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)
# 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)