def _test_std(self):
current_dir = osp.dirname(osp.realpath(__file__))
cfg_file = osp.join(current_dir, '..', 'configs', 'R-50_1x.yaml')
merge_cfg_from_file(cfg_file)
cfg.TEST.WEIGHTS = osp.join(
current_dir, '..', 'outputs', 'train',
'coco_2014_train+coco_2014_valminusminival', 'R-50_1x', 'default',
'model_final.pkl')
cfg.RETINANET.INFERENCE_TH = 0.
dataset = JsonDataset('coco_2014_minival')
roidb = dataset.get_roidb()
model = model_builder.create(cfg.MODEL.TYPE, train=False, gpu_id=0)
utils.net.initialize_gpu_from_weights_file(model,
cfg.TEST.WEIGHTS,
gpu_id=0)
model_builder.add_inference_inputs(model)
workspace.CreateNet(model.net)
workspace.CreateNet(model.conv_body_net)
num_images = len(roidb)
num_classes = cfg.MODEL.NUM_CLASSES
entry = roidb[0]
im = cv2.imread(entry['image'])
with utils.c2.NamedCudaScope(0):
cls_boxes, cls_preds, cls_probs, box_preds, anchors, im_info = im_detect_bbox(
model, im, debug=True)
workspace.ResetWorkspace()
return cls_preds, cls_probs, box_preds, anchors, im_info
def main(args):
merge_cfg_from_file(args.cfg)
cfg.NUM_GPUS = 1
args.weights = cache_url(args.weights, cfg.DOWNLOAD_CACHE)
assert_and_infer_cfg(cache_urls=False)
model = infer_engine.initialize_model_from_cfg(args.weights)
dummy_coco_dataset = dummy_datasets.get_coco_dataset()
cap = cv2.VideoCapture(0)
while True:
ret, frame = cap.read()
timers = defaultdict(Timer)
t = time.time()
with c2_utils.NamedCudaScope(0):
cls_boxes, cls_segms, cls_keyps = infer_engine.im_detect_all(
model, frame, None, timers=timers)
image = vis_utils.vis_one_image_opencv(np.array(frame),
cls_boxes,
cls_segms,
cls_keyps,
thresh=0.7,
kp_thresh=2,
show_box=True,
show_class=True)
cv2.imshow('camera', image)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
print("Time:", time.time() - t)
cap.release()
cv2.destroyAllWindows()
def main():
args = parser.parse_args()
logger = logging.getLogger(__name__)
merge_cfg_from_file(args.cfg)
cfg.TEST.WEIGHTS = args.weights
cfg.NUM_GPUS = 1
assert_and_infer_cfg()
model = infer_engine.initialize_model_from_cfg()
dummy_coco_dataset = dummy_datasets.get_coco_dataset()
'''
if os.path.isdir(args.im_or_folder):
im_list = glob.iglob(args.im_or_folder + '/*.' + args.image_ext)
else:
im_list = [args.im_or_folder]
'''
#for i, im_name in enumerate(im_list):
#out_name = os.path.join(
# args.output_dir, '{}'.format(os.path.basename(im_name) + '.pdf')
#)
#logger.info('Processing {} -> {}'.format(im_name, out_name))
#im = cv2.imread(im_name)
hintDataURL = bottle.request.forms.get("hint")
hintDataURL = re.sub('^data:image/.+;base64,', '', hintDataURL)
hintDataURL = base64.urlsafe_b64decode(hintDataURL.encode("ascii"))
hintDataURL = np.fromstring(hintDataURL, dtype=np.uint8)
hintDataURL = cv2.imdecode(hintDataURL, -1)
hstr = str(np.random.randint(100, 999))
cv2.imwrite('record/' + hstr + '.hint.png', hintDataURL)
im = cv2.imread('record/' + hstr + '.hint.png')
timers = defaultdict(Timer)
t = time.time()
with c2_utils.NamedCudaScope(0):
cls_boxes, cls_segms, cls_keyps = infer_engine.im_detect_all(
model, im, None, timers=timers)
return 'ok'
def main(args):
logger = logging.getLogger(__name__)
merge_cfg_from_file(args.cfg)
cfg.TEST.WEIGHTS = args.weights
cfg.NUM_GPUS = 1
assert_and_infer_cfg()
model = infer_engine.initialize_model_from_cfg()
#jasonj
#dummy_coco_dataset = dummy_datasets.get_coco_dataset()
if os.path.isdir(args.im_or_folder):
im_list = glob.iglob(args.im_or_folder + '/*.' + args.image_ext)
else:
im_list = [args.im_or_folder]
for i, im_name in enumerate(im_list):
out_name = os.path.join(
args.output_dir, '{}'.format(os.path.basename(im_name) + '.pdf'))
logger.info('Processing {} -> {}'.format(im_name, out_name))
im = cv2.imread(im_name)
timers = defaultdict(Timer)
t = time.time()
with c2_utils.NamedCudaScope(0):
#jasonj
cls_boxes, cls_segms, cls_keyps = infer_engine.im_detect_all(
model, im, "infer_res.jpg", None, timers=timers)
logger.info('Inference time: {:.3f}s'.format(time.time() - t))
for k, v in timers.items():
logger.info(' | {}: {:.3f}s'.format(k, v.average_time))
if i == 0:
logger.info(
' \ Note: inference on the first image will be slower than the '
'rest (caches and auto-tuning need to warm up)')
def get_rpn_box_proposals(im, args):
cfg.immutable(False)
"""Load a yaml config file and merge it into the global config."""
merge_cfg_from_file(args.rpn_cfg)
'''Number of GPUs to use (applies to both training and testing)'''
cfg.NUM_GPUS = 1
'''Indicates the model's computation terminates with the production of RPN proposals (i.e., it outputs proposals ONLY, no actual object detections)'''
cfg.MODEL.RPN_ONLY = True
'''Number of top scoring RPN proposals to keep before applying NMS When FPN is used, this is *per FPN level* (not total)'''
cfg.TEST.RPN_PRE_NMS_TOP_N = 10000
'''Number of top scoring RPN proposals to keep after applying NMS his is the total number of RPN proposals produced (for both FPN and non-FPN cases)'''
cfg.TEST.RPN_POST_NMS_TOP_N = 2000
'''Call this function in your script after you have finished setting all cfg values that are necessary (e.g., merging a config from a file, merging
command line config options, etc.)'''
assert_and_infer_cfg()
"""Initialize a model from the global cfg. Loads test-time weights and creates the networks in the Caffe2 workspace. """
model = model_engine.initialize_model_from_cfg(args.rpn_pkl)
with c2_utils.NamedCudaScope(0):
"""Generate RPN proposals on a single image."""
boxes, scores = rpn_engine.im_proposals(model, im)
return boxes, scores
def build_graph(self):
c2_utils.import_detectron_ops()
# OpenCL may be enabled by default in OpenCV3; disable it because it's not
# thread safe and causes unwanted GPU memory allocations.
cv2.ocl.setUseOpenCL(False)
merge_cfg_from_file(self.config.args['config_path'])
# If this is a CPU kernel, tell Caffe2 that it should not use
# any GPUs for its graph operations
cpu_only = True
for handle in self.config.devices:
if handle.type == DeviceType.GPU.value:
cpu_only = False
if cpu_only:
cfg.NUM_GPUS = 0
else:
cfg.NUM_GPUS = 1
# TODO: wrap this in "with device"
weights_path = cache_url(self.config.args['weights_path'],
cfg.DOWNLOAD_CACHE)
assert_and_infer_cfg(cache_urls=False)
model = infer_engine.initialize_model_from_cfg(weights_path)
return model
def __init__(self, cfg_path, weights_path):
#nms_same_class 0.3 ---- *.yaml/TEST:NMS:0.3 中设置 defalut 0.5
self.gpu_id = 1 #gpu_id default 0
self.score_thresh = 0.4 #score > score_thresh default 0.3
self.per_class_thresh = False #score > class_score_thresh
self.autotruck_score_thresh = 0.6
self.forklift_score_thresh = 0.65
self.digger_score_thresh = 0.65
self.car_score_thresh = 0.45
self.bus_score_thresh = 0.0
self.tanker_score_thresh = 0.55
self.person_score_thresh = 0.35
self.minitruck_score_thresh = 0.0
self.minibus_score_thresh = 0.59
self.class_nms_thresh = 0.85 #nms_between_classes IOU > class_nms_thresh default 0.9
merge_cfg_from_file(cfg_path)
self.model = infer_engine.initialize_model_from_cfg(
weights_path, self.gpu_id)
self.dummy_coco_dataset = dummy_datasets.get_steal_oil_class14_dataset(
)
print("model is ok")
def main():
# Initialize C2
workspace.GlobalInit(
['caffe2', '--caffe2_log_level=0', '--caffe2_gpu_memory_tracking=1']
)
# Set up logging and load config options
logger = setup_logging(__name__)
logging.getLogger('roi_data.loader').setLevel(logging.INFO)
args = parse_args()
logger.info('Called with args:')
logger.info(args)
if args.cfg_file is not None:
merge_cfg_from_file(args.cfg_file)
if args.opts is not None:
merge_cfg_from_list(args.opts)
assert_and_infer_cfg()
logger.info('Training with config:')
logger.info(pprint.pformat(cfg))
# Note that while we set the numpy random seed network training will not be
# deterministic in general. There are sources of non-determinism that cannot
# be removed with a reasonble execution-speed tradeoff (such as certain
# non-deterministic cudnn functions).
np.random.seed(cfg.RNG_SEED)
# Execute the training run
checkpoints = train_model()
# Test the trained model
if not args.skip_test:
test_model(checkpoints['final'], args.multi_gpu_testing, args.opts)
def main():
# Initialize C2
workspace.GlobalInit(
['caffe2', '--caffe2_log_level=0', '--caffe2_gpu_memory_tracking=1'])
# Set up logging and load config options
logger = setup_logging(__name__)
logging.getLogger('roi_data.loader').setLevel(logging.INFO)
args = parse_args()
logger.info('Called with args:')
logger.info(args)
if args.cfg_file is not None:
merge_cfg_from_file(args.cfg_file)
if args.opts is not None:
merge_cfg_from_list(args.opts)
assert_and_infer_cfg()
logger.info('Training with config:')
logger.info(pprint.pformat(cfg))
# Note that while we set the numpy random seed network training will not be
# deterministic in general. There are sources of non-determinism that cannot
# be removed with a reasonble execution-speed tradeoff (such as certain
# non-deterministic cudnn functions).
np.random.seed(cfg.RNG_SEED)
# Execute the training run
checkpoints = train_model()
# Test the trained model
if not args.skip_test:
test_model(checkpoints['final'], args.multi_gpu_testing, args.opts)
def main(args):
merge_cfg_from_file(args.cfg)
cfg.NUM_GPUS = 1
# get the weight path
args.weights = cache_url(args.weights, cfg.DOWNLOAD_CACHE)
assert_and_infer_cfg(cache_urls=False)
model = infer_engine.initialize_model_from_cfg(args.weights)
#dummy_coco_dataset = dummy_datasets.get_coco_dataset()
det_dir = os.path.join(args.input_dir, 'det')
if not os.path.exists(det_dir):
os.makedirs(det_dir)
txt_file = os.path.join(det_dir, "det.txt")
fid = open(txt_file, 'w')
img_dir = os.path.join(args.input_dir, "img1")
img_list = os.listdir(img_dir)
img_list = sorted(img_list)
for i in range(len(img_list)):
print("processing: %d/%d" % (i + 1, len(img_list)))
img_name = img_list[i][:-4]
img_idx = int(img_name)
img_path = os.path.join(img_dir, img_list[i])
frame = cv2.imread(img_path)
with c2_utils.NamedCudaScope(0):
cls_boxes, cls_segms, cls_keyps = infer_engine.im_detect_all(
model, frame, None, None)
vis_utils.write_txt(fid, img_idx, cls_boxes)
fid.close()
def main(args):
logger = logging.getLogger(__name__)
merge_cfg_from_file(args.cfg)
cfg.TEST.WEIGHTS = args.weights
cfg.NUM_GPUS = 1
assert_and_infer_cfg()
model = infer_engine.initialize_model_from_cfg()
dummy_coco_dataset = dummy_datasets.get_coco_dataset()
video_frame_length = video_frame(args) #Yunhan Yang pass in a list to save all the frames
print ("The video has length " + str(video_frame_length) + " frames")
f_image_path = args.im_or_folder+ "frame%d.jpg" % 0
fr = cv2.imread(f_image_path, 0)
origin_width, origin_height = fr.shape[:2]
for x in range(0,video_frame_length):
im_list = [args.im_or_folder+"frame" + str(x) + ".jpg"] #Yunhan Yang have to save frame in real folder and then read in
#maybe need need double for loop for list of frames
for i, im_name in enumerate(im_list):
out_name = os.path.join(
args.output_dir, '{}'.format(os.path.basename(im_name) + '.pdf')
)
logger.info('Processing {} -> {}'.format(im_name, out_name))
im = cv2.imread(im_name)
timers = defaultdict(Timer)
t = time.time()
with c2_utils.NamedCudaScope(0):
cls_boxes, cls_segms, cls_keyps = infer_engine.im_detect_all(
model, im, None, timers=timers
)
logger.info('Inference time: {:.3f}s'.format(time.time() - t))
for k, v in timers.items():
logger.info(' | {}: {:.3f}s'.format(k, v.average_time))
if i == 0:
logger.info(
' \ Note: inference on the first image will be slower than the '
'rest (caches and auto-tuning need to warm up)'
)
#Yunhan Yang edit
if not os.path.exists(args.im_or_folder+ "/video"):
os.makedirs(args.im_or_folder+ "/video")
#Yunhan Yang edit Detectron/lib/utils/vis.py add make result as jpg than pdf
vis_utils.vis_one_image(
im[:, :, ::-1], # BGR -> RGB for visualization
im_name,
args.output_dir,
cls_boxes,
cls_segms,
cls_keyps,
dataset=dummy_coco_dataset,
box_alpha=0.3,
show_class=True,
thresh=0.7,
kp_thresh=2
)
def main(args):
logger = logging.getLogger(__name__)
merge_cfg_from_file(args.cfg)
cfg.TEST.WEIGHTS = args.weights
cfg.NUM_GPUS = 1
assert_and_infer_cfg()
model = infer_engine.initialize_model_from_cfg()
dummy_dataset = dummy_datasets.get_cifar100_dataset()
if os.path.isdir(args.im_or_folder):
im_list = glob.iglob(args.im_or_folder + '/*.' + args.image_ext)
else:
im_list = [args.im_or_folder]
for i, im_name in enumerate(im_list):
logger.info('Processing {}'.format(im_name))
im = cv2.imread(im_name)
timers = defaultdict(Timer)
t = time.time()
with c2_utils.NamedCudaScope(0):
cls_scores, _, _ = infer_engine.im_detect_all(model,
im,
None,
timers=timers)
logger.info('Inference time: {:.3f}s'.format(time.time() - t))
cl = np.argmax(cls_scores)
for k, v in timers.items():
logger.info(' | {}: {:.3f}s'.format(k, v.average_time))
logger.info(' | Class is: {}'.format(dummy_dataset.classes[cl]))
logger.info(' | Class Confidance is: {:.2f}%'.format(
cls_scores[cl] * 100))
if i == 0:
logger.info(
' \ Note: inference on the first image will be slower than the '
'rest (caches and auto-tuning need to warm up)')
def _test_std(self):
root_dir = osp.join('/private', 'home', 'xinleic', 'pyramid')
cfg_file = osp.join(root_dir, 'configs', 'visual_genome', 'e2e_faster_rcnn_R-50-FPN_1x.yaml')
merge_cfg_from_file(cfg_file)
cfg.NUM_GPUS = 1
cfg.TEST.RPN_PRE_NMS_TOP_N = 100
cfg.TEST.RPN_POST_NMS_TOP_N = 20
assert_and_infer_cfg()
test_weight = osp.join(root_dir, 'outputs', 'train', 'visual_genome_train',
'e2e_faster_rcnn_R-50-FPN_1x', 'RNG_SEED#3', 'model_final.pkl')
model = test_engine.initialize_model_from_cfg(test_weight, gpu_id=0)
dataset = JsonDataset('visual_genome_val')
roidb = dataset.get_roidb()
num_images = len(roidb)
num_classes = cfg.MODEL.NUM_CLASSES
entry = roidb[1]
im = cv2.imread(entry['image'])
max_level = cfg.FPN.RPN_MAX_LEVEL
min_level = cfg.FPN.RPN_MIN_LEVEL
# input: rpn_cls_probs_fpn2, rpn_bbox_pred_fpn2
# output: rpn_rois_fpn2, rpn_roi_probs_fpn2
with utils.c2.NamedCudaScope(0):
# let's manually do the testing here
inputs, im_scale = _get_blobs(im, None, cfg.TEST.SCALE, cfg.TEST.MAX_SIZE)
for k, v in inputs.items():
workspace.FeedBlob(core.ScopedName(k), v)
workspace.RunNet(model.net.Proto().name)
cls_probs = [core.ScopedName('rpn_cls_probs_fpn%d' % i) for i in range(min_level, max_level+1)]
box_preds = [core.ScopedName('rpn_bbox_pred_fpn%d' % i) for i in range(min_level, max_level+1)]
rpn_rois = [core.ScopedName('rpn_rois_fpn%d' % i) for i in range(min_level, max_level+1)]
rpn_roi_probs = [core.ScopedName('rpn_roi_probs_fpn%d' % i) for i in range(min_level, max_level+1)]
cls_probs = workspace.FetchBlobs(cls_probs)
box_preds = workspace.FetchBlobs(box_preds)
rpn_rois = workspace.FetchBlobs(rpn_rois)
rpn_roi_probs = workspace.FetchBlobs(rpn_roi_probs)
rpn_rois = np.vstack(rpn_rois)
rpn_roi_probs = np.vstack(rpn_roi_probs)
# remove the image dimension
rpn_rois = rpn_rois[:, 1:]
boxes = np.hstack([rpn_rois, rpn_roi_probs])
im_name = osp.splitext(osp.basename(entry['image']))[0]
utils.vis.vis_one_image(im[:, :, ::-1],
'{:s}-std-output'.format(im_name),
osp.join(root_dir, 'tests'),
boxes,
segms=None,
keypoints=None,
thresh=0.,
box_alpha=0.8,
dataset=dataset,
show_class=False)
workspace.ResetWorkspace()
im_info = inputs['im_info'].astype(np.float32)
return cls_probs, box_preds, im_info, im, im_name, root_dir, dataset
def main(args):
logger = logging.getLogger(__name__)
merge_cfg_from_file(args.cfg)
cfg.TEST.WEIGHTS = args.weights
cfg.NUM_GPUS = 1
assert_and_infer_cfg(cache_urls=False)
model = infer_engine.initialize_model_from_cfg()
dummy_coco_dataset = dummy_datasets.get_coco_dataset()
if os.path.isdir(args.im_or_folder):
im_list = glob.iglob(args.im_or_folder + '/*.' + args.image_ext)
else:
im_list = [args.im_or_folder]
for i, im_name in enumerate(im_list):
out_name = os.path.join(
args.output_dir, '{}'.format(os.path.basename(im_name) + '.pdf'))
logger.info('Processing {} -> {}'.format(im_name, out_name))
im = cv2.imread(im_name)
timers = defaultdict(Timer)
t = time.time()
with c2_utils.NamedCudaScope(0):
cls_boxes, cls_segms, cls_keyps = infer_engine.im_detect_all(
model, im, None, timers=timers)
logger.info('Inference time: {:.3f}s'.format(time.time() - t))
for k, v in timers.items():
logger.info(' | {}: {:.3f}s'.format(k, v.average_time))
if i == 0:
logger.info(
' \ Note: inference on the first image will be slower than the '
'rest (caches and auto-tuning need to warm up)')
t1 = time.time()
im = vis_utils.vis_one_image_opencv(im,
cls_boxes,
segms=cls_segms,
keypoints=cls_keyps,
thresh=0.7,
kp_thresh=2,
show_box=True,
dataset=dummy_coco_dataset,
show_class=True)
# vis_utils.vis_one_image(
# im[:, :, ::-1], # BGR -> RGB for visualization
# im_name,
# args.output_dir,
# cls_boxes,
# cls_segms,
# cls_keyps,
# dataset=dummy_coco_dataset,
# box_alpha=0.3,
# show_class=True,
# thresh=0.7,
# kp_thresh=2
# )
t2 = time.time() - t1
print("vis time %f ms" % (t2 * 1000))
cv2.imwrite(
args.output_dir + '/' + im_name.split('/')[-1].split('.')[0] +
'.jpg', im)
def main():
workspace.GlobalInit(['caffe2', '--caffe2_log_level=0'])
args = parse_args()
logger.info('Called with args:')
logger.info(args)
if args.cfg_file is not None:
merge_cfg_from_file(args.cfg_file)
if args.opts is not None:
merge_cfg_from_list(args.opts)
cfg.NUM_GPUS = 1
assert_and_infer_cfg()
logger.info('Conerting model with config:')
logger.info(pprint.pformat(cfg))
assert not cfg.MODEL.KEYPOINTS_ON, "Keypoint model not supported."
assert not cfg.MODEL.MASK_ON, "Mask model not supported."
assert not cfg.FPN.FPN_ON, "FPN not supported."
assert not cfg.RETINANET.RETINANET_ON, "RetinaNet model not supported."
# load model from cfg
model, blobs = load_model(args)
net = core.Net('')
net.Proto().op.extend(copy.deepcopy(model.net.Proto().op))
net.Proto().external_input.extend(
copy.deepcopy(model.net.Proto().external_input))
net.Proto().external_output.extend(
copy.deepcopy(model.net.Proto().external_output))
net.Proto().type = args.net_execution_type
net.Proto().num_workers = 1 if args.net_execution_type == 'simple' else 4
# Reset the device_option, change to unscope name and replace python operators
convert_net(args, net.Proto(), blobs)
# add operators for bbox
add_bbox_ops(args, net, blobs)
if args.fuse_af:
print('Fusing affine channel...')
net, blobs = mutils.fuse_net_affine(
net, blobs)
if args.use_nnpack:
mutils.update_mobile_engines(net.Proto())
# generate init net
empty_blobs = ['data', 'im_info']
init_net = gen_init_net(net, blobs, empty_blobs)
if args.device == 'gpu':
[net, init_net] = convert_model_gpu(args, net, init_net)
net.Proto().name = args.net_name
init_net.Proto().name = args.net_name + "_init"
if args.test_img is not None:
verify_model(args, [net, init_net], args.test_img)
_save_models(net, init_net, args)
def main(args):
logger = logging.getLogger(__name__)
merge_cfg_from_file(args.cfg)
cfg.TEST.WEIGHTS = args.weights
cfg.NUM_GPUS = 1
cfg.TRAIN.IMS_PER_BATCH = 1
assert_and_infer_cfg()
model = infer_engine.initialize_model_from_cfg()
dummy_coco_dataset = dummy_datasets.get_coco_dataset()
if os.path.isdir(args.im_or_folder):
im_list = glob.iglob(args.im_or_folder + '/*.' + args.image_ext)
else:
im_list = [args.im_or_folder]
for i, im_name in enumerate(im_list):
out_name = os.path.join(
args.output_dir, '{}'.format(os.path.basename(im_name) + '.pdf'))
logger.info('Processing {} -> {}'.format(im_name, out_name))
im = cv2.imread(im_name)
timers = defaultdict(Timer)
t = time.time()
with c2_utils.NamedCudaScope(0):
cls_boxes, cls_segms, cls_keyps, \
cls_refined_segms, cls_refined_keyps = infer_engine.im_detect_all(
model, im, None, timers=timers
)
logger.info('Inference time: {:.3f}s'.format(time.time() - t))
for k, v in timers.items():
logger.info(' | {}: {:.3f}s'.format(k, v.average_time))
if i == 0:
logger.info(
' \ Note: inference on the first image will be slower than the '
'rest (caches and auto-tuning need to warm up)')
vis_utils.vis_one_image(
im[:, :, ::-1], # BGR -> RGB for visualization
im_name,
os.path.join(args.output_dir, 'vis_local'),
cls_boxes,
cls_segms,
cls_keyps,
dataset=dummy_coco_dataset,
box_alpha=0.3,
show_class=True,
thresh=0.7,
kp_thresh=2)
vis_utils.vis_one_image(
im[:, :, ::-1], # BGR -> RGB for visualization
im_name,
os.path.join(args.output_dir, 'vis_refined'),
cls_boxes,
cls_refined_segms,
cls_refined_keyps,
dataset=dummy_coco_dataset,
box_alpha=0.3,
show_class=True,
thresh=0.7,
kp_thresh=2)
def get_model(cfg_file, weights_file):
merge_cfg_from_file(cfg_file)
cfg.TRAIN.WEIGHTS = '' # NOTE: do not download pretrained model weights
cfg.TEST.WEIGHTS = weights_file
cfg.NUM_GPUS = 1
assert_and_infer_cfg()
model = infer_engine.initialize_model_from_cfg()
return model
def main(args):
logger = logging.getLogger(__name__)
merge_cfg_from_file(args.cfg)
cfg.TEST.WEIGHTS = args.weights
cfg.NUM_GPUS = 1
assert_and_infer_cfg()
model = infer_engine.initialize_model_from_cfg()
dummy_coco_dataset = dummy_datasets.get_coco_dataset()
if os.path.isdir(args.im_or_folder):
im_list = glob.iglob(args.im_or_folder + '/*.' + args.image_ext)
else:
im_list = [args.im_or_folder]
# for i, im_name in enumerate(im_list):
# out_name = os.path.join(
# args.output_dir, '{}'.format(os.path.basename(im_name) + '.pdf')
# )
# logger.info('Processing {} -> {}'.format(im_name, out_name))
#set webcam
cam = cv2.VideoCapture(0)
while True:
#Fetch image from camera
ret_val, im = cam.read()
#uncomment to resize image
#im = cv2.resize(im, (1200,1024))
timers = defaultdict(Timer)
t = time.time()
with c2_utils.NamedCudaScope(0):
cls_boxes, cls_segms, cls_keyps = infer_engine.im_detect_all(
model, im, None, timers=timers
)
logger.info('Inference time: {:.3f}s'.format(time.time() - t))
for k, v in timers.items():
logger.info(' | {}: {:.3f}s'.format(k, v.average_time))
if 0:
logger.info(
' \ Note: inference on the first image will be slower than the '
'rest (caches and auto-tuning need to warm up)'
)
vis_utils.vis_one_image(
im[:, :, ::-1], # BGR -> RGB for visualization
"dummy_name",
args.output_dir,
cls_boxes,
cls_segms,
cls_keyps,
dataset=dummy_coco_dataset,
box_alpha=0.3,
show_class=True,
thresh=0.7,
kp_thresh=2
)
cv2.destroyAllWindows()
def get_model(cfg_file, weights_file):
merge_cfg_from_file(cfg_file)
cfg.TRAIN.WEIGHTS = '' # NOTE: do not download pretrained model weights
cfg.TEST.WEIGHTS = weights_file
cfg.NUM_GPUS = 1
assert_and_infer_cfg()
#according the cfg to bulid model
model = model_builder.create(cfg.MODEL.TYPE,train=True)
return model
def main(args):
logger = logging.getLogger(__name__)
merge_cfg_from_file(args.cfg)
cfg.TEST.WEIGHTS = args.weights
cfg.NUM_GPUS = 1
assert_and_infer_cfg()
model = infer_engine.initialize_model_from_cfg()
predict_dataset(args.project, visualize=False, randomize=False)
def main(args):
logger = logging.getLogger(__name__)
merge_cfg_from_file(args.cfg)
cfg.NUM_GPUS = 1
args.weights = cache_url(args.weights, cfg.DOWNLOAD_CACHE)
assert_and_infer_cfg(cache_urls=False)
model = infer_engine.initialize_model_from_cfg(args.weights)
start = timeit.default_timer()
if os.path.isdir(args.im_or_folder):
im_list = glob.iglob(args.im_or_folder + '/*.' + args.image_ext)
else:
im_list = [args.im_or_folder]
##extract bboxes from bottom-up attention model
image_bboxes = {}
if args.bbox_file is not None:
image_bboxes = extract_bboxes(args.bbox_file)
count = 0
if not os.path.exists(args.output_dir):
os.makedirs(args.output_dir)
for i, im_name in enumerate(im_list):
im_base_name = os.path.basename(im_name)
image_id = int(im_base_name.split(".")[0].split("_")[-1]) ##for COCO
if image_id % args.total_group == args.group_id:
bbox = image_bboxes[image_id] if image_id in image_bboxes else None
im = cv2.imread(im_name)
if im is not None:
outfile = os.path.join(args.output_dir,
im_base_name.replace('jpg', 'npy'))
lock_folder = outfile.replace('npy', 'lock')
if not os.path.exists(lock_folder) and os.path.exists(outfile):
continue
if not os.path.exists(lock_folder):
os.makedirs(lock_folder)
result = get_detections_from_im(cfg,
model,
im,
image_id,
args.feat_name,
args.min_bboxes,
args.max_bboxes,
bboxes=bbox)
np.save(outfile, result)
os.rmdir(lock_folder)
count += 1
if count % 100 == 0:
end = timeit.default_timer()
epoch_time = end - start
print('process {:d} images after {:.1f} s'.format(
count, epoch_time))
def __init__(self, config, **kwargs):
kwargs['handlers'] = [(r'/analyse', AnalyseHandler)]
super(Application, self).__init__(**kwargs)
merge_cfg_from_file(config.get('DETECTRON', 'CONFIG'))
cfg.TEST.WEIGHTS = config.get('DETECTRON', 'WEIGHTS')
cfg.NUM_GPUS = 1
assert_and_infer_cfg()
self.model = infer_engine.initialize_model_from_cfg()
self.dummy_coco_dataset = dummy_datasets.get_coco_dataset()
def main(args):
logger = logging.getLogger(__name__)
merge_cfg_from_file(args.cfg)
cfg.TEST.WEIGHTS = args.weights
cfg.NUM_GPUS = 1
logger.info('about to assert')
assert_and_infer_cfg()
logger.info('About to initialise model')
model = infer_engine.initialize_model_from_cfg()
logger.info("Done initialising")
dummy_coco_dataset = dummy_datasets.get_coco_dataset()
if os.path.isdir(args.im_or_folder):
im_list = glob.iglob(args.im_or_folder + '/*.' + args.image_ext)
else:
im_list = [args.im_or_folder]
for i, im_name in enumerate(im_list):
out_name = os.path.join(
args.output_dir, '{}'.format(os.path.basename(im_name) + '.png'))
logger.info('Processing {} -> {}'.format(im_name, out_name))
im = cv2.imread(im_name)
timers = defaultdict(Timer)
t = time.time()
with c2_utils.NamedCudaScope(0):
cls_boxes, cls_segms, cls_keyps = infer_engine.im_detect_all(
model, im, None, timers=timers)
logger.info('Inference time: {:.3f}s'.format(time.time() - t))
for k, v in timers.items():
logger.info(' | {}: {:.3f}s'.format(k, v.average_time))
if i == 0:
logger.info(
' \ Note: inference on the first image will be slower than the '
'rest (caches and auto-tuning need to warm up)')
segmented_images, classes, scores, segmented_binary_masks = vis_utils.segmented_images_in_original_image_size(
im,
im_name,
args.output_dir,
cls_boxes,
cls_segms,
cls_keyps,
dataset=dummy_coco_dataset,
box_alpha=0.3,
show_class=True,
thresh=0.7,
kp_thresh=2)
found = False
for index, value in enumerate(segmented_images):
if classes[index] == args.class_label and not found:
logger.info('Writing output file to: {}'.format(str(i)))
bin_mask = vis_utils.vis_binary_mask(
im, segmented_binary_masks[index])
cv2.imwrite(out_name, value)
cv2.imwrite(out_name.rstrip(".png") + "bin.png", bin_mask)
found = True
def main(args):
logger = logging.getLogger(__name__)
merge_cfg_from_file(args.cfg)
cfg.TEST.WEIGHTS = args.weights
cfg.NUM_GPUS = 1
assert_and_infer_cfg()
model = infer_engine.initialize_model_from_cfg()
dummy_coco_dataset = dummy_datasets.get_coco_dataset()
if os.path.isdir(args.im_or_folder):
im_list = glob.iglob(args.im_or_folder + '/*.' + args.image_ext)
else:
im_list = [args.im_or_folder]
"""
Add support for webcam
"""
# Set and get camera from OpenCV
cam = cv2.VideoCapture(0)
im_name = 'tmp_im'
while True:
# Fetch image from camera
_, im = cam.read()
timers = defaultdict(Timer)
t = time.time()
with c2_utils.NamedCudaScope(0):
cls_boxes, cls_segms, cls_keyps = infer_engine.im_detect_all(
model, im, None, timers=timers)
logger.info('Inference time: {:.3f}s'.format(time.time() - t))
for k, v in timers.items():
logger.info(' | {}: {:.3f}s'.format(k, v.average_time))
if 0:
logger.info(
' \ Note: inference on the first image will be slower than the '
'rest (caches and auto-tuning need to warm up)')
vis_utils.vis_one_image(
im[:, :, ::-1], # BGR -> RGB for visualization
im_name,
args.output_dir,
cls_boxes,
cls_segms,
cls_keyps,
dataset=dummy_coco_dataset,
box_alpha=0.3,
show_class=True,
thresh=0.7,
kp_thresh=2,
ext='jpg' # default is PDF, but we want JPG.
)
cv2.destroyAllWindows()
def main(args):
logger = logging.getLogger(__name__)
merge_cfg_from_file(args.cfg)
cfg.NUM_GPUS = 1
args.weights = cache_url(args.weights, cfg.DOWNLOAD_CACHE)
assert_and_infer_cfg()
model = infer_engine.initialize_model_from_cfg(args.weights)
dummy_coco_dataset = dummy_datasets.get_coco_dataset()
if os.path.isdir(args.im_or_folder):
# im_list = glob.iglob(args.im_or_folder + '/*.' + args.image_ext)
im_list = search(args.im_or_folder, args.image_ext)
else:
im_list = [args.im_or_folder]
for i, im_name in enumerate(im_list):
#for i, im_name in im_list:
#out_name = os.path.join(
# args.output_dir, '{}'.format(os.path.basename(im_name) + '.pdf')
#)
out_name = im_name.replace(args.im_or_folder, args.output_dir)
par_path = os.path.dirname(out_name)
if not os.path.exists(par_path):
os.makedirs(par_path)
logger.info('Processing {} -> {}'.format(im_name, out_name))
im = cv2.imread(im_name)
timers = defaultdict(Timer)
t = time.time()
with c2_utils.NamedCudaScope(0):
cls_boxes, cls_segms, cls_keyps = infer_engine.im_detect_all(
model, im, None, timers=timers
)
logger.info('Inference time: {:.3f}s'.format(time.time() - t))
for k, v in timers.items():
logger.info(' | {}: {:.3f}s'.format(k, v.average_time))
if i == 0:
logger.info(
' \ Note: inference on the first image will be slower than the '
'rest (caches and auto-tuning need to warm up)'
)
vis_utils.vis_one_image(
im[:, :, ::-1], # BGR -> RGB for visualization
im_name,
par_path,
cls_boxes,
cls_segms,
cls_keyps,
dataset=dummy_coco_dataset,
box_alpha=0.3,
show_class=True,
thresh=0.7,
kp_thresh=2,
ext='png'
)
def main(args):
logger = logging.getLogger(__name__)
merge_cfg_from_file(args.cfg)
cfg.NUM_GPUS = 1
args.weights = cache_url(args.weights, cfg.DOWNLOAD_CACHE)
assert_and_infer_cfg(cache_urls=False)
model = infer_engine.initialize_model_from_cfg(args.weights)
dummy_coco_dataset = (
dummy_datasets.get_vg3k_dataset()
if args.use_vg3k else dummy_datasets.get_coco_dataset())
if os.path.isdir(args.im_or_folder):
im_list = sorted(glob.iglob(args.im_or_folder + '/*.' + args.image_ext))
else:
im_list = [args.im_or_folder]
for i, im_name in enumerate(im_list):
out_name = os.path.join(
args.output_dir, '{}'.format(os.path.basename(im_name) + '.npz')
)
logger.info('Processing {} -> {}'.format(im_name, out_name))
im = cv2.imread(im_name)
if im is None:
logger.info('Unable to read image, skipping.')
continue
timers = defaultdict(Timer)
t = time.time()
with c2_utils.NamedCudaScope(0):
cls_boxes, cls_segms, cls_keyps = infer_engine.im_detect_all(
model, im, None, timers=timers
)
logger.info('Inference time: {:.3f}s'.format(time.time() - t))
for k, v in timers.items():
logger.info(' | {}: {:.3f}s'.format(k, v.average_time))
if i == 0:
logger.info(
' \ Note: inference on the first image will be slower than the '
'rest (caches and auto-tuning need to warm up)'
)
boxes, segms, classes = convert(cls_boxes, cls_segms)
classes = np.array(classes, dtype=np.uint16)
resolution = segms[0]['size']
segms = np.array([x['counts'] for x in segms]) # Run-length encoding
valid = boxes[:, 4] >= args.thresh
if args.filter_classes:
valid &= np.isin(classes, all_classes)
boxes = boxes[valid].copy()
classes = classes[valid].copy()
segms = segms[valid].copy()
output_name = os.path.basename(im_name)
np.savez(args.output_dir + '/' + output_name, boxes=boxes, segments=segms, classes=classes, resolution=resolution)
def main(args):
logger = logging.getLogger(__name__)
merge_cfg_from_file(args.cfg)
cfg.TEST.WEIGHTS = args.weights
cfg.NUM_GPUS = 1
assert_and_infer_cfg()
model = infer_engine.initialize_model_from_cfg()
dummy_coco_dataset = dummy_datasets.get_coco_dataset()
if os.path.isdir(args.im_or_folder):
im_list = glob.iglob(args.im_or_folder + '/*.' + args.image_ext)
else:
im_list = [args.im_or_folder]
test_ids = []
rles = []
for i, im_name in enumerate(im_list):
out_name = os.path.join(
args.output_dir, '{}'.format(os.path.basename(im_name) + '.pdf'))
logger.info('Processing {} -> {}'.format(im_name, out_name))
im = cv2.imread(im_name)
timers = defaultdict(Timer)
t = time.time()
with c2_utils.NamedCudaScope(0):
cls_boxes, cls_segms, cls_keyps = infer_engine.im_detect_all(
model, im, None, timers=timers)
logger.info('Inference time: {:.3f}s'.format(time.time() - t))
for k, v in timers.items():
logger.info(' | {}: {:.3f}s'.format(k, v.average_time))
if i == 0:
logger.info(
' \ Note: inference on the first image will be slower than the '
'rest (caches and auto-tuning need to warm up)')
new_test_ids, new_rles = vis_utils.make_submission(im[:, :, ::-1],
im_name,
cls_boxes,
cls_segms,
cls_keyps,
thresh=0.7)
test_ids.extend(new_test_ids)
rles.extend(new_rles)
import pandas as pd
sub = pd.DataFrame()
sub['ImageId'] = test_ids
sub['EncodedPixels'] = pd.Series(rles).apply(
lambda x: ' '.join(str(y) for y in x))
sub.to_csv(args.output_dir +
'/e2e_mask_rcnn_R-50-FPN_1x-lr3e-3-nuclei-6-new.csv',
index=False)
def main(args):
logger = logging.getLogger(__name__)
dummy_coco_dataset = dummy_datasets.get_coco_dataset()
cfg_orig = yaml.load(yaml.dump(cfg))
im = cv2.imread(args.im_file)
if args.rpn_pkl is not None:
proposal_boxes, _proposal_scores = get_rpn_box_proposals(im, args)
workspace.ResetWorkspace()
else:
proposal_boxes = None
cls_boxes, cls_segms, cls_keyps = None, None, None
for i in range(0, len(args.models_to_run), 2):
pkl = args.models_to_run[i]
yml = args.models_to_run[i + 1]
cfg.immutable(False)
merge_cfg_from_cfg(cfg_orig)
merge_cfg_from_file(yml)
if len(pkl) > 0:
weights_file = pkl
else:
weights_file = cfg.TEST.WEIGHTS
cfg.NUM_GPUS = 1
assert_and_infer_cfg()
model = model_engine.initialize_model_from_cfg(weights_file)
with c2_utils.NamedCudaScope(0):
cls_boxes_, cls_segms_, cls_keyps_ = \
model_engine.im_detect_all(model, im, proposal_boxes)
cls_boxes = cls_boxes_ if cls_boxes_ is not None else cls_boxes
cls_segms = cls_segms_ if cls_segms_ is not None else cls_segms
cls_keyps = cls_keyps_ if cls_keyps_ is not None else cls_keyps
workspace.ResetWorkspace()
out_name = os.path.join(
args.output_dir, '{}'.format(os.path.basename(args.im_file) + '.pdf')
)
logger.info('Processing {} -> {}'.format(args.im_file, out_name))
vis_utils.vis_one_image(
im[:, :, ::-1],
args.im_file,
args.output_dir,
cls_boxes,
cls_segms,
cls_keyps,
dataset=dummy_coco_dataset,
box_alpha=0.3,
show_class=True,
thresh=0.7,
kp_thresh=2
)
def track(cfg_path, opts):
# Setup tracker configuration
merge_cfg_from_file(cfg_path)
opts = opts.split(' ')
if len(opts) > 0:
merge_cfg_from_list(opts)
device = torch.device('cuda:{}'.format(0))
tracker = SiamTracker(device)
def load_image(img_path, use_pil):
if use_pil:
pil_img = Image.open(img_path)
if pil_img.mode == 'L':
pil_img = pil_img.convert(
'RGB') # convert to RGB 3 channels if necessary
im_tensor = to_tensor(pil_img)
else:
im = cv2.imread(img_path, cv2.IMREAD_COLOR) # HxWxC
im_tensor = torch.from_numpy(np.transpose(im, (2, 0, 1))).float()
im_tensor = im_tensor.unsqueeze(0).to(device) # 1*C*H*W
return im_tensor
# start to track
handle = vot.VOT("polygon")
Polygon = handle.region()
box_cxcywh = vot.get_axis_aligned_bbox(Polygon)
# convert to xyxy
box_xyxy = ubox.xcycwh_to_xyxy(box_cxcywh)
image_file = handle.frame()
if not image_file:
sys.exit(0)
im_tensor = load_image(image_file, tracker.use_pil)
tracker.tracker.init_tracker(im_tensor, box_xyxy)
while True:
image_file = handle.frame()
if not image_file:
break
im_tensor = load_image(image_file, tracker.use_pil)
box_xyxy = tracker.tracker.predict_next_frame(im_tensor, box_xyxy)
box_xywh = ubox.xyxy_to_xywh(box_xyxy)
handle.report(
Rectangle(box_xywh[0], box_xywh[1], box_xywh[2], box_xywh[3]))
def get_rpn_box_proposals(im, args):
merge_cfg_from_file(args.rpn_cfg)
cfg.TEST.WEIGHTS = args.rpn_pkl
cfg.NUM_GPUS = 1
cfg.MODEL.RPN_ONLY = True
cfg.TEST.RPN_PRE_NMS_TOP_N = 10000
cfg.TEST.RPN_POST_NMS_TOP_N = 2000
assert_and_infer_cfg()
model = model_engine.initialize_model_from_cfg()
with c2_utils.NamedCudaScope(0):
boxes, scores = rpn_engine.im_proposals(model, im)
return boxes, scores
def __init__(self):
c2_utils.import_detectron_ops()
# OpenCL may be enabled by default in OpenCV3; disable it because it's not
# thread safe and causes unwanted GPU memory allocations.
cv2.ocl.setUseOpenCL(False)
merge_cfg_from_file(
'/home/king/Documents/measurement/detectron/configs/12_2017_baselines/e2e_keypoint_rcnn_X-101-32x8d-FPN_s1x.yaml'
)
cfg.NUM_GPUS = 1
weights = '/home/king/Documents/measurement/model_final.pkl'
assert_and_infer_cfg(cache_urls=False)
self.model = infer_engine.initialize_model_from_cfg(weights)
def get_rpn_box_proposals(im, args):
merge_cfg_from_file(args.rpn_cfg)
cfg.TEST.WEIGHTS = args.rpn_pkl
cfg.NUM_GPUS = 1
cfg.MODEL.RPN_ONLY = True
cfg.TEST.RPN_PRE_NMS_TOP_N = 10000
cfg.TEST.RPN_POST_NMS_TOP_N = 2000
assert_and_infer_cfg()
model = model_engine.initialize_model_from_cfg()
with c2_utils.NamedCudaScope(0):
boxes, scores = rpn_engine.im_proposals(model, im)
return boxes, scores
def main(args):
logger = logging.getLogger(__name__)
merge_cfg_from_file(args.cfg)
cfg.TEST.WEIGHTS = args.weights
cfg.NUM_GPUS = 1
assert_and_infer_cfg()
model = infer_engine.initialize_model_from_cfg()
dummy_coco_dataset = dummy_datasets.get_coco_dataset()
if os.path.isdir(args.im_or_folder):
im_list = glob.iglob(args.im_or_folder + '/*.' + args.image_ext)
else:
im_list = [args.im_or_folder]
for i, im_name in enumerate(im_list):
out_name = os.path.join(
args.output_dir, '{}'.format(os.path.basename(im_name) + '.pdf')
)
logger.info('Processing {} -> {}'.format(im_name, out_name))
im = cv2.imread(im_name)
timers = defaultdict(Timer)
t = time.time()
with c2_utils.NamedCudaScope(0):
cls_boxes, cls_segms, cls_keyps = infer_engine.im_detect_all(
model, im, None, timers=timers
)
logger.info('Inference time: {:.3f}s'.format(time.time() - t))
for k, v in timers.items():
logger.info(' | {}: {:.3f}s'.format(k, v.average_time))
if i == 0:
logger.info(
' \ Note: inference on the first image will be slower than the '
'rest (caches and auto-tuning need to warm up)'
)
vis_utils.vis_one_image(
im[:, :, ::-1], # BGR -> RGB for visualization
im_name,
args.output_dir,
cls_boxes,
cls_segms,
cls_keyps,
dataset=dummy_coco_dataset,
box_alpha=0.3,
show_class=True,
thresh=0.7,
kp_thresh=2
)
def main(args):
dummy_coco_dataset = dummy_datasets.get_coco_dataset()
cfg_orig = yaml.load(yaml.dump(cfg))
im = cv2.imread(args.im_file)
if args.rpn_pkl is not None:
proposal_boxes, _proposal_scores = get_rpn_box_proposals(im, args)
workspace.ResetWorkspace()
else:
proposal_boxes = None
cls_boxes, cls_segms, cls_keyps = None, None, None
for i in range(0, len(args.models_to_run), 2):
pkl = args.models_to_run[i]
yml = args.models_to_run[i + 1]
merge_cfg_from_cfg(cfg_orig)
merge_cfg_from_file(yml)
if len(pkl) > 0:
cfg.TEST.WEIGHTS = pkl
cfg.NUM_GPUS = 1
assert_and_infer_cfg()
model = model_engine.initialize_model_from_cfg()
with c2_utils.NamedCudaScope(0):
cls_boxes_, cls_segms_, cls_keyps_ = \
model_engine.im_detect_all(model, im, proposal_boxes)
cls_boxes = cls_boxes_ if cls_boxes_ is not None else cls_boxes
cls_segms = cls_segms_ if cls_segms_ is not None else cls_segms
cls_keyps = cls_keyps_ if cls_keyps_ is not None else cls_keyps
workspace.ResetWorkspace()
vis_utils.vis_one_image(
im[:, :, ::-1],
args.im_file,
args.output_dir,
cls_boxes,
cls_segms,
cls_keyps,
dataset=dummy_coco_dataset,
box_alpha=0.3,
show_class=True,
thresh=0.7,
kp_thresh=2
)
logger.info('{:d}/{:d}: Averge dequeue time: {:.3f}s [{:d}/{:d}]'.
format(i + 1, opts.num_batches, total_time / (i + 1),
roi_data_loader._minibatch_queue.qsize(),
opts.minibatch_queue_size))
# Sleep to simulate the time taken by running a little network
time.sleep(opts.sleep_time)
# To inspect:
# blobs = workspace.FetchBlobs(all_blobs)
# from IPython import embed; embed()
logger.info('Shutting down data loader (EnqueueBlob errors are ok)...')
roi_data_loader.shutdown()
if __name__ == '__main__':
workspace.GlobalInit(['caffe2', '--caffe2_log_level=0'])
logger = utils.logging.setup_logging(__name__)
logger.setLevel(logging.DEBUG)
logging.getLogger('roi_data.loader').setLevel(logging.INFO)
np.random.seed(cfg.RNG_SEED)
args = parse_args()
logger.info('Called with args:')
logger.info(args)
if args.cfg_file is not None:
merge_cfg_from_file(args.cfg_file)
if args.opts is not None:
merge_cfg_from_list(args.opts)
assert_and_infer_cfg()
logger.info('Running with config:')
logger.info(pprint.pformat(cfg))
main(args)
