def multi_gpu_eval_net_on_dataset(model, args, dataset_name, proposal_file,
num_images, output_dir, include_feat):
"""Multi-gpu inference on a dataset."""
binary_dir = envu.get_runtime_dir()
binary_ext = envu.get_py_bin_ext()
binary = os.path.join(binary_dir, args.test_net_file + binary_ext)
assert os.path.exists(binary), 'Binary \'{}\' not found'.format(binary)
# Pass the target dataset and proposal file (if any) via the command line
opts = ['TEST.DATASETS', '("{}",)'.format(dataset_name)]
if proposal_file:
opts += ['TEST.PROPOSAL_FILES', '("{}",)'.format(proposal_file)]
if args.do_val:
opts += ['--do_val']
if args.use_gt_boxes:
opts += ['--use_gt_boxes']
if args.use_gt_labels:
opts += ['--use_gt_labels']
# Run inference in parallel in subprocesses
# Outputs will be a list of outputs from each subprocess, where the output
# of each subprocess is the dictionary saved by test_net().
outputs = subprocess_utils.process_in_parallel('rel_detection', num_images,
binary, output_dir,
args.load_ckpt,
args.load_detectron, opts)
# Collate the results from each subprocess
all_results = []
for det_data in outputs:
all_results += det_data
return all_results
def multi_gpu_test_retinanet_on_dataset(num_images, output_dir, dataset):
"""
If doing multi-gpu testing, we need to divide the data on various gpus and
make the subprocess call for each child process that'll run test_retinanet()
on its subset data. After all the subprocesses finish, we combine the results
and return
"""
# Retrieve the test_net binary path
binary_dir = envu.get_runtime_dir()
binary_ext = envu.get_py_bin_ext()
binary = os.path.join(binary_dir, 'test_net' + binary_ext)
assert os.path.exists(binary), 'Binary \'{}\' not found'.format(binary)
# Run inference in parallel in subprocesses
outputs = subprocess_utils.process_in_parallel('detection', num_images,
binary, output_dir)
# Combine the results from each subprocess
all_boxes = [[] for _ in range(cfg.MODEL.NUM_CLASSES)]
for det_data in outputs:
all_boxes_batch = det_data['all_boxes']
for cls_idx in range(1, cfg.MODEL.NUM_CLASSES):
all_boxes[cls_idx] += all_boxes_batch[cls_idx]
# Save the computed detections
det_file = os.path.join(output_dir, 'detections.pkl')
cfg_yaml = yaml.dump(cfg)
save_object(dict(all_boxes=all_boxes, cfg=cfg_yaml), det_file)
logger.info('Wrote detections to: {}'.format(os.path.abspath(det_file)))
return all_boxes
def multi_gpu_generate_rpn_on_dataset(weights_file, dataset_name,
_proposal_file_ignored, num_images,
output_dir):
"""Multi-gpu inference on a dataset."""
# Retrieve the test_net binary path
binary_dir = envu.get_runtime_dir()
binary_ext = envu.get_py_bin_ext()
binary = os.path.join(binary_dir, 'test_net' + binary_ext)
assert os.path.exists(binary), 'Binary \'{}\' not found'.format(binary)
# Pass the target dataset via the command line
opts = ['TEST.DATASETS', '("{}",)'.format(dataset_name)]
opts += ['TEST.WEIGHTS', weights_file]
# Run inference in parallel in subprocesses
outputs = subprocess_utils.process_in_parallel('rpn_proposals', num_images,
binary, output_dir, opts)
# Collate the results from each subprocess
boxes, scores, ids = [], [], []
for rpn_data in outputs:
boxes += rpn_data['boxes']
scores += rpn_data['scores']
ids += rpn_data['ids']
rpn_file = os.path.join(output_dir, 'rpn_proposals.pkl')
cfg_yaml = yaml.dump(cfg)
save_object(dict(boxes=boxes, scores=scores, ids=ids, cfg=cfg_yaml),
rpn_file)
logger.info('Wrote RPN proposals to {}'.format(os.path.abspath(rpn_file)))
return boxes, scores, ids, rpn_file
def multi_gpu_test_net_on_dataset(num_images, output_dir):
"""Multi-gpu inference on a dataset."""
binary_dir = envu.get_runtime_dir()
binary_ext = envu.get_py_bin_ext()
binary = os.path.join(binary_dir, 'test_net' + binary_ext)
assert os.path.exists(binary), 'Binary \'{}\' not found'.format(binary)
# Run inference in parallel in subprocesses
# Outputs will be a list of outputs from each subprocess, where the output
# of each subprocess is the dictionary saved by test_net().
outputs = subprocess_utils.process_in_parallel('detection', num_images,
binary, output_dir)
# Collate the results from each subprocess
all_boxes = [[] for _ in range(cfg.MODEL.NUM_CLASSES)]
all_segms = [[] for _ in range(cfg.MODEL.NUM_CLASSES)]
all_keyps = [[] for _ in range(cfg.MODEL.NUM_CLASSES)]
for det_data in outputs:
all_boxes_batch = det_data['all_boxes']
all_segms_batch = det_data['all_segms']
all_keyps_batch = det_data['all_keyps']
for cls_idx in range(1, cfg.MODEL.NUM_CLASSES):
all_boxes[cls_idx] += all_boxes_batch[cls_idx]
all_segms[cls_idx] += all_segms_batch[cls_idx]
all_keyps[cls_idx] += all_keyps_batch[cls_idx]
det_file = os.path.join(output_dir, 'detections.pkl')
cfg_yaml = yaml.dump(cfg)
save_object(
dict(all_boxes=all_boxes,
all_segms=all_segms,
all_keyps=all_keyps,
cfg=cfg_yaml), det_file)
logger.info('Wrote detections to: {}'.format(os.path.abspath(det_file)))
return all_boxes, all_segms, all_keyps
def multi_gpu_test_retinanet_on_dataset(num_images, output_dir, dataset):
"""
If doing multi-gpu testing, we need to divide the data on various gpus and
make the subprocess call for each child process that'll run test_retinanet()
on its subset data. After all the subprocesses finish, we combine the results
and return
"""
# Retrieve the test_net binary path
binary_dir = envu.get_runtime_dir()
binary_ext = envu.get_py_bin_ext()
binary = os.path.join(binary_dir, 'test_net' + binary_ext)
assert os.path.exists(binary), 'Binary \'{}\' not found'.format(binary)
# Run inference in parallel in subprocesses
outputs = subprocess_utils.process_in_parallel(
'retinanet_detections', num_images, binary, output_dir)
# Combine the results from each subprocess now
boxes, scores, classes, image_ids = [], [], [], []
for det_data in outputs:
boxes.extend(det_data['boxes'])
scores.extend(det_data['scores'])
classes.extend(det_data['classes'])
image_ids.extend(det_data['ids'])
return boxes, scores, classes, image_ids,
def multi_gpu_generate_rpn_on_dataset(num_images, output_dir):
"""Multi-gpu inference on a dataset."""
# Retrieve the test_net binary path
binary_dir = envu.get_runtime_dir()
binary_ext = envu.get_py_bin_ext()
binary = os.path.join(binary_dir, 'test_net' + binary_ext)
assert os.path.exists(binary), 'Binary \'{}\' not found'.format(binary)
# Run inference in parallel in subprocesses
outputs = subprocess_utils.process_in_parallel(
'rpn_proposals', num_images, binary, output_dir
)
# Collate the results from each subprocess
boxes, scores, ids = [], [], []
for rpn_data in outputs:
boxes += rpn_data['boxes']
scores += rpn_data['scores']
ids += rpn_data['ids']
rpn_file = os.path.join(output_dir, 'rpn_proposals.pkl')
cfg_yaml = yaml.dump(cfg)
save_object(
dict(boxes=boxes, scores=scores, ids=ids, cfg=cfg_yaml), rpn_file
)
logger.info('Wrote RPN proposals to {}'.format(os.path.abspath(rpn_file)))
return boxes, scores, ids, rpn_file
def multi_gpu_test_net_on_dataset(
weights_file, dataset_name, proposal_file, num_images, output_dir
):
"""Multi-gpu inference on a dataset."""
binary_dir = envu.get_runtime_dir()
binary_ext = envu.get_py_bin_ext()
binary = os.path.join(binary_dir, 'test_net' + binary_ext)
assert os.path.exists(binary), 'Binary \'{}\' not found'.format(binary)
# Run inference in parallel in subprocesses
# Outputs will be a list of outputs from each subprocess, where the output
# of each subprocess is the dictionary saved by test_net().
outputs = subprocess_utils.process_in_parallel(cfg.CFG_FILE, num_images, binary, output_dir, weights_file)
# Collate the results from each subprocess
all_scores = []
for det_data in outputs:
all_scores_batch = det_data['all_scores']
all_scores += all_scores_batch
det_file = os.path.join(output_dir, 'detections.pkl')
cfg_yaml = yaml.dump(cfg)
save_object(
dict(
all_scores=all_scores,
cfg=cfg_yaml
), det_file
)
logger.info('Wrote detections to: {}'.format(os.path.abspath(det_file)))
return all_scores
def multi_gpu_test_retinanet_on_dataset(num_images, output_dir, dataset):
"""
If doing multi-gpu testing, we need to divide the data on various gpus and
make the subprocess call for each child process that'll run test_retinanet()
on its subset data. After all the subprocesses finish, we combine the results
and return
"""
# Retrieve the test_net binary path
binary_dir = envu.get_runtime_dir()
binary_ext = envu.get_py_bin_ext()
binary = os.path.join(binary_dir, 'test_net' + binary_ext)
assert os.path.exists(binary), 'Binary \'{}\' not found'.format(binary)
# Run inference in parallel in subprocesses
outputs = subprocess_utils.process_in_parallel('retinanet_detections',
num_images, binary,
output_dir)
# Combine the results from each subprocess now
boxes, scores, classes, image_ids = [], [], [], []
for det_data in outputs:
boxes.extend(det_data['boxes'])
scores.extend(det_data['scores'])
classes.extend(det_data['classes'])
image_ids.extend(det_data['ids'])
return boxes, scores, classes, image_ids,
def multi_gpu_test_net_on_dataset(args, dataset_name, proposal_file,
num_images, output_dir):
"""Multi-gpu inference on a dataset."""
binary_dir = envu.get_runtime_dir()
binary_ext = envu.get_py_bin_ext()
binary = os.path.join(binary_dir, args.test_net_file + binary_ext)
assert os.path.exists(binary), 'Binary \'{}\' not found'.format(binary)
# Pass the target dataset and proposal file (if any) via the command line
opts = ['TEST.DATASETS', '("{}",)'.format(dataset_name)]
if proposal_file:
opts += ['TEST.PROPOSAL_FILES', '("{}",)'.format(proposal_file)]
OVERWRITE = True
if OVERWRITE:
# Run inference in parallel in subprocesses. Outputs will be a list of outputs from each subprocess,
# where the output of each subprocess is the dictionary saved by test_net().
outputs = subprocess_utils.process_in_parallel( # call 'test_net', see below
'detection', num_images, binary, output_dir, args.load_ckpt,
args.load_detectron, opts)
else:
if '_part' in dataset_name:
pkl_file = 'detections_part.pkl'
else:
pkl_file = 'detections.pkl'
outputs = []
with open(os.path.join(output_dir, pkl_file), 'rb') as f:
outputs.append(pickle.load(f))
# Collate the results from each subprocess
all_boxes = [[] for _ in range(cfg.MODEL.NUM_CLASSES)]
all_segms = [[] for _ in range(cfg.MODEL.NUM_CLASSES)]
all_keyps = [[] for _ in range(cfg.MODEL.NUM_CLASSES)]
for det_data in outputs:
all_boxes_batch = det_data['all_boxes']
all_segms_batch = det_data['all_segms']
all_keyps_batch = det_data['all_keyps']
for cls_idx in range(
1, cfg.MODEL.NUM_CLASSES): # exclude 'background' class here
all_boxes[cls_idx] += all_boxes_batch[cls_idx]
all_segms[cls_idx] += all_segms_batch[cls_idx]
all_keyps[cls_idx] += all_keyps_batch[cls_idx]
if OVERWRITE:
if '_part' in dataset_name:
det_file = os.path.join(output_dir, 'detections_part.pkl')
else:
det_file = os.path.join(output_dir, 'detections.pkl')
cfg_yaml = yaml.dump(cfg)
save_object(
dict(all_boxes=all_boxes,
all_segms=all_segms,
all_keyps=all_keyps,
cfg=cfg_yaml), det_file)
logger.info('Wrote detections to: {}'.format(
os.path.abspath(det_file)))
return all_boxes, all_segms, all_keyps
def multi_gpu_test_net_on_dataset(args, dataset_name, proposal_file,
num_images, output_dir):
"""Multi-gpu inference on a dataset."""
binary_dir = envu.get_runtime_dir()
binary_ext = envu.get_py_bin_ext()
binary = os.path.join(binary_dir, args.test_net_file + binary_ext)
assert os.path.exists(binary), 'Binary \'{}\' not found'.format(binary)
# Pass the target dataset and proposal file (if any) via the command line
opts = ['TEST.DATASETS', '("{}",)'.format(dataset_name)]
if proposal_file:
opts += ['TEST.PROPOSAL_FILES', '("{}",)'.format(proposal_file)]
# Run inference in parallel in subprocesses
# Outputs will be a list of outputs from each subprocess, where the output
# of each subprocess is the dictionary saved by test_net().
outputs = subprocess_utils.process_in_parallel(
'detection', num_images, binary, output_dir, args.load_ckpt,
args.load_detectron, args.net_name, args.mlp_head_dim,
args.heatmap_kernel_size, args.part_crop_size, args.use_kps17, opts)
# Collate the results from each subprocess
all_boxes = [[] for _ in range(cfg.MODEL.NUM_CLASSES)]
all_segms = [[] for _ in range(cfg.MODEL.NUM_CLASSES)]
all_keyps = [[] for _ in range(cfg.MODEL.NUM_CLASSES)]
all_hois = {}
all_losses = defaultdict(list)
all_keyps_vcoco = [[] for _ in range(cfg.MODEL.NUM_CLASSES)]
for det_data in outputs:
all_boxes_batch = det_data['all_boxes']
all_segms_batch = det_data['all_segms']
all_keyps_batch = det_data['all_keyps']
all_hois = {**all_hois, **det_data['all_hois']}
for k, v in det_data['all_losses'].items():
all_losses[k].extend(v)
all_keyps_vcoco_batch = det_data['all_keyps_vcoco']
for cls_idx in range(1, cfg.MODEL.NUM_CLASSES):
all_boxes[cls_idx] += all_boxes_batch[cls_idx]
all_segms[cls_idx] += all_segms_batch[cls_idx]
all_keyps[cls_idx] += all_keyps_batch[cls_idx]
all_keyps_vcoco[cls_idx] += all_keyps_vcoco_batch[cls_idx]
det_file = os.path.join(output_dir, 'detections.pkl')
cfg_yaml = yaml.dump(cfg)
save_object(
dict(all_boxes=all_boxes,
all_segms=all_segms,
all_keyps=all_keyps,
all_hois=all_hois,
all_keyps_vcoco=all_keyps_vcoco,
all_losses=all_losses,
cfg=cfg_yaml), det_file)
logger.info('Wrote detections to: {}'.format(os.path.abspath(det_file)))
return all_boxes, all_segms, all_keyps, all_hois, all_keyps_vcoco, all_losses
def multi_gpu_test_net_on_dataset(args, num_images):
"""Multi-gpu inference on a dataset."""
binary_dir = envu.get_runtime_dir()
binary_ext = envu.get_py_bin_ext()
binary = os.path.join(binary_dir, args.test_net_file + binary_ext)
assert os.path.exists(binary), 'Binary \'{}\' not found'.format(binary)
# Run inference in parallel in subprocesses
# Outputs will be a list of outputs from each subprocess, where the output
# of each subprocess is the dictionary saved by test_net().
subprocess_utils.process_in_parallel_wad(args, num_images, binary)
def multi_gpu_test_net_on_dataset(
weights_file, dataset_name, proposal_file, num_images, output_dir
):
"""Multi-gpu inference on a dataset."""
binary_dir = envu.get_runtime_dir()
binary_ext = envu.get_py_bin_ext()
binary = os.path.join(binary_dir, 'test_net' + binary_ext)
if not os.path.exists(binary):
binary = os.path.join(binary_dir, 'tools/test_net' + binary_ext)
assert os.path.exists(binary), 'Binary \'{}\' not found'.format(binary)
# Pass the target dataset and proposal file (if any) via the command line
opts = ['TEST.DATASETS', '("{}",)'.format(dataset_name)]
opts += ['TEST.WEIGHTS', weights_file]
if proposal_file:
opts += ['TEST.PROPOSAL_FILES', '("{}",)'.format(proposal_file)]
# Run inference in parallel in subprocesses
# Outputs will be a list of outputs from each subprocess, where the output
# of each subprocess is the dictionary saved by test_net().
outputs = subprocess_utils.process_in_parallel(
'detection', num_images, binary, output_dir, opts
)
# Collate the results from each subprocess
all_boxes = [[] for _ in range(cfg.MODEL.NUM_CLASSES)]
all_segms = [[] for _ in range(cfg.MODEL.NUM_CLASSES)]
all_keyps = [[] for _ in range(cfg.MODEL.NUM_CLASSES)]
for det_data in outputs:
all_boxes_batch = det_data['all_boxes']
all_segms_batch = det_data['all_segms']
all_keyps_batch = det_data['all_keyps']
for cls_idx in range(1, cfg.MODEL.NUM_CLASSES):
all_boxes[cls_idx] += all_boxes_batch[cls_idx]
all_segms[cls_idx] += all_segms_batch[cls_idx]
all_keyps[cls_idx] += all_keyps_batch[cls_idx]
det_file = os.path.join(output_dir, 'detections.pkl')
cfg_yaml = yaml.dump(cfg)
save_object(
dict(
all_boxes=all_boxes,
all_segms=all_segms,
all_keyps=all_keyps,
cfg=cfg_yaml
), det_file
)
logger.info('Wrote detections to: {}'.format(os.path.abspath(det_file)))
return all_boxes, all_segms, all_keyps
def multi_gpu_test_net_on_dataset(args, dataset_name, proposal_file,
num_images, output_dir):
"""Multi-gpu inference on a dataset."""
'''This function just allocate the processes, it doesn't contain any thing on core algorithm'''
binary_dir = envu.get_runtime_dir()
binary_ext = envu.get_py_bin_ext()
binary = os.path.join(binary_dir, args.test_net_file + binary_ext)
assert os.path.exists(binary), 'Binary \'{}\' not found'.format(binary)
# Pass the target dataset and proposal file (if any) via the command line
opts = ['TEST.DATASETS', '("{}",)'.format(dataset_name)]
if proposal_file:
opts += ['TEST.PROPOSAL_FILES', '("{}",)'.format(proposal_file)]
# Run inference in parallel in subprocesses
# Outputs will be a list of outputs from each subprocess, where the output
# of each subprocess is the dictionary saved by test_net().
outputs = subprocess_utils.process_in_parallel('detection', num_images,
binary, output_dir,
args.load_ckpt,
args.load_detectron, opts)
# Collate the results from each subprocess
all_boxes = [[] for _ in range(cfg.MODEL.NUM_CLASSES)]
all_segms = [[] for _ in range(cfg.MODEL.NUM_CLASSES)]
all_keyps = [[] for _ in range(cfg.MODEL.NUM_CLASSES)]
for det_data in outputs:
'''
pickle files are used to pass the output, I think it's not merely log file,
instead, it keeps the whole hierachy, and thus output results can directly be gained
'''
all_boxes_batch = det_data['all_boxes']
all_segms_batch = det_data['all_segms']
all_keyps_batch = det_data['all_keyps']
for cls_idx in range(1, cfg.MODEL.NUM_CLASSES):
all_boxes[cls_idx] += all_boxes_batch[cls_idx]
all_segms[cls_idx] += all_segms_batch[cls_idx]
all_keyps[cls_idx] += all_keyps_batch[cls_idx]
det_file = os.path.join(output_dir, 'detections.pkl')
cfg_yaml = yaml.dump(cfg)
save_object(
dict(all_boxes=all_boxes,
all_segms=all_segms,
all_keyps=all_keyps,
cfg=cfg_yaml), det_file)
'''wrote to the pkl file'''
logger.info('Wrote detections to: {}'.format(os.path.abspath(det_file)))
return all_boxes, all_segms, all_keyps
def multi_gpu_test_net_on_dataset(
weights_file, dataset_name, proposal_file, num_images, output_dir
):
"""Multi-gpu inference on a dataset."""
binary_dir = envu.get_runtime_dir()
binary_ext = envu.get_py_bin_ext()
binary = os.path.join(binary_dir, 'test_net' + binary_ext)
assert os.path.exists(binary), 'Binary \'{}\' not found'.format(binary)
# Pass the target dataset and proposal file (if any) via the command line
opts = ['TEST.DATASETS', '("{}",)'.format(dataset_name)]
opts += ['TEST.WEIGHTS', weights_file]
if proposal_file:
opts += ['TEST.PROPOSAL_FILES', '("{}",)'.format(proposal_file)]
# Run inference in parallel in subprocesses
# Outputs will be a list of outputs from each subprocess, where the output
# of each subprocess is the dictionary saved by test_net().
outputs = subprocess_utils.process_in_parallel(
'detection', num_images, binary, output_dir, opts
)
# Collate the results from each subprocess
all_boxes = [[] for _ in range(cfg.MODEL.NUM_CLASSES)]
all_segms = [[] for _ in range(cfg.MODEL.NUM_CLASSES)]
all_keyps = [[] for _ in range(cfg.MODEL.NUM_CLASSES)]
for det_data in outputs:
all_boxes_batch = det_data['all_boxes']
all_segms_batch = det_data['all_segms']
all_keyps_batch = det_data['all_keyps']
for cls_idx in range(1, cfg.MODEL.NUM_CLASSES):
all_boxes[cls_idx] += all_boxes_batch[cls_idx]
all_segms[cls_idx] += all_segms_batch[cls_idx]
all_keyps[cls_idx] += all_keyps_batch[cls_idx]
det_file = os.path.join(output_dir, 'detections.pkl')
cfg_yaml = yaml.dump(cfg)
save_object(
dict(
all_boxes=all_boxes,
all_segms=all_segms,
all_keyps=all_keyps,
cfg=cfg_yaml
), det_file
)
logger.info('Wrote detections to: {}'.format(os.path.abspath(det_file)))
return all_boxes, all_segms, all_keyps
def multi_gpu_test_net_on_dataset(
args, dataset_name, proposal_file, num_images, output_dir):
"""Multi-gpu inference on a dataset."""
binary_dir = envu.get_runtime_dir()
binary_ext = envu.get_py_bin_ext()
binary = os.path.join(binary_dir, args.test_net_file + binary_ext)
assert os.path.exists(binary), 'Binary \'{}\' not found'.format(binary)
# Pass the target dataset and proposal file (if any) via the command line
opts = ['TEST.DATASETS', '("{}",)'.format(dataset_name)]
if proposal_file:
opts += ['TEST.PROPOSAL_FILES', '("{}",)'.format(proposal_file)]
# Run inference in parallel in subprocesses
# Outputs will be a list of outputs from each subprocess, where the output
# of each subprocess is the dictionary saved by test_net().
tag = 'discovery' if 'train' in dataset_name else 'detection'
outputs = subprocess_utils.process_in_parallel(
tag, num_images, binary, output_dir,
args.load_ckpt, args.load_detectron, opts
)
# Collate the results from each subprocess
all_boxes = {}
for det_data in outputs:
all_boxes_batch = det_data['all_boxes']
all_boxes.update(all_boxes_batch)
if 'train' in dataset_name:
det_file = os.path.join(output_dir, 'discovery.pkl')
else:
det_file = os.path.join(output_dir, 'detections.pkl')
cfg_yaml = yaml.dump(cfg)
save_object(
dict(
all_boxes=all_boxes,
cfg=cfg_yaml
), det_file
)
logger.info('Wrote detections to: {}'.format(os.path.abspath(det_file)))
return all_boxes
def multi_gpu_test_cls_net_on_dataset(num_images, output_dir):
"""Multi-gpu inference on a dataset."""
binary_dir = envu.get_runtime_dir()
binary_ext = envu.get_py_bin_ext()
binary = os.path.join(binary_dir, 'test_net' + binary_ext)
assert os.path.exists(binary), 'Binary \'{}\' not found'.format(binary)
# Run inference in parallel in subprocesses
# Outputs will be a list of outputs from each subprocess, where the output
# of each subprocess is the dictionary saved by test_net().
outputs = subprocess_utils.process_in_parallel('detection', num_images,
binary, output_dir)
# Collate the results from each subprocess
all_cls = [[] for _ in range(cfg.MODEL.NUM_CLASSES)]
for cls_data in outputs:
all_cls_batch = cls_data['all_scores']
for cls_idx in range(1, cfg.MODEL.NUM_CLASSES):
all_cls[cls_idx] += all_cls_batch[cls_idx]
return all_cls
def multi_gpu_test_net_on_dataset(num_images, output_dir):
"""Multi-gpu inference on a dataset."""
binary_dir = envu.get_runtime_dir()
binary_ext = envu.get_py_bin_ext()
binary = os.path.join(binary_dir, 'test_net' + binary_ext)
assert os.path.exists(binary), 'Binary \'{}\' not found'.format(binary)
# Run inference in parallel in subprocesses
# Outputs will be a list of outputs from each subprocess, where the output
# of each subprocess is the dictionary saved by test_net().
outputs = subprocess_utils.process_in_parallel(
'detection', num_images, binary, output_dir
)
# Collate the results from each subprocess
all_boxes = [[] for _ in range(cfg.MODEL.NUM_CLASSES)]
all_segms = [[] for _ in range(cfg.MODEL.NUM_CLASSES)]
all_keyps = [[] for _ in range(cfg.MODEL.NUM_CLASSES)]
for det_data in outputs:
all_boxes_batch = det_data['all_boxes']
all_segms_batch = det_data['all_segms']
all_keyps_batch = det_data['all_keyps']
for cls_idx in range(1, cfg.MODEL.NUM_CLASSES):
all_boxes[cls_idx] += all_boxes_batch[cls_idx]
all_segms[cls_idx] += all_segms_batch[cls_idx]
all_keyps[cls_idx] += all_keyps_batch[cls_idx]
det_file = os.path.join(output_dir, 'detections.pkl')
cfg_yaml = yaml.dump(cfg)
save_object(
dict(
all_boxes=all_boxes,
all_segms=all_segms,
all_keyps=all_keyps,
cfg=cfg_yaml
), det_file
)
logger.info('Wrote detections to: {}'.format(os.path.abspath(det_file)))
return all_boxes, all_segms, all_keyps