum=1,
pnum=(1, 4, 4),
title='F1',
color=['blue'],
)
plt.plot(thresh[mcc_idx], f1[mcc_idx], 'r*', markersize=20)
plt.plot(thresh[f1_idx], f1[f1_idx], 'k*', markersize=20)
def convert_camvid_raw_to_coco(camvid_raw_info):
"""
Converts the raw camvid format to an MSCOCO based format, ( which lets use
use ndsampler's COCO backend).
Example:
>>> # xdoctest: +REQUIRES(--download)
>>> camvid_raw_info = grab_raw_camvid()
>>> # test with a reduced set of data
>>> del camvid_raw_info['img_paths'][2:]
>>> del camvid_raw_info['mask_paths'][2:]
>>> dset = convert_camvid_raw_to_coco(camvid_raw_info)
>>> # xdoctest: +REQUIRES(--show)
>>> import kwplot
>>> plt = kwplot.autoplt()
>>> kwplot.figure(fnum=1, pnum=(1, 2, 1))
>>> dset.show_image(gid=1)
>>> kwplot.figure(fnum=1, pnum=(1, 2, 2))
>>> dset.show_image(gid=2)
"""
import re
import kwimage
import ndsampler
print('Converting CamVid to MS-COCO format')
dset_root, img_paths, label_path, mask_paths = ub.take(
camvid_raw_info,
'dset_root, img_paths, label_path, mask_paths'.split(', '))
img_infos = {
'img_fname': img_paths,
'mask_fname': mask_paths,
}
keys = list(img_infos.keys())
next_vals = list(zip(*img_infos.values()))
image_items = [{k: v for k, v in zip(keys, vals)} for vals in next_vals]
dataset = {
'img_root': dset_root,
'images': [],
'categories': [],
'annotations': [],
}
lines = ub.readfrom(label_path).split('\n')
lines = [line for line in lines if line]
for line in lines:
color_text, name = re.split('\t+', line)
r, g, b = map(int, color_text.split(' '))
color = (r, g, b)
# Parse the special camvid format
cid = (r << 16) + (g << 8) + (b << 0)
cat = {
'id': cid,
'name': name,
'color': color,
}
dataset['categories'].append(cat)
for gid, img_item in enumerate(image_items, start=1):
img = {
'id': gid,
'file_name': img_item['img_fname'],
# nonstandard image field
'segmentation': img_item['mask_fname'],
}
dataset['images'].append(img)
dset = ndsampler.CocoDataset(dataset)
dset.rename_categories({'Void': 'background'})
assert dset.name_to_cat['background']['id'] == 0
dset.name_to_cat['background'].setdefault('alias', []).append('Void')
if False:
_define_camvid_class_hierarcy(dset)
if 1:
# TODO: Binarize CCs (and efficiently encode if possible)
import numpy as np
bad_info = []
once = False
# Add images
dset.remove_all_annotations()
for gid, img in ub.ProgIter(dset.imgs.items(),
desc='parse label masks'):
mask_fpath = join(dset_root, img['segmentation'])
rgb_mask = kwimage.imread(mask_fpath, space='rgb')
r, g, b = rgb_mask.T.astype(np.int64)
cid_mask = np.ascontiguousarray(rgb_to_cid(r, g, b).T)
cids = set(np.unique(cid_mask)) - {0}
for cid in cids:
if cid not in dset.cats:
if gid == 618:
# Handle a known issue with image 618
c_mask = (cid == cid_mask).astype(np.uint8)
total_bad = c_mask.sum()
if total_bad < 32:
if not once:
print(
'gid 618 has a few known bad pixels, ignoring them'
)
once = True
continue
else:
raise Exception('more bad pixels than expected')
else:
raise Exception(
'UNKNOWN cid = {!r} in gid={!r}'.format(cid, gid))
# bad_rgb = cid_to_rgb(cid)
# print('bad_rgb = {!r}'.format(bad_rgb))
# print('WARNING UNKNOWN cid = {!r} in gid={!r}'.format(cid, gid))
# bad_info.append({
# 'gid': gid,
# 'cid': cid,
# })
else:
ann = {
'category_id': cid,
'image_id': gid
# 'segmentation': mask.to_coco()
}
assert cid in dset.cats
c_mask = (cid == cid_mask).astype(np.uint8)
mask = kwimage.Mask(c_mask, 'c_mask')
box = kwimage.Boxes([mask.get_xywh()], 'xywh')
# box = mask.to_boxes()
ann['bbox'] = ub.peek(box.to_coco())
ann['segmentation'] = mask.to_coco()
dset.add_annotation(**ann)
if 0:
bad_cids = [i['cid'] for i in bad_info]
print(sorted([c['color'] for c in dataset['categories']]))
print(sorted(set([cid_to_rgb(i['cid']) for i in bad_info])))
gid = 618
img = dset.imgs[gid]
mask_fpath = join(dset_root, img['segmentation'])
rgb_mask = kwimage.imread(mask_fpath, space='rgb')
r, g, b = rgb_mask.T.astype(np.int64)
cid_mask = np.ascontiguousarray(rgb_to_cid(r, g, b).T)
cid_hist = ub.dict_hist(cid_mask.ravel())
bad_cid_hist = {}
for cid in bad_cids:
bad_cid_hist[cid] = cid_hist.pop(cid)
import kwplot
kwplot.autompl()
kwplot.imshow(rgb_mask)
if 0:
import kwplot
plt = kwplot.autoplt()
plt.clf()
dset.show_image(1)
import xdev
gid_list = list(dset.imgs)
for gid in xdev.InteractiveIter(gid_list):
dset.show_image(gid)
xdev.InteractiveIter.draw()
dset._build_index()
dset._build_hashid()
return dset
def grab_coco_camvid():
"""
Example:
>>> # xdoctest: +REQUIRES(--download)
>>> dset = grab_coco_camvid()
>>> print('dset = {!r}'.format(dset))
>>> # xdoctest: +REQUIRES(--show)
>>> import kwplot
>>> plt = kwplot.autoplt()
>>> plt.clf()
>>> dset.show_image(gid=1)
Ignore:
import xdev
gid_list = list(dset.imgs)
for gid in xdev.InteractiveIter(gid_list):
dset.show_image(gid)
xdev.InteractiveIter.draw()
"""
import ndsampler
cache_dpath = ub.ensure_app_cache_dir('netharn', 'camvid')
coco_fpath = join(cache_dpath, 'camvid.mscoco.json')
# Need to manually bump this if you make a change to loading
SCRIPT_VERSION = 'v4'
# Ubelt's stamp-based caches are super cheap and let you take control of
# the data format.
stamp = ub.CacheStamp('camvid_coco',
cfgstr=SCRIPT_VERSION,
dpath=cache_dpath,
product=coco_fpath,
hasher='sha1',
verbose=3)
if stamp.expired():
camvid_raw_info = grab_raw_camvid()
dset = convert_camvid_raw_to_coco(camvid_raw_info)
with ub.Timer('dumping MS-COCO dset to: {}'.format(coco_fpath)):
dset.dump(coco_fpath)
# Mark this process as completed by saving a small file containing the
# hash of the "product" you are stamping.
stamp.renew()
# We can also cache the index build step independently. This uses
# ubelt.Cacher, which is pickle based, and writes the actual object to
# disk. Each type of caching has its own uses and tradeoffs.
cacher = ub.Cacher('prebuilt-coco',
cfgstr=SCRIPT_VERSION,
dpath=cache_dpath,
verbose=3)
dset = cacher.tryload()
if dset is None:
print('Reading coco_fpath = {!r}'.format(coco_fpath))
dset = ndsampler.CocoDataset(coco_fpath, tag='camvid')
# Directly save the file to disk.
dset._build_index()
dset._build_hashid()
cacher.save(dset)
camvid_dset = dset
print('Loaded camvid_dset = {!r}'.format(camvid_dset))
return camvid_dset
def grab_tiny_imagenet_as_coco():
import ubelt as ub
url = 'http://cs231n.stanford.edu/tiny-imagenet-200.zip'
dpath = ub.ensure_app_cache_dir('netharn', 'tiny-imagenet-200')
dset_root = join(dpath, 'tiny-imagenet-200')
zip_fpath = ub.grabdata(url, dpath=dpath)
if not exists(dset_root):
import zipfile
zip_ref = zipfile.ZipFile(zip_fpath, 'r')
zip_ref.extractall(dpath)
zip_ref.close()
tiny_imgnet_info = {
'train': join(dset_root, 'train'),
'test': join(dset_root, 'test'),
'vali': join(dset_root, 'val'),
'wnids': join(dset_root, 'wnids.txt'),
'words': join(dset_root, 'words.txt'),
}
import glob
train_annots = list(glob.glob(join(tiny_imgnet_info['train'], '*/*boxes.txt')))
vali_annots = list(glob.glob(join(tiny_imgnet_info['vali'], 'val_annotations.txt')))
import ndsampler
img_root = {
'train': join(tiny_imgnet_info['train']),
'vali': join(tiny_imgnet_info['vali'], 'images'),
'test': join(tiny_imgnet_info['test'], 'images'),
}
gpaths = {
'train': list(glob.glob(join(tiny_imgnet_info['train'], '*/images/*.JPEG'))),
'vali': list(glob.glob(join(tiny_imgnet_info['vali'], 'images/*.JPEG'))),
'test': list(glob.glob(join(tiny_imgnet_info['test'], 'images/*.JPEG')))
}
annots_text = {
'train': ''.join(ub.readfrom(fpath) for fpath in train_annots),
'vali': ''.join(ub.readfrom(fpath) for fpath in vali_annots),
}
coco_datasets = {
'train': ndsampler.CocoDataset(tag='tiny-imagenet-train'),
'vali': ndsampler.CocoDataset(tag='tiny-imagenet-vali'),
}
for catname in (_ for _ in ub.readfrom(tiny_imgnet_info['wnids']).split('\n') if _):
for dset in coco_datasets.values():
dset.add_category(name=catname)
for tag in ['train', 'vali']:
gpaths_ = gpaths[tag]
annots_ = annots_text[tag]
dset = coco_datasets[tag]
dset.img_root = img_root[tag]
for gpath in gpaths_:
dset.add_image(file_name=gpath)
for line in (_ for _ in annots_.split('\n') if _):
parts = line.split('\t')
if tag == 'train':
gname = parts[0]
catname = gname.split('_')[0]
x, y, w, h = list(map(float, parts[1:]))
gpath = join(img_root[tag], catname, 'images', gname)
else:
gname, catname = parts[0:2]
x, y, w, h = list(map(float, parts[2:]))
gpath = join(img_root[tag], gname)
bbox = (x, y, w + 1, h + 1)
cat = dset.name_to_cat[catname]
img = dset.index.file_name_to_img[gpath]
dset.add_annotation(image_id=img['id'], bbox=bbox,
category_id=cat['id'])
dset._ensure_imgsize()
dset._build_hashid()
print('dset.hashid = {!r}'.format(dset.hashid))
return coco_datasets
