def main():
"""
Main evaluate function
"""
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 'eval_feed' not in cfg:
eval_feed = create(main_arch + 'EvalFeed')
else:
eval_feed = create(cfg.eval_feed)
# 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():
_, feed_vars = create_feed(eval_feed, iterable=True)
fetches = model.eval(feed_vars)
eval_prog = eval_prog.clone(True)
# load model
exe.run(startup_prog)
if 'weights' in cfg:
checkpoint.load_params(exe, eval_prog, cfg.weights)
assert cfg.metric in ['WIDERFACE'], \
"unknown metric type {}".format(cfg.metric)
annotation_file = getattr(eval_feed.dataset, 'annotation', None)
dataset_dir = FLAGS.dataset_dir if FLAGS.dataset_dir else \
getattr(eval_feed.dataset, 'dataset_dir', None)
img_root_dir = dataset_dir
if FLAGS.eval_mode == "widerface":
image_dir = getattr(eval_feed.dataset, 'image_dir', None)
img_root_dir = os.path.join(dataset_dir, image_dir)
gt_file = os.path.join(dataset_dir, annotation_file)
pred_dir = FLAGS.output_eval if FLAGS.output_eval else 'output/pred'
face_eval_run(exe,
eval_prog,
fetches,
img_root_dir,
gt_file,
pred_dir=pred_dir,
eval_mode=FLAGS.eval_mode,
multi_scale=FLAGS.multi_scale)
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)
if 'test_feed' not in cfg:
test_feed = create(main_arch + 'TestFeed')
else:
test_feed = create(cfg.test_feed)
# Use CPU for exporting inference model instead of GPU
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():
_, feed_vars = create_feed(test_feed, iterable=True)
test_fetches = model.test(feed_vars)
infer_prog = infer_prog.clone(True)
exe.run(startup_prog)
checkpoint.load_params(exe, infer_prog, cfg.weights)
save_infer_model(FLAGS, exe, feed_vars, test_fetches, infer_prog)
def init_model(self):
self.place = fluid.CUDAPlace(0) if self.use_gpu else fluid.CPUPlace()
self.exe = fluid.Executor(self.place)
self.model = create(self.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(self.test_feed, use_pyreader=False)
self.test_fetches = self.model.test(feed_vars)
self.infer_prog = infer_prog.clone(True)
self.feeder = fluid.DataFeeder(place=self.place,
feed_list=feed_vars.values())
self.exe.run(startup_prog)
if self.cfg.weights:
checkpoint.load_checkpoint(self.exe, self.infer_prog,
self.model_path)
self.is_bbox_normalized = False
if hasattr(self.model, 'is_bbox_normalized') and \
callable(self.model.is_bbox_normalized):
self.is_bbox_normalized = self.model.is_bbox_normalized()
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)
if 'log_iter' not in cfg:
cfg.log_iter = 20
# check if set use_gpu=True in paddlepaddle cpu version
check_gpu(cfg.use_gpu)
if cfg.use_gpu:
devices_num = fluid.core.get_cuda_device_count()
else:
devices_num = int(
os.environ.get('CPU_NUM', multiprocessing.cpu_count()))
if 'eval_feed' not in cfg:
eval_feed = create(main_arch + 'EvalFeed')
else:
eval_feed = create(cfg.eval_feed)
place = fluid.CUDAPlace(0) if cfg.use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
_, test_feed_vars = create_feed(eval_feed, False)
eval_reader = create_reader(eval_feed, args_path=FLAGS.dataset_dir)
#eval_pyreader.decorate_sample_list_generator(eval_reader, place)
test_data_feed = fluid.DataFeeder(test_feed_vars.values(), place)
assert os.path.exists(FLAGS.model_path)
infer_prog, feed_names, fetch_targets = fluid.io.load_inference_model(
dirname=FLAGS.model_path,
executor=exe,
model_filename=FLAGS.model_name,
params_filename=FLAGS.params_name)
eval_keys = ['bbox', 'gt_box', 'gt_label', 'is_difficult']
eval_values = [
'multiclass_nms_0.tmp_0', 'gt_box', 'gt_label', 'is_difficult'
]
eval_cls = []
eval_values[0] = fetch_targets[0]
results = eval_run(exe, infer_prog, eval_reader, eval_keys, eval_values,
eval_cls, test_data_feed)
resolution = None
if 'mask' in results[0]:
resolution = model.mask_head.resolution
eval_results(results, eval_feed, cfg.metric, cfg.num_classes, resolution,
False, FLAGS.output_eval)
def getinferdata(image_path):
cfg = load_config('configs/faster_rcnn_r50_1x.yml')
test_feed = create(cfg.test_feed)
test_images = get_test_images(None, image_path)
test_feed.dataset.add_images(test_images)
reader = create_reader(test_feed)
loader, feed_vars = create_feed(test_feed,
iterable=True) #ppdet.modeling.model_input
place = fluid.CPUPlace()
loader.set_sample_list_generator(reader, place)
for iter_id, data in enumerate(loader()):
print(iter_id, data)
print(type(data[0]['im_shape']), type(data[0]['im_id']),
type(data[0]['im_info']), type(data[0]['image']))
print('im_shape', str(data[0]['im_shape']))
print('im_id', str(data[0]['im_id']))
print('im_info', str(data[0]['im_info'])) #
print('image', np.array(data[0]['image']),
np.array(data[0]['image']).shape)
return data
def main():
"""
Main evaluate function
"""
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 cfg.use_gpu:
devices_num = fluid.core.get_cuda_device_count()
else:
devices_num = int(
os.environ.get('CPU_NUM', multiprocessing.cpu_count()))
if 'eval_feed' not in cfg:
eval_feed = create(main_arch + 'EvalFeed')
else:
eval_feed = create(cfg.eval_feed)
# 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():
pyreader, feed_vars = create_feed(eval_feed)
fetches = model.eval(feed_vars)
eval_prog = eval_prog.clone(True)
reader = create_reader(eval_feed, args_path=FLAGS.dataset_dir)
pyreader.decorate_sample_list_generator(reader, place)
# 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(eval_feed,
cfg.metric,
json_directory=FLAGS.output_eval)
return
# compile program for multi-devices
if devices_num <= 1:
compile_program = fluid.compiler.CompiledProgram(eval_prog)
else:
build_strategy = fluid.BuildStrategy()
build_strategy.memory_optimize = False
build_strategy.enable_inplace = False
compile_program = fluid.compiler.CompiledProgram(
eval_prog).with_data_parallel(build_strategy=build_strategy)
# load model
exe.run(startup_prog)
if 'weights' in cfg:
checkpoint.load_pretrain(exe, eval_prog, cfg.weights)
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_box', 'gt_label', '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()
results = eval_run(exe, compile_program, pyreader, keys, values, cls)
# evaluation
resolution = None
if 'mask' in results[0]:
resolution = model.mask_head.resolution
eval_results(results, eval_feed, cfg.metric, cfg.num_classes, resolution,
is_bbox_normalized, FLAGS.output_eval, cfg.map_type)
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)
if 'log_iter' not in cfg:
cfg.log_iter = 20
# check if set use_gpu=True in paddlepaddle cpu version
check_gpu(cfg.use_gpu)
if cfg.use_gpu:
devices_num = fluid.core.get_cuda_device_count()
else:
devices_num = int(
os.environ.get('CPU_NUM', multiprocessing.cpu_count()))
if 'train_feed' not in cfg:
train_feed = create(main_arch + 'TrainFeed')
else:
train_feed = create(cfg.train_feed)
if FLAGS.eval:
if 'eval_feed' not in cfg:
eval_feed = create(main_arch + 'EvalFeed')
else:
eval_feed = create(cfg.eval_feed)
place = fluid.CUDAPlace(0) 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()
with fluid.program_guard(train_prog, startup_prog):
with fluid.unique_name.guard():
model = create(main_arch)
train_pyreader, feed_vars = create_feed(train_feed)
train_fetches = model.train(feed_vars)
loss = train_fetches['loss']
lr = lr_builder()
optimizer = optim_builder(lr)
optimizer.minimize(loss)
train_reader = create_reader(train_feed, cfg.max_iters * devices_num,
FLAGS.dataset_dir)
train_pyreader.decorate_sample_list_generator(train_reader, place)
# 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)
eval_pyreader, feed_vars = create_feed(eval_feed)
fetches = model.eval(feed_vars)
eval_prog = eval_prog.clone(True)
eval_reader = create_reader(eval_feed, args_path=FLAGS.dataset_dir)
eval_pyreader.decorate_sample_list_generator(eval_reader, place)
# parse eval fetches
extra_keys = []
if cfg.metric == 'COCO':
extra_keys = ['im_info', 'im_id', 'im_shape']
if cfg.metric == 'VOC':
extra_keys = ['gt_box', 'gt_label', 'is_difficult']
eval_keys, eval_values, eval_cls = parse_fetches(
fetches, eval_prog, extra_keys)
# compile program for multi-devices
build_strategy = fluid.BuildStrategy()
build_strategy.memory_optimize = False
build_strategy.enable_inplace = False
sync_bn = getattr(model.backbone, 'norm_type', None) == 'sync_bn'
# only enable sync_bn in multi GPU devices
build_strategy.sync_batch_norm = sync_bn and devices_num > 1 \
and cfg.use_gpu
train_compile_program = fluid.compiler.CompiledProgram(
train_prog).with_data_parallel(loss_name=loss.name,
build_strategy=build_strategy)
if FLAGS.eval:
eval_compile_program = fluid.compiler.CompiledProgram(eval_prog)
exe.run(startup_prog)
fuse_bn = getattr(model.backbone, 'norm_type', None) == 'affine_channel'
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:
checkpoint.load_and_fusebn(exe, train_prog, cfg.pretrain_weights)
elif cfg.pretrain_weights:
checkpoint.load_pretrain(exe, train_prog, cfg.pretrain_weights)
# 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()
train_stats = TrainingStats(cfg.log_smooth_window, train_keys)
train_pyreader.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_iter)
best_box_ap_list = [0.0, 0] #[map, iter]
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(train_compile_program, fetch_list=train_values)
stats = {k: np.array(v).mean() for k, v in zip(train_keys, outs[:-1])}
train_stats.update(stats)
logs = train_stats.log()
if it % cfg.log_iter == 0:
strs = 'iter: {}, lr: {:.6f}, {}, time: {:.3f}, eta: {}'.format(
it, np.mean(outs[-1]), logs, time_cost, eta)
logger.info(strs)
if it > 0 and it % cfg.snapshot_iter == 0 or it == cfg.max_iters - 1:
save_name = str(it) if it != cfg.max_iters - 1 else "model_final"
checkpoint.save(exe, train_prog, os.path.join(save_dir, save_name))
if FLAGS.eval:
# evaluation
results = eval_run(exe, eval_compile_program, eval_pyreader,
eval_keys, eval_values, eval_cls)
resolution = None
if 'mask' in results[0]:
resolution = model.mask_head.resolution
box_ap_stats = eval_results(results, eval_feed, cfg.metric,
cfg.num_classes, resolution,
is_bbox_normalized,
FLAGS.output_eval)
if box_ap_stats[0] > best_box_ap_list[0]:
best_box_ap_list[0] = box_ap_stats[0]
best_box_ap_list[1] = it
checkpoint.save(exe, train_prog,
os.path.join(save_dir, "best_model"))
logger.info("Best test box ap: {}, in iter: {}".format(
best_box_ap_list[0], best_box_ap_list[1]))
train_pyreader.reset()
def main():
"""
Main evaluate function
"""
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)
# check if paddlepaddle version is satisfied
check_version()
if 'eval_feed' not in cfg:
eval_feed = create(main_arch + 'EvalFeed')
else:
eval_feed = create(cfg.eval_feed)
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():
loader, feed_vars = create_feed(eval_feed)
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(eval_feed, args_path=FLAGS.dataset_dir)
loader.set_sample_list_generator(reader, place)
# 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(eval_feed,
cfg.metric,
json_directory=FLAGS.output_eval)
return
compile_program = fluid.compiler.CompiledProgram(
eval_prog).with_data_parallel()
# load model
exe.run(startup_prog)
if 'weights' in cfg:
checkpoint.load_params(exe, eval_prog, cfg.weights)
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_box', 'gt_label', '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():
_, feed_vars = create_feed(eval_feed,
False,
sub_prog_feed=True)
sub_fetches = model.eval(feed_vars,
multi_scale_test,
mask_branch=True)
extra_keys = []
if cfg.metric == 'COCO':
extra_keys = ['im_id', 'im_shape']
if cfg.metric == 'VOC':
extra_keys = ['gt_box', 'gt_label', 'is_difficult']
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)
results = eval_run(exe, compile_program, loader, keys, values, cls, cfg,
sub_eval_prog, sub_keys, sub_values)
# evaluation
resolution = None
if 'mask' in results[0]:
resolution = model.mask_head.resolution
# 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'
eval_results(results, eval_feed, cfg.metric, cfg.num_classes, resolution,
is_bbox_normalized, FLAGS.output_eval, map_type)
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)
if 'log_iter' not in cfg:
cfg.log_iter = 20
# check if set use_gpu=True in paddlepaddle cpu version
check_gpu(cfg.use_gpu)
if cfg.use_gpu:
devices_num = fluid.core.get_cuda_device_count()
else:
devices_num = int(
os.environ.get('CPU_NUM', multiprocessing.cpu_count()))
if 'train_feed' not in cfg:
train_feed = create(main_arch + 'TrainFeed')
else:
train_feed = create(cfg.train_feed)
if 'eval_feed' not in cfg:
eval_feed = create(main_arch + 'EvalFeed')
else:
eval_feed = create(cfg.eval_feed)
place = fluid.CUDAPlace(0) 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()
with fluid.program_guard(train_prog, startup_prog):
with fluid.unique_name.guard():
model = create(main_arch)
_, feed_vars = create_feed(train_feed, True)
train_fetches = model.train(feed_vars)
loss = train_fetches['loss']
lr = lr_builder()
optimizer = optim_builder(lr)
optimizer.minimize(loss)
train_reader = create_reader(train_feed, cfg.max_iters, FLAGS.dataset_dir)
# parse train fetches
train_keys, train_values, _ = parse_fetches(train_fetches)
train_keys.append("lr")
train_values.append(lr.name)
train_fetch_list = []
for k, v in zip(train_keys, train_values):
train_fetch_list.append((k, v))
eval_prog = fluid.Program()
with fluid.program_guard(eval_prog, startup_prog):
with fluid.unique_name.guard():
model = create(main_arch)
_, test_feed_vars = create_feed(eval_feed, True)
fetches = model.eval(test_feed_vars)
eval_prog = eval_prog.clone(True)
eval_reader = create_reader(eval_feed, args_path=FLAGS.dataset_dir)
test_data_feed = fluid.DataFeeder(test_feed_vars.values(), place)
# parse eval fetches
extra_keys = []
if cfg.metric == 'COCO':
extra_keys = ['im_info', 'im_id', 'im_shape']
if cfg.metric == 'VOC':
extra_keys = ['gt_box', 'gt_label', 'is_difficult']
eval_keys, eval_values, eval_cls = parse_fetches(fetches, eval_prog,
extra_keys)
eval_fetch_list = []
for k, v in zip(eval_keys, eval_values):
eval_fetch_list.append((k, v))
exe.run(startup_prog)
checkpoint.load_params(exe, train_prog, cfg.pretrain_weights)
best_box_ap_list = []
def eval_func(program, scope):
#place = fluid.CPUPlace()
#exe = fluid.Executor(place)
results = eval_run(exe, program, eval_reader, eval_keys, eval_values,
eval_cls, test_data_feed)
resolution = None
if 'mask' in results[0]:
resolution = model.mask_head.resolution
box_ap_stats = eval_results(results, eval_feed, cfg.metric,
cfg.num_classes, resolution, False,
FLAGS.output_eval)
if len(best_box_ap_list) == 0:
best_box_ap_list.append(box_ap_stats[0])
elif box_ap_stats[0] > best_box_ap_list[0]:
best_box_ap_list[0] = box_ap_stats[0]
logger.info("Best test box ap: {}".format(best_box_ap_list[0]))
return best_box_ap_list[0]
test_feed = [('image', test_feed_vars['image'].name),
('im_size', test_feed_vars['im_size'].name)]
com = Compressor(
place,
fluid.global_scope(),
train_prog,
train_reader=train_reader,
train_feed_list=[(key, value.name) for key, value in feed_vars.items()],
train_fetch_list=train_fetch_list,
eval_program=eval_prog,
eval_reader=eval_reader,
eval_feed_list=test_feed,
eval_func={'map': eval_func},
eval_fetch_list=[eval_fetch_list[0]],
save_eval_model=True,
prune_infer_model=[["image", "im_size"], ["multiclass_nms_0.tmp_0"]],
train_optimizer=None)
com.config(FLAGS.slim_file)
com.run()
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)
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)
# check if paddlepaddle version is satisfied
check_version()
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():
loader, feed_vars = create_feed(test_feed, iterable=True)
test_fetches = model.test(feed_vars)
infer_prog = infer_prog.clone(True)
reader = create_reader(test_feed)
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 = 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()
# 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
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)
if 'log_iter' not in cfg:
cfg.log_iter = 20
# check if set use_gpu=True in paddlepaddle cpu version
check_gpu(cfg.use_gpu)
if cfg.use_gpu:
devices_num = fluid.core.get_cuda_device_count()
else:
devices_num = int(
os.environ.get('CPU_NUM', multiprocessing.cpu_count()))
if 'train_feed' not in cfg:
train_feed = create(main_arch + 'TrainFeed')
else:
train_feed = create(cfg.train_feed)
if 'eval_feed' not in cfg:
eval_feed = create(main_arch + 'EvalFeed')
else:
eval_feed = create(cfg.eval_feed)
place = fluid.CUDAPlace(0) if cfg.use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
lr_builder = create('LearningRate')
optim_builder = create('OptimizerBuilder')
# build program
model = create(main_arch)
_, train_feed_vars = create_feed(train_feed, True)
train_fetches = model.train(train_feed_vars)
loss = train_fetches['loss']
lr = lr_builder()
opt = optim_builder(lr)
opt.minimize(loss)
#for v in fluid.default_main_program().list_vars():
# if "py_reader" not in v.name and "double_buffer" not in v.name and "generated_var" not in v.name:
# print(v.name, v.shape)
cfg.max_iters = 258
train_reader = create_reader(train_feed, cfg.max_iters, FLAGS.dataset_dir)
exe.run(fluid.default_startup_program())
# parse train fetches
train_keys, train_values, _ = parse_fetches(train_fetches)
train_keys.append('lr')
train_values.append(lr.name)
train_fetch_list = []
for k, v in zip(train_keys, train_values):
train_fetch_list.append((k, v))
print("train_fetch_list: {}".format(train_fetch_list))
eval_prog = fluid.Program()
startup_prog = fluid.Program()
with fluid.program_guard(eval_prog, startup_prog):
with fluid.unique_name.guard():
model = create(main_arch)
_, test_feed_vars = create_feed(eval_feed, True)
fetches = model.eval(test_feed_vars)
eval_prog = eval_prog.clone(True)
eval_reader = create_reader(eval_feed, args_path=FLAGS.dataset_dir)
test_data_feed = fluid.DataFeeder(test_feed_vars.values(), place)
# parse eval fetches
extra_keys = []
if cfg.metric == 'COCO':
extra_keys = ['im_info', 'im_id', 'im_shape']
if cfg.metric == 'VOC':
extra_keys = ['gt_box', 'gt_label', 'is_difficult']
eval_keys, eval_values, eval_cls = parse_fetches(fetches, eval_prog,
extra_keys)
eval_fetch_list = []
for k, v in zip(eval_keys, eval_values):
eval_fetch_list.append((k, v))
print("eval_fetch_list: {}".format(eval_fetch_list))
exe.run(startup_prog)
checkpoint.load_params(exe,
fluid.default_main_program(), cfg.pretrain_weights)
best_box_ap_list = []
def eval_func(program, scope):
results = eval_run(exe, program, eval_reader, eval_keys, eval_values,
eval_cls, test_data_feed)
resolution = None
is_bbox_normalized = False
if 'mask' in results[0]:
resolution = model.mask_head.resolution
box_ap_stats = eval_results(results, eval_feed, cfg.metric,
cfg.num_classes, resolution,
is_bbox_normalized, FLAGS.output_eval)
if len(best_box_ap_list) == 0:
best_box_ap_list.append(box_ap_stats[0])
elif box_ap_stats[0] > best_box_ap_list[0]:
best_box_ap_list[0] = box_ap_stats[0]
logger.info("Best test box ap: {}".format(best_box_ap_list[0]))
return best_box_ap_list[0]
test_feed = [('image', test_feed_vars['image'].name),
('im_size', test_feed_vars['im_size'].name)]
teacher_cfg = load_config(FLAGS.teacher_config)
teacher_arch = teacher_cfg.architecture
teacher_programs = []
teacher_program = fluid.Program()
teacher_startup_program = fluid.Program()
with fluid.program_guard(teacher_program, teacher_startup_program):
with fluid.unique_name.guard('teacher_'):
teacher_feed_vars = OrderedDict()
for name, var in train_feed_vars.items():
teacher_feed_vars[name] = teacher_program.global_block(
)._clone_variable(
var, force_persistable=False)
model = create(teacher_arch)
train_fetches = model.train(teacher_feed_vars)
#print("="*50+"teacher_model_params"+"="*50)
#for v in teacher_program.list_vars():
# print(v.name, v.shape)
#return
exe.run(teacher_startup_program)
assert FLAGS.teacher_pretrained and os.path.exists(
FLAGS.teacher_pretrained
), "teacher_pretrained should be set when teacher_model is not None."
def if_exist(var):
return os.path.exists(os.path.join(FLAGS.teacher_pretrained, var.name))
fluid.io.load_vars(
exe,
FLAGS.teacher_pretrained,
main_program=teacher_program,
predicate=if_exist)
teacher_programs.append(teacher_program.clone(for_test=True))
com = Compressor(
place,
fluid.global_scope(),
fluid.default_main_program(),
train_reader=train_reader,
train_feed_list=[(key, value.name)
for key, value in train_feed_vars.items()],
train_fetch_list=train_fetch_list,
eval_program=eval_prog,
eval_reader=eval_reader,
eval_feed_list=test_feed,
eval_func={'map': eval_func},
eval_fetch_list=eval_fetch_list[0:1],
save_eval_model=True,
prune_infer_model=[["image", "im_size"], ["multiclass_nms_0.tmp_0"]],
teacher_programs=teacher_programs,
train_optimizer=None,
distiller_optimizer=opt,
log_period=20)
com.config(FLAGS.slim_file)
com.run()
def main():
env = os.environ
FLAGS.dist = 'PADDLE_TRAINER_ID' in env and 'PADDLE_TRAINERS_NUM' in env
if FLAGS.dist:
trainer_id = int(env['PADDLE_TRAINER_ID'])
import random
local_seed = (99 + trainer_id)
random.seed(local_seed)
np.random.seed(local_seed)
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)
if 'log_iter' not in cfg:
cfg.log_iter = 20
# check if set use_gpu=True in paddlepaddle cpu version
check_gpu(cfg.use_gpu)
if not FLAGS.dist or trainer_id == 0:
print_total_cfg(cfg)
if cfg.use_gpu:
devices_num = fluid.core.get_cuda_device_count()
else:
devices_num = int(os.environ.get('CPU_NUM', 1))
if 'train_feed' not in cfg:
train_feed = create(main_arch + 'TrainFeed')
else:
train_feed = create(cfg.train_feed)
if FLAGS.eval:
if 'eval_feed' not in cfg:
eval_feed = create(main_arch + 'EvalFeed')
else:
eval_feed = create(cfg.eval_feed)
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()
with fluid.program_guard(train_prog, startup_prog):
with fluid.unique_name.guard():
model = create(main_arch)
train_pyreader, feed_vars = create_feed(train_feed)
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:
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()
# 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)
eval_pyreader, feed_vars = create_feed(eval_feed)
fetches = model.eval(feed_vars)
eval_prog = eval_prog.clone(True)
eval_reader = create_reader(eval_feed, args_path=FLAGS.dataset_dir)
eval_pyreader.decorate_sample_list_generator(eval_reader, place)
# parse eval fetches
extra_keys = []
if cfg.metric == 'COCO':
extra_keys = ['im_info', 'im_id', 'im_shape']
if cfg.metric == 'VOC':
extra_keys = ['gt_box', 'gt_label', 'is_difficult']
if cfg.metric == 'WIDERFACE':
extra_keys = ['im_id', 'im_shape', 'gt_box']
eval_keys, eval_values, eval_cls = parse_fetches(
fetches, eval_prog, extra_keys)
# compile program for multi-devices
build_strategy = fluid.BuildStrategy()
build_strategy.fuse_all_optimizer_ops = False
build_strategy.fuse_elewise_add_act_ops = True
# 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.compiler.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(train_feed,
(cfg.max_iters - start_iter) * devices_num,
FLAGS.dataset_dir)
train_pyreader.decorate_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_pyreader.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]
# use tb-paddle to log data
if FLAGS.use_tb:
from tb_paddle import SummaryWriter
tb_writer = SummaryWriter(FLAGS.tb_log_dir)
tb_loss_step = 0
tb_mAP_step = 0
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 tb-paddle to log loss
if FLAGS.use_tb:
if it % cfg.log_iter == 0:
for loss_name, loss_value in stats.items():
tb_writer.add_scalar(loss_name, loss_value, tb_loss_step)
tb_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)
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"
checkpoint.save(exe, train_prog, os.path.join(save_dir, save_name))
if FLAGS.eval:
# evaluation
results = eval_run(exe, compiled_eval_prog, eval_pyreader,
eval_keys, eval_values, eval_cls)
resolution = None
if 'mask' in results[0]:
resolution = model.mask_head.resolution
box_ap_stats = eval_results(results, eval_feed, cfg.metric,
cfg.num_classes, resolution,
is_bbox_normalized,
FLAGS.output_eval, map_type)
# use tb_paddle to log mAP
if FLAGS.use_tb:
tb_writer.add_scalar("mAP", box_ap_stats[0], tb_mAP_step)
tb_mAP_step += 1
if box_ap_stats[0] > best_box_ap_list[0]:
best_box_ap_list[0] = box_ap_stats[0]
best_box_ap_list[1] = it
checkpoint.save(exe, train_prog,
os.path.join(save_dir, "best_model"))
logger.info("Best test box ap: {}, in iter: {}".format(
best_box_ap_list[0], best_box_ap_list[1]))
train_pyreader.reset()
def main():
"""
Main evaluate function
"""
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 cfg.use_gpu:
devices_num = fluid.core.get_cuda_device_count()
else:
devices_num = int(
os.environ.get('CPU_NUM', multiprocessing.cpu_count()))
if 'eval_feed' not in cfg:
eval_feed = create(main_arch + 'EvalFeed')
else:
eval_feed = create(cfg.eval_feed)
# 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():
pyreader, feed_vars = create_feed(eval_feed)
fetches = model.eval(feed_vars)
eval_prog = eval_prog.clone(True)
reader = create_reader(eval_feed)
pyreader.decorate_sample_list_generator(reader, place)
# compile program for multi-devices
if devices_num <= 1:
compile_program = fluid.compiler.CompiledProgram(eval_prog)
else:
build_strategy = fluid.BuildStrategy()
build_strategy.memory_optimize = False
build_strategy.enable_inplace = False
compile_program = fluid.compiler.CompiledProgram(
eval_prog).with_data_parallel(build_strategy=build_strategy)
# load model
exe.run(startup_prog)
if 'weights' in cfg:
checkpoint.load_pretrain(exe, eval_prog, cfg.weights)
extra_keys = []
if 'metric' in cfg and cfg.metric == 'COCO':
extra_keys = ['im_info', 'im_id', 'im_shape']
keys, values, cls = parse_fetches(fetches, eval_prog, extra_keys)
results = eval_run(exe, compile_program, pyreader, keys, values, cls)
# evaluation
resolution = None
if 'mask' in results[0]:
resolution = model.mask_head.resolution
eval_results(results, eval_feed, cfg.metric, resolution, FLAGS.output_file)
def test_train(self):
train_feed = create(self.cfg['train_feed'])
model = create(self.detector_type)
_, feed_vars = create_feed(train_feed)
train_fetches = model.train(feed_vars)
def test_test(self):
test_feed = create(self.cfg['eval_feed'])
model = create(self.detector_type)
_, feed_vars = create_feed(test_feed)
test_fetches = model.eval(feed_vars)
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)
if 'log_iter' not in cfg:
cfg.log_iter = 20
# check if set use_gpu=True in paddlepaddle cpu version
check_gpu(cfg.use_gpu)
if cfg.use_gpu:
devices_num = fluid.core.get_cuda_device_count()
else:
devices_num = int(
os.environ.get('CPU_NUM', multiprocessing.cpu_count()))
if 'eval_feed' not in cfg:
eval_feed = create(main_arch + 'EvalFeed')
else:
eval_feed = create(cfg.eval_feed)
place = fluid.CUDAPlace(0) if cfg.use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
_, test_feed_vars = create_feed(eval_feed, False)
eval_reader = create_reader(eval_feed, args_path=FLAGS.dataset_dir)
#eval_pyreader.decorate_sample_list_generator(eval_reader, place)
test_data_feed = fluid.DataFeeder(test_feed_vars.values(), place)
assert os.path.exists(FLAGS.model_path)
infer_prog, feed_names, fetch_targets = fluid.io.load_inference_model(
dirname=FLAGS.model_path,
executor=exe,
model_filename='__model__.infer',
params_filename='__params__')
eval_keys = ['bbox', 'gt_box', 'gt_label', 'is_difficult']
eval_values = [
'multiclass_nms_0.tmp_0', 'gt_box', 'gt_label', 'is_difficult'
]
eval_cls = []
eval_values[0] = fetch_targets[0]
results = eval_run(exe, infer_prog, eval_reader, eval_keys, eval_values,
eval_cls, test_data_feed)
resolution = None
if 'mask' in results[0]:
resolution = model.mask_head.resolution
box_ap_stats = eval_results(results, eval_feed, cfg.metric,
cfg.num_classes, resolution, False,
FLAGS.output_eval)
logger.info("freeze the graph for inference")
test_graph = IrGraph(core.Graph(infer_prog.desc), for_test=True)
freeze_pass = QuantizationFreezePass(
scope=fluid.global_scope(),
place=place,
weight_quantize_type=FLAGS.weight_quant_type)
freeze_pass.apply(test_graph)
server_program = test_graph.to_program()
fluid.io.save_inference_model(dirname=os.path.join(FLAGS.save_path,
'float'),
feeded_var_names=feed_names,
target_vars=fetch_targets,
executor=exe,
main_program=server_program,
model_filename='model',
params_filename='weights')
logger.info("convert the weights into int8 type")
convert_int8_pass = ConvertToInt8Pass(scope=fluid.global_scope(),
place=place)
convert_int8_pass.apply(test_graph)
server_int8_program = test_graph.to_program()
fluid.io.save_inference_model(dirname=os.path.join(FLAGS.save_path,
'int8'),
feeded_var_names=feed_names,
target_vars=fetch_targets,
executor=exe,
main_program=server_int8_program,
model_filename='model',
params_filename='weights')
