def init_params(self):
startup_prog = fluid.Program()
infer_prog = fluid.Program()
with fluid.program_guard(infer_prog, startup_prog):
with fluid.unique_name.guard():
inputs_def = self.cfg['TestReader']['inputs_def']
inputs_def['iterable'] = True
feed_vars, loader = self.model.build_inputs(**inputs_def)
test_fetches = self.model.test(feed_vars)
infer_prog = infer_prog.clone(True)
self.exe.run(startup_prog)
if self.cfg.weights:
checkpoint.load_params(self.exe, infer_prog, self.cfg.weights)
extra_keys = ['im_info', 'im_id', 'im_shape']
self.keys, self.values, _ = parse_fetches(
test_fetches, infer_prog, extra_keys)
dataset = self.cfg.TestReader['dataset']
anno_file = dataset.get_anno()
with_background = dataset.with_background
use_default_label = dataset.use_default_label
self.clsid2catid, self.catid2name = get_category_info(anno_file, with_background,
use_default_label)
is_bbox_normalized = False
if hasattr(self.model, 'is_bbox_normalized') and \
callable(self.model.is_bbox_normalized):
is_bbox_normalized = self.model.is_bbox_normalized()
self.is_bbox_normalized = is_bbox_normalized
self.infer_prog = infer_prog
def parse_reader(reader_cfg, metric, arch):
preprocess_list = []
image_shape = reader_cfg['inputs_def'].get('image_shape', [3, None, None])
has_shape_def = not None in image_shape
scale_set = {'RCNN', 'RetinaNet'}
dataset = reader_cfg['dataset']
anno_file = dataset.get_anno()
with_background = dataset.with_background
use_default_label = dataset.use_default_label
if metric == 'COCO':
from ppdet.utils.coco_eval import get_category_info
elif metric == "VOC":
from ppdet.utils.voc_eval import get_category_info
elif metric == "WIDERFACE":
from ppdet.utils.widerface_eval_utils import get_category_info
else:
raise ValueError(
"metric only supports COCO, VOC, WIDERFACE, but received {}".
format(metric))
clsid2catid, catid2name = get_category_info(anno_file, with_background,
use_default_label)
label_list = [str(cat) for cat in catid2name.values()]
sample_transforms = reader_cfg['sample_transforms']
for st in sample_transforms[1:]:
method = st.__class__.__name__
p = {'type': method.replace('Image', '')}
params = st.__dict__
params.pop('_id')
if p['type'] == 'Resize' and has_shape_def:
params['target_size'] = min(
image_shape[1:]) if arch in scale_set else image_shape[1]
params['max_size'] = max(
image_shape[1:]) if arch in scale_set else 0
params['image_shape'] = image_shape[1:]
if 'target_dim' in params:
params.pop('target_dim')
p.update(params)
preprocess_list.append(p)
batch_transforms = reader_cfg.get('batch_transforms', None)
if batch_transforms:
methods = [bt.__class__.__name__ for bt in batch_transforms]
for bt in batch_transforms:
method = bt.__class__.__name__
if method == 'PadBatch':
preprocess_list.append({'type': 'PadStride'})
params = bt.__dict__
preprocess_list[-1].update({'stride': params['pad_to_stride']})
break
return with_background, preprocess_list, label_list
def run(FLAGS, cfg, place):
# Model
main_arch = cfg.architecture
model = create(cfg.architecture)
# Init Model
load_weight(model, cfg.weights)
# Data Reader
dataset = cfg.EvalDataset
eval_loader, _ = create('EvalReader')(dataset, cfg['worker_num'], place)
# Run Eval
outs_res = []
start_time = time.time()
sample_num = 0
for iter_id, data in enumerate(eval_loader):
# forward
model.eval()
outs = model(data, cfg['EvalReader']['inputs_def']['fields'], 'infer')
outs_res.append(outs)
# log
sample_num += len(data)
if iter_id % 100 == 0:
logger.info("Eval iter: {}".format(iter_id))
cost_time = time.time() - start_time
logger.info('Total sample number: {}, averge FPS: {}'.format(
sample_num, sample_num / cost_time))
eval_type = ['bbox']
if getattr(cfg, 'MaskHead', None):
eval_type.append('mask')
# Metric
# TODO: support other metric
from ppdet.utils.coco_eval import get_category_info
anno_file = dataset.get_anno()
with_background = cfg.with_background
use_default_label = dataset.use_default_label
clsid2catid, catid2name = get_category_info(anno_file, with_background,
use_default_label)
infer_res = get_infer_results(outs_res, eval_type, clsid2catid)
eval_results(infer_res, cfg.metric, anno_file)
def parse_reader(reader_cfg, dataset_cfg, metric, arch, image_shape):
preprocess_list = []
anno_file = dataset_cfg.get_anno()
with_background = reader_cfg['with_background']
use_default_label = dataset_cfg.use_default_label
if metric == 'COCO':
from ppdet.utils.coco_eval import get_category_info
elif metric == 'VOC':
from ppdet.utils.voc_eval import get_category_info
else:
raise ValueError(
"metric only supports COCO, but received {}".format(metric))
clsid2catid, catid2name = get_category_info(anno_file, with_background,
use_default_label)
label_list = [str(cat) for cat in catid2name.values()]
sample_transforms = reader_cfg['sample_transforms']
for st in sample_transforms[1:]:
for key, value in st.items():
p = {'type': key}
if key == 'ResizeOp':
if value.get('keep_ratio',
False) and image_shape[1] is not None:
max_size = max(image_shape[1:])
image_shape = [3, max_size, max_size]
value['target_size'] = image_shape[1:]
p.update(value)
preprocess_list.append(p)
batch_transforms = reader_cfg.get('batch_transforms', None)
if batch_transforms:
methods = [list(bt.keys())[0] for bt in batch_transforms]
for bt in batch_transforms:
for key, value in bt.items():
if key == 'PadBatchOp':
preprocess_list.append({'type': 'PadStride'})
preprocess_list[-1].update(
{'stride': value['pad_to_stride']})
break
return with_background, preprocess_list, label_list, image_shape
def main():
cfg = load_config(FLAGS.config)
merge_config(FLAGS.opt)
check_config(cfg)
# check if set use_gpu=True in paddlepaddle cpu version
check_gpu(cfg.use_gpu)
# check if paddlepaddle version is satisfied
check_version()
main_arch = cfg.architecture
dataset = cfg.TestReader['dataset']
test_images = get_test_images(FLAGS.infer_dir, FLAGS.infer_img)
dataset.set_images(test_images)
place = fluid.CUDAPlace(0) if cfg.use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
model = create(main_arch)
startup_prog = fluid.Program()
infer_prog = fluid.Program()
with fluid.program_guard(infer_prog, startup_prog):
with fluid.unique_name.guard():
inputs_def = cfg['TestReader']['inputs_def']
inputs_def['iterable'] = True
feed_vars, loader = model.build_inputs(**inputs_def)
test_fetches = model.test(feed_vars)
infer_prog = infer_prog.clone(True)
pruned_params = FLAGS.pruned_params
assert (
FLAGS.pruned_params is not None
), "FLAGS.pruned_params is empty!!! Please set it by '--pruned_params' option."
pruned_params = FLAGS.pruned_params.strip().split(",")
logger.info("pruned params: {}".format(pruned_params))
pruned_ratios = [float(n) for n in FLAGS.pruned_ratios.strip().split(",")]
logger.info("pruned ratios: {}".format(pruned_ratios))
assert (len(pruned_params) == len(pruned_ratios)
), "The length of pruned params and pruned ratios should be equal."
assert (pruned_ratios > [0] * len(pruned_ratios)
and pruned_ratios < [1] * len(pruned_ratios)
), "The elements of pruned ratios should be in range (0, 1)."
base_flops = flops(infer_prog)
pruner = Pruner()
infer_prog, _, _ = pruner.prune(infer_prog,
fluid.global_scope(),
params=pruned_params,
ratios=pruned_ratios,
place=place,
only_graph=True)
pruned_flops = flops(infer_prog)
logger.info("pruned FLOPS: {}".format(
float(base_flops - pruned_flops) / base_flops))
reader = create_reader(cfg.TestReader, devices_num=1)
loader.set_sample_list_generator(reader, place)
exe.run(startup_prog)
if cfg.weights:
checkpoint.load_checkpoint(exe, infer_prog, cfg.weights)
# parse infer fetches
assert cfg.metric in ['COCO', 'VOC', 'OID', 'WIDERFACE'], \
"unknown metric type {}".format(cfg.metric)
extra_keys = []
if cfg['metric'] in ['COCO', 'OID']:
extra_keys = ['im_info', 'im_id', 'im_shape']
if cfg['metric'] == 'VOC' or cfg['metric'] == 'WIDERFACE':
extra_keys = ['im_id', 'im_shape']
keys, values, _ = parse_fetches(test_fetches, infer_prog, extra_keys)
# parse dataset category
if cfg.metric == 'COCO':
from ppdet.utils.coco_eval import bbox2out, mask2out, get_category_info
if cfg.metric == 'OID':
from ppdet.utils.oid_eval import bbox2out, get_category_info
if cfg.metric == "VOC":
from ppdet.utils.voc_eval import bbox2out, get_category_info
if cfg.metric == "WIDERFACE":
from ppdet.utils.widerface_eval_utils import bbox2out, get_category_info
anno_file = dataset.get_anno()
with_background = dataset.with_background
use_default_label = dataset.use_default_label
clsid2catid, catid2name = get_category_info(anno_file, with_background,
use_default_label)
# whether output bbox is normalized in model output layer
is_bbox_normalized = False
if hasattr(model, 'is_bbox_normalized') and \
callable(model.is_bbox_normalized):
is_bbox_normalized = model.is_bbox_normalized()
imid2path = dataset.get_imid2path()
for iter_id, data in enumerate(loader()):
outs = exe.run(infer_prog,
feed=data,
fetch_list=values,
return_numpy=False)
res = {
k: (np.array(v), v.recursive_sequence_lengths())
for k, v in zip(keys, outs)
}
logger.info('Infer iter {}'.format(iter_id))
bbox_results = None
mask_results = None
if 'bbox' in res:
bbox_results = bbox2out([res], clsid2catid, is_bbox_normalized)
if 'mask' in res:
mask_results = mask2out([res], clsid2catid,
model.mask_head.resolution)
# visualize result
im_ids = res['im_id'][0]
for im_id in im_ids:
image_path = imid2path[int(im_id)]
image = Image.open(image_path).convert('RGB')
image = visualize_results(image, int(im_id), catid2name,
FLAGS.draw_threshold, bbox_results,
mask_results)
save_name = get_save_image_name(FLAGS.output_dir, image_path)
logger.info("Detection bbox results save in {}".format(save_name))
image.save(save_name, quality=95)
def main():
"""
Main evaluate function
"""
cfg = load_config(FLAGS.config)
merge_config(FLAGS.opt)
check_config(cfg)
# check if set use_gpu=True in paddlepaddle cpu version
check_gpu(cfg.use_gpu)
# check if paddlepaddle version is satisfied
check_version()
main_arch = cfg.architecture
multi_scale_test = getattr(cfg, 'MultiScaleTEST', None)
# define executor
place = fluid.CUDAPlace(0) if cfg.use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
# build program
model = create(main_arch)
startup_prog = fluid.Program()
eval_prog = fluid.Program()
with fluid.program_guard(eval_prog, startup_prog):
with fluid.unique_name.guard():
inputs_def = cfg['EvalReader']['inputs_def']
feed_vars, loader = model.build_inputs(**inputs_def)
if multi_scale_test is None:
fetches = model.eval(feed_vars)
else:
fetches = model.eval(feed_vars, multi_scale_test)
eval_prog = eval_prog.clone(True)
reader = create_reader(cfg.EvalReader, devices_num=1)
loader.set_sample_list_generator(reader, place)
dataset = cfg['EvalReader']['dataset']
# parse dataset category
if cfg.metric == 'COCO':
from ppdet.utils.coco_eval import bbox2out, mask2out, get_category_info
anno_file = dataset.get_anno()
with_background = dataset.with_background
use_default_label = dataset.use_default_label
clsid2catid, catid2name = get_category_info(anno_file, with_background,
use_default_label)
# eval already exists json file
if FLAGS.json_eval:
logger.info(
"In json_eval mode, PaddleDetection will evaluate json files in "
"output_eval directly. And proposal.json, bbox.json and mask.json "
"will be detected by default.")
json_eval_results(cfg.metric,
json_directory=FLAGS.output_eval,
dataset=dataset)
return
compile_program = fluid.CompiledProgram(eval_prog).with_data_parallel()
assert cfg.metric != 'OID', "eval process of OID dataset \
is not supported."
if cfg.metric == "WIDERFACE":
raise ValueError("metric type {} does not support in tools/eval.py, "
"please use tools/face_eval.py".format(cfg.metric))
assert cfg.metric in ['COCO', 'VOC'], \
"unknown metric type {}".format(cfg.metric)
extra_keys = []
if cfg.metric == 'COCO':
extra_keys = ['im_info', 'im_id', 'im_shape']
if cfg.metric == 'VOC':
extra_keys = ['gt_bbox', 'gt_class', 'is_difficult']
keys, values, cls = parse_fetches(fetches, eval_prog, extra_keys)
# whether output bbox is normalized in model output layer
is_bbox_normalized = False
if hasattr(model, 'is_bbox_normalized') and \
callable(model.is_bbox_normalized):
is_bbox_normalized = model.is_bbox_normalized()
sub_eval_prog = None
sub_keys = None
sub_values = None
# build sub-program
if 'Mask' in main_arch and multi_scale_test:
sub_eval_prog = fluid.Program()
with fluid.program_guard(sub_eval_prog, startup_prog):
with fluid.unique_name.guard():
inputs_def = cfg['EvalReader']['inputs_def']
inputs_def['mask_branch'] = True
feed_vars, eval_loader = model.build_inputs(**inputs_def)
sub_fetches = model.eval(feed_vars,
multi_scale_test,
mask_branch=True)
assert cfg.metric == 'COCO'
extra_keys = ['im_id', 'im_shape']
sub_keys, sub_values, _ = parse_fetches(sub_fetches, sub_eval_prog,
extra_keys)
sub_eval_prog = sub_eval_prog.clone(True)
#if 'weights' in cfg:
# checkpoint.load_params(exe, sub_eval_prog, cfg.weights)
# load model
exe.run(startup_prog)
if 'weights' in cfg:
checkpoint.load_params(exe, startup_prog, cfg.weights)
resolution = None
if 'Mask' in cfg.architecture or cfg.architecture == 'HybridTaskCascade':
resolution = model.mask_head.resolution
eval_run(exe, compile_program, loader, clsid2catid, catid2name, keys,
values, cls, cfg, sub_eval_prog, sub_keys, sub_values, resolution)
#print(cfg['EvalReader']['dataset'].__dict__)
# evaluation
# if map_type not set, use default 11point, only use in VOC eval
map_type = cfg.map_type if 'map_type' in cfg else '11point'
save_only = getattr(cfg, 'save_prediction_only', False)
eval_results(cfg.metric, dataset=dataset)
def main():
cfg = load_config(FLAGS.config)
if 'architecture' in cfg:
main_arch = cfg.architecture
else:
raise ValueError("'architecture' not specified in config file.")
merge_config(FLAGS.opt)
# check if set use_gpu=True in paddlepaddle cpu version
check_gpu(cfg.use_gpu)
if 'test_feed' not in cfg:
test_feed = create(main_arch + 'TestFeed')
else:
test_feed = create(cfg.test_feed)
test_images = get_test_images(FLAGS.infer_dir, FLAGS.infer_img)
test_feed.dataset.add_images(test_images)
place = fluid.CUDAPlace(0) if cfg.use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
model = create(main_arch)
startup_prog = fluid.Program()
infer_prog = fluid.Program()
with fluid.program_guard(infer_prog, startup_prog):
with fluid.unique_name.guard():
_, feed_vars = create_feed(test_feed, use_pyreader=False)
test_fetches = model.test(feed_vars)
infer_prog = infer_prog.clone(True)
reader = create_reader(test_feed)
feeder = fluid.DataFeeder(place=place, feed_list=feed_vars.values())
exe.run(startup_prog)
if cfg.weights:
checkpoint.load_checkpoint(exe, infer_prog, cfg.weights)
if FLAGS.save_inference_model:
save_infer_model(FLAGS, exe, feed_vars, test_fetches, infer_prog)
# parse infer fetches
assert cfg.metric in ['COCO', 'VOC'], \
"unknown metric type {}".format(cfg.metric)
extra_keys = []
if cfg['metric'] == 'COCO':
extra_keys = ['im_info', 'im_id', 'im_shape']
if cfg['metric'] == 'VOC':
extra_keys = ['im_id', 'im_shape']
keys, values, _ = parse_fetches(test_fetches, infer_prog, extra_keys)
# parse dataset category
if cfg.metric == 'COCO':
from ppdet.utils.coco_eval import bbox2out, mask2out, get_category_info
if cfg.metric == "VOC":
from ppdet.utils.voc_eval import bbox2out, get_category_info
anno_file = getattr(test_feed.dataset, 'annotation', None)
with_background = getattr(test_feed, 'with_background', True)
use_default_label = getattr(test_feed, 'use_default_label', False)
clsid2catid, catid2name = get_category_info(anno_file, with_background,
use_default_label)
# whether output bbox is normalized in model output layer
is_bbox_normalized = False
if hasattr(model, 'is_bbox_normalized') and \
callable(model.is_bbox_normalized):
is_bbox_normalized = model.is_bbox_normalized()
imid2path = reader.imid2path
for iter_id, data in enumerate(reader()):
outs = exe.run(infer_prog,
feed=feeder.feed(data),
fetch_list=values,
return_numpy=False)
res = {
k: (np.array(v), v.recursive_sequence_lengths())
for k, v in zip(keys, outs)
}
logger.info('Infer iter {}'.format(iter_id))
bbox_results = None
mask_results = None
if 'bbox' in res:
bbox_results = bbox2out([res], clsid2catid, is_bbox_normalized)
if 'mask' in res:
mask_results = mask2out([res], clsid2catid,
model.mask_head.resolution)
# visualize result
im_ids = res['im_id'][0]
for im_id in im_ids:
image_path = imid2path[int(im_id)]
image = Image.open(image_path).convert('RGB')
image = visualize_results(image, int(im_id), catid2name,
FLAGS.draw_threshold, bbox_results,
mask_results)
save_name = get_save_image_name(FLAGS.output_dir, image_path)
logger.info("Detection bbox results save in {}".format(save_name))
image.save(save_name, quality=95)
def main():
cfg = load_config(FLAGS.config)
merge_config(FLAGS.opt)
check_config(cfg)
# check if set use_gpu=True in paddlepaddle cpu version
check_gpu(cfg.use_gpu)
# disable npu in config by default and check use_npu
if 'use_npu' not in cfg:
cfg.use_npu = False
check_npu(cfg.use_npu)
# disable xpu in config by default and check use_xpu
if 'use_xpu' not in cfg:
cfg.use_xpu = False
check_xpu(cfg.use_xpu)
# check if paddlepaddle version is satisfied
check_version()
main_arch = cfg.architecture
dataset = cfg.TestReader['dataset']
test_images = get_test_images(FLAGS.infer_dir, FLAGS.infer_img)
dataset.set_images(test_images)
if cfg.use_gpu:
place = fluid.CUDAPlace(0)
elif cfg.use_npu:
place = fluid.NPUPlace(0)
elif cfg.use_xpu:
place = fluid.XPUPlace(0)
else:
place = fluid.CPUPlace()
exe = fluid.Executor(place)
model = create(main_arch)
startup_prog = fluid.Program()
infer_prog = fluid.Program()
with fluid.program_guard(infer_prog, startup_prog):
with fluid.unique_name.guard():
inputs_def = cfg['TestReader']['inputs_def']
inputs_def['iterable'] = True
feed_vars, loader = model.build_inputs(**inputs_def)
test_fetches = model.test(feed_vars)
infer_prog = infer_prog.clone(True)
reader = create_reader(cfg.TestReader, devices_num=1)
loader.set_sample_list_generator(reader, place)
exe.run(startup_prog)
if cfg.weights:
checkpoint.load_params(exe, infer_prog, cfg.weights)
# parse infer fetches
assert cfg.metric in ['COCO', 'VOC', 'OID', 'WIDERFACE'], \
"unknown metric type {}".format(cfg.metric)
extra_keys = []
if cfg['metric'] in ['COCO', 'OID']:
extra_keys = ['im_info', 'im_id', 'im_shape']
if cfg['metric'] == 'VOC' or cfg['metric'] == 'WIDERFACE':
extra_keys = ['im_id', 'im_shape']
keys, values, _ = parse_fetches(test_fetches, infer_prog, extra_keys)
# parse dataset category
if cfg.metric == 'COCO':
from ppdet.utils.coco_eval import bbox2out, mask2out, segm2out, get_category_info
if cfg.metric == 'OID':
from ppdet.utils.oid_eval import bbox2out, get_category_info
if cfg.metric == "VOC":
from ppdet.utils.voc_eval import bbox2out, get_category_info
if cfg.metric == "WIDERFACE":
from ppdet.utils.widerface_eval_utils import bbox2out, lmk2out, get_category_info
anno_file = dataset.get_anno()
with_background = dataset.with_background
use_default_label = dataset.use_default_label
clsid2catid, catid2name = get_category_info(anno_file, with_background,
use_default_label)
# whether output bbox is normalized in model output layer
is_bbox_normalized = False
if hasattr(model, 'is_bbox_normalized') and \
callable(model.is_bbox_normalized):
is_bbox_normalized = model.is_bbox_normalized()
# use VisualDL to log image
if FLAGS.use_vdl:
assert six.PY3, "VisualDL requires Python >= 3.5"
from visualdl import LogWriter
vdl_writer = LogWriter(FLAGS.vdl_log_dir)
vdl_image_step = 0
vdl_image_frame = 0 # each frame can display ten pictures at most.
imid2path = dataset.get_imid2path()
for iter_id, data in enumerate(loader()):
outs = exe.run(infer_prog,
feed=data,
fetch_list=values,
return_numpy=False)
res = {
k: (np.array(v), v.recursive_sequence_lengths())
for k, v in zip(keys, outs)
}
logger.info('Infer iter {}'.format(iter_id))
if 'TTFNet' in cfg.architecture:
res['bbox'][1].append([len(res['bbox'][0])])
if 'CornerNet' in cfg.architecture:
from ppdet.utils.post_process import corner_post_process
post_config = getattr(cfg, 'PostProcess', None)
corner_post_process(res, post_config, cfg.num_classes)
bbox_results = None
mask_results = None
segm_results = None
lmk_results = None
if 'bbox' in res:
bbox_results = bbox2out([res], clsid2catid, is_bbox_normalized)
if 'mask' in res:
mask_results = mask2out([res], clsid2catid,
model.mask_head.resolution)
if 'segm' in res:
segm_results = segm2out([res], clsid2catid)
if 'landmark' in res:
lmk_results = lmk2out([res], is_bbox_normalized)
# visualize result
im_ids = res['im_id'][0]
for im_id in im_ids:
image_path = imid2path[int(im_id)]
image = Image.open(image_path).convert('RGB')
image = ImageOps.exif_transpose(image)
# use VisualDL to log original image
if FLAGS.use_vdl:
original_image_np = np.array(image)
vdl_writer.add_image(
"original/frame_{}".format(vdl_image_frame),
original_image_np, vdl_image_step)
image = visualize_results(image, int(im_id), catid2name,
FLAGS.draw_threshold, bbox_results,
mask_results, segm_results, lmk_results)
# use VisualDL to log image with bbox
if FLAGS.use_vdl:
infer_image_np = np.array(image)
vdl_writer.add_image("bbox/frame_{}".format(vdl_image_frame),
infer_image_np, vdl_image_step)
vdl_image_step += 1
if vdl_image_step % 10 == 0:
vdl_image_step = 0
vdl_image_frame += 1
save_name = get_save_image_name(FLAGS.output_dir, image_path)
logger.info("Detection bbox results save in {}".format(save_name))
image.save(save_name, quality=95)
def run(FLAGS, cfg, place):
# Model
main_arch = cfg.architecture
model = create(cfg.architecture)
# data
dataset = cfg.TestDataset
test_images = get_test_images(FLAGS.infer_dir, FLAGS.infer_img)
dataset.set_images(test_images)
test_loader = create('TestReader')(dataset, cfg['worker_num'])
extra_key = ['im_shape', 'scale_factor', 'im_id']
# TODO: support other metrics
imid2path = dataset.get_imid2path()
anno_file = dataset.get_anno()
with_background = cfg.with_background
use_default_label = dataset.use_default_label
if cfg.metric == 'COCO':
from ppdet.utils.coco_eval import get_category_info
if cfg.metric == 'VOC':
from ppdet.utils.voc_eval import get_category_info
clsid2catid, catid2name = get_category_info(anno_file, with_background,
use_default_label)
# Init Model
load_weight(model, cfg.weights)
# Run Infer
for iter_id, data in enumerate(test_loader):
# forward
model.eval()
outs = model(data)
for key in extra_key:
outs[key] = data[key]
for key, value in outs.items():
outs[key] = value.numpy()
if 'mask' in outs and 'bbox' in outs:
mask_resolution = model.mask_post_process.mask_resolution
from ppdet.py_op.post_process import mask_post_process
outs['mask'] = mask_post_process(outs, outs['im_shape'],
outs['scale_factor'],
mask_resolution)
eval_type = []
if 'bbox' in outs:
eval_type.append('bbox')
if 'mask' in outs:
eval_type.append('mask')
batch_res = get_infer_results([outs], eval_type, clsid2catid)
logger.info('Infer iter {}'.format(iter_id))
bbox_res = None
mask_res = None
bbox_num = outs['bbox_num']
start = 0
for i, im_id in enumerate(outs['im_id']):
image_path = imid2path[int(im_id)]
image = Image.open(image_path).convert('RGB')
end = start + bbox_num[i]
# use VisualDL to log original image
if FLAGS.use_vdl:
original_image_np = np.array(image)
vdl_writer.add_image(
"original/frame_{}".format(vdl_image_frame),
original_image_np, vdl_image_step)
if 'bbox' in batch_res:
bbox_res = batch_res['bbox'][start:end]
if 'mask' in batch_res:
mask_res = batch_res['mask'][start:end]
image = visualize_results(image, bbox_res, mask_res,
int(outs['im_id']), catid2name,
FLAGS.draw_threshold)
# use VisualDL to log image with bbox
if FLAGS.use_vdl:
infer_image_np = np.array(image)
vdl_writer.add_image("bbox/frame_{}".format(vdl_image_frame),
infer_image_np, vdl_image_step)
vdl_image_step += 1
if vdl_image_step % 10 == 0:
vdl_image_step = 0
vdl_image_frame += 1
# save image with detection
save_name = get_save_image_name(FLAGS.output_dir, image_path)
logger.info("Detection bbox results save in {}".format(save_name))
image.save(save_name, quality=95)
start = end
def run(FLAGS, cfg, place):
# Model
main_arch = cfg.architecture
model = create(cfg.architecture)
# data
dataset = cfg.TestDataset
test_images = get_test_images(FLAGS.infer_dir, FLAGS.infer_img)
dataset.set_images(test_images)
test_loader, _ = create('TestReader')(dataset, cfg['worker_num'], place)
# TODO: support other metrics
imid2path = dataset.get_imid2path()
from ppdet.utils.coco_eval import get_category_info
anno_file = dataset.get_anno()
with_background = cfg.with_background
use_default_label = dataset.use_default_label
clsid2catid, catid2name = get_category_info(anno_file, with_background,
use_default_label)
# Init Model
load_weight(model, cfg.weights)
# Run Infer
for iter_id, data in enumerate(test_loader):
# forward
model.eval()
outs = model(data, cfg.TestReader['inputs_def']['fields'], 'infer')
batch_res = get_infer_results([outs], outs.keys(), clsid2catid)
logger.info('Infer iter {}'.format(iter_id))
bbox_res = None
mask_res = None
im_ids = outs['im_id']
bbox_num = outs['bbox_num']
start = 0
for i, im_id in enumerate(im_ids):
im_id = im_ids[i]
image_path = imid2path[int(im_id)]
image = Image.open(image_path).convert('RGB')
end = start + bbox_num[i]
# use VisualDL to log original image
if FLAGS.use_vdl:
original_image_np = np.array(image)
vdl_writer.add_image(
"original/frame_{}".format(vdl_image_frame),
original_image_np, vdl_image_step)
if 'bbox' in batch_res:
bbox_res = batch_res['bbox'][start:end]
if 'mask' in batch_res:
mask_res = batch_res['mask'][start:end]
image = visualize_results(image, bbox_res, mask_res, int(im_id),
catid2name, FLAGS.draw_threshold)
# use VisualDL to log image with bbox
if FLAGS.use_vdl:
infer_image_np = np.array(image)
vdl_writer.add_image("bbox/frame_{}".format(vdl_image_frame),
infer_image_np, vdl_image_step)
vdl_image_step += 1
if vdl_image_step % 10 == 0:
vdl_image_step = 0
vdl_image_frame += 1
# save image with detection
save_name = get_save_image_name(FLAGS.output_dir, image_path)
logger.info("Detection bbox results save in {}".format(save_name))
image.save(save_name, quality=95)
start = end
def main():
cfg = load_config(FLAGS.config)
merge_config(FLAGS.opt)
check_config(cfg)
# check if set use_gpu=True in paddlepaddle cpu version
check_gpu(cfg.use_gpu)
# check if paddlepaddle version is satisfied
check_version()
main_arch = cfg.architecture
dataset = cfg.TestReader['dataset']
test_images = get_test_images(FLAGS.infer_dir, FLAGS.infer_img)
dataset.set_images(test_images)
place = fluid.CUDAPlace(0) if cfg.use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
model = create(main_arch)
startup_prog = fluid.Program()
infer_prog = fluid.Program()
with fluid.program_guard(infer_prog, startup_prog):
with fluid.unique_name.guard():
inputs_def = cfg['TestReader']['inputs_def']
feed_vars, loader = model.build_inputs(**inputs_def)
test_fetches = model.test(feed_vars)
infer_prog = infer_prog.clone(True)
reader = create_reader(cfg.TestReader)
# When iterable mode, set set_sample_list_generator(reader, place)
loader.set_sample_list_generator(reader)
not_quant_pattern = []
if FLAGS.not_quant_pattern:
not_quant_pattern = FLAGS.not_quant_pattern
config = {
'weight_quantize_type': 'channel_wise_abs_max',
'activation_quantize_type': 'moving_average_abs_max',
'quantize_op_types': ['depthwise_conv2d', 'mul', 'conv2d'],
'not_quant_pattern': not_quant_pattern
}
infer_prog = quant_aware(infer_prog, place, config, for_test=True)
exe.run(startup_prog)
if cfg.weights:
checkpoint.load_params(exe, infer_prog, cfg.weights)
infer_prog = convert(infer_prog, place, config, save_int8=False)
# parse infer fetches
assert cfg.metric in ['COCO', 'VOC', 'OID', 'WIDERFACE'], \
"unknown metric type {}".format(cfg.metric)
extra_keys = []
if cfg['metric'] in ['COCO', 'OID']:
extra_keys = ['im_info', 'im_id', 'im_shape']
if cfg['metric'] == 'VOC' or cfg['metric'] == 'WIDERFACE':
extra_keys = ['im_id', 'im_shape']
keys, values, _ = parse_fetches(test_fetches, infer_prog, extra_keys)
# parse dataset category
if cfg.metric == 'COCO':
from ppdet.utils.coco_eval import bbox2out, mask2out, get_category_info
if cfg.metric == 'OID':
from ppdet.utils.oid_eval import bbox2out, get_category_info
if cfg.metric == "VOC":
from ppdet.utils.voc_eval import bbox2out, get_category_info
if cfg.metric == "WIDERFACE":
from ppdet.utils.widerface_eval_utils import bbox2out, get_category_info
anno_file = dataset.get_anno()
with_background = dataset.with_background
use_default_label = dataset.use_default_label
clsid2catid, catid2name = get_category_info(anno_file, with_background,
use_default_label)
# whether output bbox is normalized in model output layer
is_bbox_normalized = False
if hasattr(model, 'is_bbox_normalized') and \
callable(model.is_bbox_normalized):
is_bbox_normalized = model.is_bbox_normalized()
imid2path = dataset.get_imid2path()
iter_id = 0
try:
loader.start()
while True:
outs = exe.run(infer_prog, fetch_list=values, return_numpy=False)
res = {
k: (np.array(v), v.recursive_sequence_lengths())
for k, v in zip(keys, outs)
}
logger.info('Infer iter {}'.format(iter_id))
iter_id += 1
bbox_results = None
mask_results = None
if 'bbox' in res:
bbox_results = bbox2out([res], clsid2catid, is_bbox_normalized)
if 'mask' in res:
mask_results = mask2out([res], clsid2catid,
model.mask_head.resolution)
# visualize result
im_ids = res['im_id'][0]
for im_id in im_ids:
image_path = imid2path[int(im_id)]
image = Image.open(image_path).convert('RGB')
image = visualize_results(image, int(im_id), catid2name,
FLAGS.draw_threshold, bbox_results,
mask_results)
save_name = get_save_image_name(FLAGS.output_dir, image_path)
logger.info(
"Detection bbox results save in {}".format(save_name))
image.save(save_name, quality=95)
except (StopIteration, fluid.core.EOFException):
loader.reset()
def run(FLAGS, cfg, place):
# Model
main_arch = cfg.architecture
model = create(cfg.architecture)
# Init Model
load_weight(model, cfg.weights)
# Data Reader
dataset = cfg.EvalDataset
eval_loader = create('EvalReader')(dataset, cfg['worker_num'])
extra_key = ['im_shape', 'scale_factor', 'im_id']
if cfg.metric == 'VOC':
extra_key += ['gt_bbox', 'gt_class', 'difficult']
# Run Eval
outs_res = []
sample_num = 0
start_time = time.time()
for iter_id, data in enumerate(eval_loader):
# forward
model.eval()
outs = model(data, mode='infer')
for key in extra_key:
outs[key] = data[key]
for key, value in outs.items():
outs[key] = value.numpy()
if 'mask' in outs and 'bbox' in outs:
mask_resolution = model.mask_post_process.mask_resolution
from ppdet.py_op.post_process import mask_post_process
outs['mask'] = mask_post_process(outs, outs['im_shape'],
outs['scale_factor'],
mask_resolution)
outs_res.append(outs)
# log
sample_num += outs['im_id'].shape[0]
if iter_id % 100 == 0:
logger.info("Eval iter: {}".format(iter_id))
cost_time = time.time() - start_time
logger.info('Total sample number: {}, averge FPS: {}'.format(
sample_num, sample_num / cost_time))
eval_type = []
if 'bbox' in outs:
eval_type.append('bbox')
if 'mask' in outs:
eval_type.append('mask')
# Metric
# TODO: support other metric
with_background = cfg.with_background
use_default_label = dataset.use_default_label
if cfg.metric == 'COCO':
from ppdet.utils.coco_eval import get_category_info
clsid2catid, catid2name = get_category_info(dataset.get_anno(),
with_background,
use_default_label)
infer_res = get_infer_results(outs_res, eval_type, clsid2catid)
elif cfg.metric == 'VOC':
from ppdet.utils.voc_eval import get_category_info
clsid2catid, catid2name = get_category_info(dataset.get_label_list(),
with_background,
use_default_label)
infer_res = outs_res
eval_results(infer_res, cfg.metric, dataset)
def main():
env = os.environ
FLAGS.dist = 'PADDLE_TRAINER_ID' in env \
and 'PADDLE_TRAINERS_NUM' in env \
and int(env['PADDLE_TRAINERS_NUM']) > 1
if FLAGS.dist:
trainer_id = int(env['PADDLE_TRAINER_ID'])
local_seed = (99 + trainer_id)
random.seed(local_seed)
np.random.seed(local_seed)
if FLAGS.enable_ce:
random.seed(0)
np.random.seed(0)
cfg = load_config(FLAGS.config)
merge_config(FLAGS.opt)
check_config(cfg)
# check if set use_gpu=True in paddlepaddle cpu version
check_gpu(cfg.use_gpu)
# check if paddlepaddle version is satisfied
check_version()
save_only = getattr(cfg, 'save_prediction_only', False)
if save_only:
raise NotImplementedError('The config file only support prediction,'
' training stage is not implemented now')
main_arch = cfg.architecture
if cfg.use_gpu:
devices_num = fluid.core.get_cuda_device_count()
else:
devices_num = int(os.environ.get('CPU_NUM', 1))
if 'FLAGS_selected_gpus' in env:
device_id = int(env['FLAGS_selected_gpus'])
else:
device_id = 0
place = fluid.CUDAPlace(device_id) if cfg.use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
lr_builder = create('LearningRate')
optim_builder = create('OptimizerBuilder')
# build program
startup_prog = fluid.Program()
train_prog = fluid.Program()
if FLAGS.enable_ce:
startup_prog.random_seed = 1000
train_prog.random_seed = 1000
with fluid.program_guard(train_prog, startup_prog):
with fluid.unique_name.guard():
model = create(main_arch)
if FLAGS.fp16:
assert (getattr(model.backbone, 'norm_type', None)
!= 'affine_channel'), \
'--fp16 currently does not support affine channel, ' \
' please modify backbone settings to use batch norm'
with mixed_precision_context(FLAGS.loss_scale, FLAGS.fp16) as ctx:
inputs_def = cfg['TrainReader']['inputs_def']
feed_vars, train_loader = model.build_inputs(**inputs_def)
train_fetches = model.train(feed_vars)
loss = train_fetches['loss']
if FLAGS.fp16:
loss *= ctx.get_loss_scale_var()
lr = lr_builder()
optimizer = optim_builder(lr)
optimizer.minimize(loss)
if FLAGS.fp16:
loss /= ctx.get_loss_scale_var()
if 'use_ema' in cfg and cfg['use_ema']:
global_steps = _decay_step_counter()
ema = ExponentialMovingAverage(cfg['ema_decay'],
thres_steps=global_steps)
ema.update()
# parse train fetches
train_keys, train_values, _ = parse_fetches(train_fetches)
train_values.append(lr)
if FLAGS.eval:
eval_prog = fluid.Program()
with fluid.program_guard(eval_prog, startup_prog):
with fluid.unique_name.guard():
model = create(main_arch)
inputs_def = cfg['EvalReader']['inputs_def']
feed_vars, eval_loader = model.build_inputs(**inputs_def)
fetches = model.eval(feed_vars)
eval_prog = eval_prog.clone(True)
eval_reader = create_reader(cfg.EvalReader, devices_num=1)
eval_loader.set_sample_list_generator(eval_reader, place)
# parse eval fetches
extra_keys = []
if cfg.metric == 'COCO':
# 为了在eval取结果时拿到im_size，这里加上了im_size
extra_keys = ['im_info', 'im_id', 'im_shape', 'im_size']
if cfg.metric == 'VOC':
extra_keys = ['gt_bbox', 'gt_class', 'is_difficult']
if cfg.metric == 'WIDERFACE':
extra_keys = ['im_id', 'im_shape', 'gt_bbox']
eval_keys, eval_values, eval_cls = parse_fetches(
fetches, eval_prog, extra_keys)
# parse dataset category
if cfg.metric == 'COCO':
from ppdet.utils.coco_eval import get_category_info
eval_dataset = cfg.EvalReader['dataset']
anno_file = eval_dataset.get_anno()
with_background = eval_dataset.with_background
use_default_label = eval_dataset.use_default_label
clsid2catid, catid2name = get_category_info(anno_file, with_background,
use_default_label)
# compile program for multi-devices
build_strategy = fluid.BuildStrategy()
build_strategy.fuse_all_optimizer_ops = False
# only enable sync_bn in multi GPU devices
sync_bn = getattr(model.backbone, 'norm_type', None) == 'sync_bn'
build_strategy.sync_batch_norm = sync_bn and devices_num > 1 \
and cfg.use_gpu
exec_strategy = fluid.ExecutionStrategy()
# iteration number when CompiledProgram tries to drop local execution scopes.
# Set it to be 1 to save memory usages, so that unused variables in
# local execution scopes can be deleted after each iteration.
exec_strategy.num_iteration_per_drop_scope = 1
if FLAGS.dist:
dist_utils.prepare_for_multi_process(exe, build_strategy, startup_prog,
train_prog)
exec_strategy.num_threads = 1
exe.run(startup_prog)
compiled_train_prog = fluid.CompiledProgram(train_prog).with_data_parallel(
loss_name=loss.name,
build_strategy=build_strategy,
exec_strategy=exec_strategy)
if FLAGS.eval:
compiled_eval_prog = fluid.CompiledProgram(eval_prog)
fuse_bn = getattr(model.backbone, 'norm_type', None) == 'affine_channel'
ignore_params = cfg.finetune_exclude_pretrained_params \
if 'finetune_exclude_pretrained_params' in cfg else []
start_iter = 0
if FLAGS.resume_checkpoint:
checkpoint.load_checkpoint(exe, train_prog, FLAGS.resume_checkpoint)
start_iter = checkpoint.global_step()
elif cfg.pretrain_weights and fuse_bn and not ignore_params:
checkpoint.load_and_fusebn(exe, train_prog, cfg.pretrain_weights)
elif cfg.pretrain_weights:
checkpoint.load_params(exe,
train_prog,
cfg.pretrain_weights,
ignore_params=ignore_params)
train_reader = create_reader(cfg.TrainReader,
(cfg.max_iters - start_iter) * devices_num,
cfg,
devices_num=devices_num)
train_loader.set_sample_list_generator(train_reader, place)
# whether output bbox is normalized in model output layer
is_bbox_normalized = False
if hasattr(model, 'is_bbox_normalized') and \
callable(model.is_bbox_normalized):
is_bbox_normalized = model.is_bbox_normalized()
# if map_type not set, use default 11point, only use in VOC eval
map_type = cfg.map_type if 'map_type' in cfg else '11point'
train_stats = TrainingStats(cfg.log_smooth_window, train_keys)
train_loader.start()
start_time = time.time()
end_time = time.time()
cfg_name = os.path.basename(FLAGS.config).split('.')[0]
save_dir = os.path.join(cfg.save_dir, cfg_name)
time_stat = deque(maxlen=cfg.log_smooth_window)
best_box_ap_list = [0.0, 0] #[map, iter]
best_ap_list = [0.0, 0] #[map, iter]
print(
'============================ asasasaaawws ============================'
)
print(clsid2catid)
for it in range(start_iter, cfg.max_iters):
start_time = end_time
end_time = time.time()
time_stat.append(end_time - start_time)
time_cost = np.mean(time_stat)
eta_sec = (cfg.max_iters - it) * time_cost
eta = str(datetime.timedelta(seconds=int(eta_sec)))
outs = exe.run(compiled_train_prog, fetch_list=train_values)
stats = {k: np.array(v).mean() for k, v in zip(train_keys, outs[:-1])}
# use vdl-paddle to log loss
if FLAGS.use_vdl:
if it % cfg.log_iter == 0:
for loss_name, loss_value in stats.items():
vdl_writer.add_scalar(loss_name, loss_value, vdl_loss_step)
vdl_loss_step += 1
train_stats.update(stats)
logs = train_stats.log()
if it % cfg.log_iter == 0 and (not FLAGS.dist or trainer_id == 0):
strs = 'iter: {}, lr: {:.6f}, {}, time: {:.3f}, eta: {}'.format(
it, np.mean(outs[-1]), logs, time_cost, eta)
logger.info(strs)
# NOTE : profiler tools, used for benchmark
if FLAGS.is_profiler and it == 5:
profiler.start_profiler("All")
elif FLAGS.is_profiler and it == 10:
profiler.stop_profiler("total", FLAGS.profiler_path)
return
if (it > 0 and it % cfg.snapshot_iter == 0 or it == cfg.max_iters - 1) \
and (not FLAGS.dist or trainer_id == 0):
save_name = str(it) if it != cfg.max_iters - 1 else "model_final"
if 'use_ema' in cfg and cfg['use_ema']:
exe.run(ema.apply_program)
checkpoint.save(exe, train_prog, os.path.join(save_dir, save_name))
clear_model(save_dir)
# ========================= eval ===========================
if FLAGS.eval:
if (it > 0 and it % FLAGS.eval_iter == 0
or it == cfg.max_iters - 1):
eval_run(exe, compiled_eval_prog, eval_loader, clsid2catid,
catid2name, eval_keys, eval_values, eval_cls)
box_ap, mask_ap = eval_results(cfg.metric,
cfg['EvalReader']['dataset'])
logger.info("box ap: %.3f, mask ap: %.3f" %
(box_ap[0], mask_ap[0]))
# 以mask_ap作为标准而不是box_ap
ap = mask_ap
if ap[0] > best_ap_list[0]:
best_ap_list[0] = ap[0]
best_ap_list[1] = it
checkpoint.save(exe, train_prog,
os.path.join(save_dir, "best_model"))
clear_model(save_dir)
logger.info("Best test ap: {}, in iter: {}".format(
best_ap_list[0], best_ap_list[1]))
if 'use_ema' in cfg and cfg['use_ema']:
exe.run(ema.restore_program)
train_loader.reset()
def main():
cfg = load_config(FLAGS.config)
merge_config(FLAGS.opt)
check_config(cfg)
# check if set use_gpu=True in paddlepaddle cpu version
check_gpu(cfg.use_gpu)
# check if paddlepaddle version is satisfied
check_version()
main_arch = cfg.architecture
dataset = cfg.TestReader['dataset']
test_images = get_test_images(FLAGS.infer_dir, FLAGS.infer_img)
dataset.set_images(test_images)
place = fluid.CUDAPlace(0) if cfg.use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
model = create(main_arch)
startup_prog = fluid.Program()
infer_prog = fluid.Program()
with fluid.program_guard(infer_prog, startup_prog):
with fluid.unique_name.guard():
inputs_def = cfg['TestReader']['inputs_def']
inputs_def['iterable'] = True
feed_vars, loader = model.build_inputs(**inputs_def)
test_fetches = model.test(feed_vars)
infer_prog = infer_prog.clone(True)
reader = create_reader(cfg.TestReader, devices_num=1)
loader.set_sample_list_generator(reader, place)
exe.run(startup_prog)
if cfg.weights:
checkpoint.load_params(exe, infer_prog, cfg.weights)
# parse infer fetches
assert cfg.metric in ['COCO', 'VOC', 'OID', 'WIDERFACE'], \
"unknown metric type {}".format(cfg.metric)
extra_keys = []
if cfg['metric'] in ['COCO', 'OID']:
extra_keys = ['im_info', 'im_id', 'im_shape']
if cfg['metric'] == 'VOC' or cfg['metric'] == 'WIDERFACE':
extra_keys = ['im_id', 'im_shape']
keys, values, _ = parse_fetches(test_fetches, infer_prog, extra_keys)
# parse dataset category
if cfg.metric == 'COCO':
from ppdet.utils.coco_eval import bbox2out, mask2out, segm2out, get_category_info
if cfg.metric == 'OID':
from ppdet.utils.oid_eval import bbox2out, get_category_info
if cfg.metric == "VOC":
from ppdet.utils.voc_eval import bbox2out, get_category_info
if cfg.metric == "WIDERFACE":
from ppdet.utils.widerface_eval_utils import bbox2out, lmk2out, get_category_info
anno_file = dataset.get_anno()
with_background = dataset.with_background
use_default_label = dataset.use_default_label
clsid2catid, catid2name = get_category_info(anno_file, with_background,
use_default_label)
# whether output bbox is normalized in model output layer
is_bbox_normalized = False
if hasattr(model, 'is_bbox_normalized') and \
callable(model.is_bbox_normalized):
is_bbox_normalized = model.is_bbox_normalized()
# use VisualDL to log image
if FLAGS.use_vdl:
assert six.PY3, "VisualDL requires Python >= 3.5"
from visualdl import LogWriter
vdl_writer = LogWriter(FLAGS.vdl_log_dir)
vdl_image_step = 0
vdl_image_frame = 0 # each frame can display ten pictures at most.
imid2path = dataset.get_imid2path()
resultBBox = []
for iter_id, data in enumerate(loader()):
outs = exe.run(infer_prog,
feed=data,
fetch_list=values,
return_numpy=False)
res = {
k: (np.array(v), v.recursive_sequence_lengths())
for k, v in zip(keys, outs)
}
logger.info('Infer iter {}'.format(iter_id))
if 'TTFNet' in cfg.architecture:
res['bbox'][1].append([len(res['bbox'][0])])
if 'CornerNet' in cfg.architecture:
from ppdet.utils.post_process import corner_post_process
post_config = getattr(cfg, 'PostProcess', None)
corner_post_process(res, post_config, cfg.num_classes)
bbox_results = None
mask_results = None
segm_results = None
lmk_results = None
if 'bbox' in res:
bbox_results = bbox2out([res], clsid2catid, is_bbox_normalized)
if 'mask' in res:
mask_results = mask2out([res], clsid2catid,
model.mask_head.resolution)
if 'segm' in res:
segm_results = segm2out([res], clsid2catid)
if 'landmark' in res:
lmk_results = lmk2out([res], is_bbox_normalized)
# bbox 四个值：左上角坐标 + 宽度 + 高度
# {'image_id': 0, 'category_id': 0, 'bbox': [695.04443359375, 723.8153686523438, 128.288818359375, 61.5987548828125], 'score': 0.9990022778511047}
im_ids = res['im_id'][0]
image_path = imid2path[int(im_ids[0])]
prefix = image_path.split('/')[-1]
imageName = prefix.split('.')[0]
for i, result in enumerate(bbox_results):
score = result["score"]
bbox = result["bbox"]
x1 = str(int(bbox[0]))
y1 = str(int(bbox[1]))
x2 = str(int(bbox[2] + bbox[0]))
y2 = str(int(bbox[3] + bbox[1]))
if (score > 0.01):
resStr = imageName + ' ' + str(round(
score,
3)) + ' ' + x1 + ' ' + y1 + ' ' + x2 + ' ' + y2 + '\n'
resultBBox.append(resStr)
# visualize result
for im_id in im_ids:
image_path = imid2path[int(im_id)]
image = Image.open(image_path).convert('RGB')
image = ImageOps.exif_transpose(image)
# use VisualDL to log original image
if FLAGS.use_vdl:
original_image_np = np.array(image)
vdl_writer.add_image(
"original/frame_{}".format(vdl_image_frame),
original_image_np, vdl_image_step)
image = visualize_results(image, int(im_id), catid2name,
FLAGS.draw_threshold, bbox_results,
mask_results, segm_results, lmk_results)
# use VisualDL to log image with bbox
if FLAGS.use_vdl:
infer_image_np = np.array(image)
vdl_writer.add_image("bbox/frame_{}".format(vdl_image_frame),
infer_image_np, vdl_image_step)
vdl_image_step += 1
if vdl_image_step % 10 == 0:
vdl_image_step = 0
vdl_image_frame += 1
save_name = get_save_image_name(FLAGS.output_dir, image_path)
logger.info("Detection bbox results save in {}".format(save_name))
image.save(save_name, quality=95)
resulttxtPath = "/home/aistudio/work/PaddleDetection-release-2.0-beta/output/test_result.txt"
f = open(resulttxtPath, 'w+', encoding='utf-8')
for i, p in enumerate(resultBBox):
f.write(p)
f.close()
def main():
cfg = load_config(FLAGS.config)
merge_config(FLAGS.opt)
check_config(cfg)
# check if set use_gpu=True in paddlepaddle cpu version
check_gpu(cfg.use_gpu)
# check if paddlepaddle version is satisfied
check_version()
main_arch = cfg.architecture
dataset = cfg.TestReader['dataset']
test_images = get_test_images(FLAGS.infer_dir, FLAGS.infer_img)
dataset.set_images(test_images)
place = fluid.CUDAPlace(0) if cfg.use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
model = create(main_arch)
startup_prog = fluid.Program()
infer_prog = fluid.Program()
with fluid.program_guard(infer_prog, startup_prog):
with fluid.unique_name.guard():
inputs_def = cfg['TestReader']['inputs_def']
inputs_def['iterable'] = True
feed_vars, loader = model.build_inputs(**inputs_def)
test_fetches = model.test(feed_vars)
infer_prog = infer_prog.clone(True)
reader = create_reader(cfg.TestReader, devices_num=1)
loader.set_sample_list_generator(reader, place)
exe.run(startup_prog)
if cfg.weights:
checkpoint.load_params(exe, infer_prog, cfg.weights)
# parse infer fetches
assert cfg.metric in ['COCO', 'VOC', 'OID', 'WIDERFACE'], \
"unknown metric type {}".format(cfg.metric)
extra_keys = []
if cfg['metric'] in ['COCO', 'OID']:
extra_keys = ['im_info', 'im_id', 'im_shape']
if cfg['metric'] == 'VOC' or cfg['metric'] == 'WIDERFACE':
extra_keys = ['im_id', 'im_shape']
keys, values, _ = parse_fetches(test_fetches, infer_prog, extra_keys)
# parse dataset category
if cfg.metric == 'COCO':
from ppdet.utils.coco_eval import bbox2out, mask2out, get_category_info
if cfg.metric == 'OID':
from ppdet.utils.oid_eval import bbox2out, get_category_info
if cfg.metric == "VOC":
from ppdet.utils.voc_eval import bbox2out, get_category_info
if cfg.metric == "WIDERFACE":
from ppdet.utils.widerface_eval_utils import bbox2out, lmk2out, get_category_info
anno_file = dataset.get_anno()
with_background = dataset.with_background
use_default_label = dataset.use_default_label
clsid2catid, catid2name = get_category_info(anno_file, with_background,
use_default_label)
# whether output bbox is normalized in model output layer
is_bbox_normalized = False
if hasattr(model, 'is_bbox_normalized') and \
callable(model.is_bbox_normalized):
is_bbox_normalized = model.is_bbox_normalized()
colors = get_colors(len(catid2name) * 7)
draw_image = True
draw_thresh = 0.15
imid2path = dataset.get_imid2path()
for iter_id, data in enumerate(loader()):
outs = exe.run(infer_prog,
feed=data,
fetch_list=values,
return_numpy=False)
res = {
k: (np.array(v), v.recursive_sequence_lengths())
for k, v in zip(keys, outs)
}
logger.info('Infer iter {}'.format(iter_id))
# visualize result
im_ids = res['im_id'][0]
for im_id in im_ids:
im_id = int(im_id)
image_path = imid2path[im_id]
image = cv2.imread(image_path)
masks = res['masks'][0]
classes = res['classes'][0]
scores = res['scores'][0]
if scores[0] < 0.0:
masks = np.array([])
classes = np.array([])
scores = np.array([])
boxes = np.array([])
else:
# 获取boxes
boxes = []
for ms in masks:
sum_1 = np.sum(ms, axis=0)
x = np.where(sum_1 > 0.5)[0]
sum_2 = np.sum(ms, axis=1)
y = np.where(sum_2 > 0.5)[0]
if len(x) == 0: # 掩码全是0的话（即没有一个像素是前景）
x0, x1, y0, y1 = 0, 1, 0, 1
else:
x0, x1, y0, y1 = x[0], x[-1], y[0], y[-1]
boxes.append([x0, y0, x1, y1])
boxes = np.array(boxes).astype(np.float32)
if len(scores) > 0 and draw_image:
pos = np.where(scores >= draw_thresh)
masks2 = masks[pos] # [M, h, w]
classes2 = classes[pos] # [M, ]
scores2 = scores[pos] # [M, ]
boxes2 = boxes[pos] # [M, 4]
image = draw(image, boxes2, scores2, classes2, masks2,
clsid2catid, catid2name, colors)
save_name = get_save_image_name(FLAGS.output_dir, image_path)
logger.info("Detection bbox results save in {}".format(save_name))
cv2.imwrite(save_name, image)
def main():
cfg = load_config(FLAGS.config)
merge_config(FLAGS.opt)
check_config(cfg)
# check if set use_gpu=True in paddlepaddle cpu version
check_gpu(cfg.use_gpu)
# check if paddlepaddle version is satisfied
check_version()
main_arch = cfg.architecture
dataset = cfg.TestReader['dataset']
test_images = get_test_images(FLAGS.infer_dir, FLAGS.infer_img)
dataset.set_images(test_images)
place = fluid.CUDAPlace(0) if cfg.use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
model = create(main_arch)
startup_prog = fluid.Program()
infer_prog = fluid.Program()
with fluid.program_guard(infer_prog, startup_prog):
with fluid.unique_name.guard():
inputs_def = cfg['TestReader']['inputs_def']
inputs_def['iterable'] = True
feed_vars, loader = model.build_inputs(**inputs_def)
test_fetches = model.test(feed_vars)
infer_prog = infer_prog.clone(True)
reader = create_reader(cfg.TestReader, devices_num=1)
loader.set_sample_list_generator(reader, place)
exe.run(startup_prog)
if cfg.weights:
checkpoint.load_params(exe, infer_prog, cfg.weights)
# parse infer fetches
assert cfg.metric in ['COCO', 'VOC', 'OID', 'WIDERFACE'], \
"unknown metric type {}".format(cfg.metric)
extra_keys = []
if cfg['metric'] in ['COCO', 'OID']:
extra_keys = ['im_info', 'im_id', 'im_shape']
if cfg['metric'] == 'VOC' or cfg['metric'] == 'WIDERFACE':
extra_keys = ['im_id', 'im_shape']
keys, values, _ = parse_fetches(test_fetches, infer_prog, extra_keys)
# parse dataset category
if cfg.metric == 'COCO':
from ppdet.utils.coco_eval import bbox2out, mask2out, get_category_info
if cfg.metric == 'OID':
from ppdet.utils.oid_eval import bbox2out, get_category_info
if cfg.metric == "VOC":
from ppdet.utils.voc_eval import bbox2out, get_category_info
if cfg.metric == "WIDERFACE":
from ppdet.utils.widerface_eval_utils import bbox2out, get_category_info
anno_file = dataset.get_anno()
with_background = dataset.with_background
use_default_label = dataset.use_default_label
clsid2catid, catid2name = get_category_info(anno_file, with_background,
use_default_label)
# whether output bbox is normalized in model output layer
is_bbox_normalized = False
if hasattr(model, 'is_bbox_normalized') and \
callable(model.is_bbox_normalized):
is_bbox_normalized = model.is_bbox_normalized()
# use tb-paddle to log image
if FLAGS.use_tb:
from tb_paddle import SummaryWriter
tb_writer = SummaryWriter(FLAGS.tb_log_dir)
tb_image_step = 0
tb_image_frame = 0 # each frame can display ten pictures at most.
imid2path = dataset.get_imid2path()
for iter_id, data in enumerate(loader()):
outs = exe.run(infer_prog,
feed=data,
fetch_list=values,
return_numpy=False)
res = {
k: (np.array(v), v.recursive_sequence_lengths())
for k, v in zip(keys, outs)
}
logger.info('Infer iter {}'.format(iter_id))
bbox_results = None
mask_results = None
if 'bbox' in res:
bbox_results = bbox2out([res], clsid2catid, is_bbox_normalized)
if 'mask' in res:
mask_results = mask2out([res], clsid2catid,
model.mask_head.resolution)
# visualize result
im_ids = res['im_id'][0]
for im_id in im_ids:
image_path = imid2path[int(im_id)]
image = Image.open(image_path).convert('RGB')
# use tb-paddle to log original image
if FLAGS.use_tb:
original_image_np = np.array(image)
tb_writer.add_image("original/frame_{}".format(tb_image_frame),
original_image_np,
tb_image_step,
dataformats='HWC')
image = visualize_results(image, int(im_id), catid2name,
FLAGS.draw_threshold, bbox_results,
mask_results)
# use tb-paddle to log image with bbox
if FLAGS.use_tb:
infer_image_np = np.array(image)
tb_writer.add_image("bbox/frame_{}".format(tb_image_frame),
infer_image_np,
tb_image_step,
dataformats='HWC')
tb_image_step += 1
if tb_image_step % 10 == 0:
tb_image_step = 0
tb_image_frame += 1
save_name = get_save_image_name(FLAGS.output_dir, image_path)
logger.info("Detection bbox results save in {}".format(save_name))
image.save(save_name, quality=95)
def main():
cfg = load_config(FLAGS.config)
if 'architecture' in cfg:
main_arch = cfg.architecture
else:
raise ValueError("'architecture' not specified in config file.")
merge_config(FLAGS.opt)
# check if set use_gpu=True in paddlepaddle cpu version
check_gpu(cfg.use_gpu)
# print_total_cfg(cfg)
if 'test_feed' not in cfg:
test_feed = create(main_arch + 'TestFeed')
else:
test_feed = create(cfg.test_feed)
test_images = get_test_images(FLAGS.infer_dir, FLAGS.infer_img)
test_feed.dataset.add_images(test_images)
place = fluid.CUDAPlace(0) if cfg.use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
infer_prog, feed_var_names, fetch_list = fluid.io.load_inference_model(
dirname=FLAGS.model_path,
model_filename=FLAGS.model_name,
params_filename=FLAGS.params_name,
executor=exe)
reader = create_reader(test_feed)
feeder = fluid.DataFeeder(
place=place, feed_list=feed_var_names, program=infer_prog)
# parse infer fetches
assert cfg.metric in ['COCO', 'VOC'], \
"unknown metric type {}".format(cfg.metric)
extra_keys = []
if cfg['metric'] == 'COCO':
extra_keys = ['im_info', 'im_id', 'im_shape']
if cfg['metric'] == 'VOC':
extra_keys = ['im_id', 'im_shape']
keys, values, _ = parse_fetches({
'bbox': fetch_list
}, infer_prog, extra_keys)
# parse dataset category
if cfg.metric == 'COCO':
from ppdet.utils.coco_eval import bbox2out, mask2out, get_category_info
if cfg.metric == "VOC":
from ppdet.utils.voc_eval import bbox2out, get_category_info
anno_file = getattr(test_feed.dataset, 'annotation', None)
with_background = getattr(test_feed, 'with_background', True)
use_default_label = getattr(test_feed, 'use_default_label', False)
clsid2catid, catid2name = get_category_info(anno_file, with_background,
use_default_label)
# whether output bbox is normalized in model output layer
is_bbox_normalized = False
# use tb-paddle to log image
if FLAGS.use_tb:
from tb_paddle import SummaryWriter
tb_writer = SummaryWriter(FLAGS.tb_log_dir)
tb_image_step = 0
tb_image_frame = 0 # each frame can display ten pictures at most.
imid2path = reader.imid2path
keys = ['bbox']
infer_time = True
compile_prog = fluid.compiler.CompiledProgram(infer_prog)
for iter_id, data in enumerate(reader()):
feed_data = [[d[0], d[1]] for d in data]
# for infer time
if infer_time:
warmup_times = 10
repeats_time = 100
feed_data_dict = feeder.feed(feed_data)
for i in range(warmup_times):
exe.run(compile_prog,
feed=feed_data_dict,
fetch_list=fetch_list,
return_numpy=False)
start_time = time.time()
for i in range(repeats_time):
exe.run(compile_prog,
feed=feed_data_dict,
fetch_list=fetch_list,
return_numpy=False)
print("infer time: {} ms/sample".format((time.time() - start_time) *
1000 / repeats_time))
infer_time = False
outs = exe.run(compile_prog,
feed=feeder.feed(feed_data),
fetch_list=fetch_list,
return_numpy=False)
res = {
k: (np.array(v), v.recursive_sequence_lengths())
for k, v in zip(keys, outs)
}
res['im_id'] = [[d[2] for d in data]]
logger.info('Infer iter {}'.format(iter_id))
bbox_results = None
mask_results = None
if 'bbox' in res:
bbox_results = bbox2out([res], clsid2catid, is_bbox_normalized)
if 'mask' in res:
mask_results = mask2out([res], clsid2catid,
model.mask_head.resolution)
# visualize result
im_ids = res['im_id'][0]
for im_id in im_ids:
image_path = imid2path[int(im_id)]
image = Image.open(image_path).convert('RGB')
# use tb-paddle to log original image
if FLAGS.use_tb:
original_image_np = np.array(image)
tb_writer.add_image(
"original/frame_{}".format(tb_image_frame),
original_image_np,
tb_image_step,
dataformats='HWC')
image = visualize_results(image,
int(im_id), catid2name,
FLAGS.draw_threshold, bbox_results,
mask_results)
# use tb-paddle to log image with bbox
if FLAGS.use_tb:
infer_image_np = np.array(image)
tb_writer.add_image(
"bbox/frame_{}".format(tb_image_frame),
infer_image_np,
tb_image_step,
dataformats='HWC')
tb_image_step += 1
if tb_image_step % 10 == 0:
tb_image_step = 0
tb_image_frame += 1
save_name = get_save_image_name(FLAGS.output_dir, image_path)
logger.info("Detection bbox results save in {}".format(save_name))
image.save(save_name, quality=95)
