def infer():
data_path = DatasetPath('val')
test_list = data_path.get_file_list()
cocoGt = COCO(test_list)
num_id_to_cat_id_map = {i + 1: v for i, v in enumerate(cocoGt.getCatIds())}
category_ids = cocoGt.getCatIds()
label_list = {
item['id']: item['name']
for item in cocoGt.loadCats(category_ids)
}
label_list[0] = ['background']
image_shape = [3, cfg.TEST.max_size, cfg.TEST.max_size]
class_nums = cfg.class_num
model = model_builder.RCNN(
add_conv_body_func=resnet.add_ResNet50_conv4_body,
add_roi_box_head_func=resnet.add_ResNet_roi_conv5_head,
use_pyreader=False,
is_train=False)
model.build_model(image_shape)
pred_boxes = model.eval_bbox_out()
if cfg.MASK_ON:
masks = model.eval_mask_out()
place = fluid.CUDAPlace(0) if cfg.use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
# yapf: disable
if cfg.pretrained_model:
def if_exist(var):
return os.path.exists(os.path.join(cfg.pretrained_model, var.name))
fluid.io.load_vars(exe, cfg.pretrained_model, predicate=if_exist)
# yapf: enable
infer_reader = reader.infer()
feeder = fluid.DataFeeder(place=place, feed_list=model.feeds())
dts_res = []
segms_res = []
if cfg.MASK_ON:
fetch_list = [pred_boxes, masks]
else:
fetch_list = [pred_boxes]
data = next(infer_reader())
im_info = [data[0][1]]
result = exe.run(fetch_list=[v.name for v in fetch_list],
feed=feeder.feed(data),
return_numpy=False)
pred_boxes_v = result[0]
if cfg.MASK_ON:
masks_v = result[1]
new_lod = pred_boxes_v.lod()
nmsed_out = pred_boxes_v
path = os.path.join(cfg.image_path, cfg.image_name)
image = None
if cfg.MASK_ON:
segms_out = segm_results(nmsed_out, masks_v, im_info)
image = draw_mask_on_image(path, segms_out, cfg.draw_threshold)
draw_bounding_box_on_image(path, nmsed_out, cfg.draw_threshold, label_list,
num_id_to_cat_id_map, image)
def train():
learning_rate = cfg.learning_rate
image_shape = [3, cfg.TRAIN.max_size, cfg.TRAIN.max_size]
devices_num = get_device_num()
total_batch_size = devices_num * cfg.TRAIN.im_per_batch
use_random = True
model = model_builder.RCNN(
add_conv_body_func=resnet.
add_ResNet50_conv4_body, # res4: [-1, 1024, 84, 84]
add_roi_box_head_func=resnet.
add_ResNet_roi_conv5_head, # res5: [-1, 2048, 7, 7]
use_pyreader=cfg.use_pyreader,
use_random=use_random)
model.build_model(image_shape)
losses, keys = model.loss()
loss = losses[0]
fetch_list = losses
boundaries = cfg.lr_steps
gamma = cfg.lr_gamma
step_num = len(cfg.lr_steps)
values = [learning_rate * (gamma**i) for i in range(step_num + 1)]
lr = exponential_with_warmup_decay(learning_rate=learning_rate,
boundaries=boundaries,
values=values,
warmup_iter=cfg.warm_up_iter,
warmup_factor=cfg.warm_up_factor)
optimizer = fluid.optimizer.Momentum(
learning_rate=lr,
regularization=fluid.regularizer.L2Decay(cfg.weight_decay),
momentum=cfg.momentum)
optimizer.minimize(loss)
fetch_list = fetch_list + [lr]
for var in fetch_list:
var.persistable = True
gpu_id = int(os.environ.get('FLAGS_selected_gpus', 0))
place = fluid.CUDAPlace(gpu_id) if cfg.use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
exe.run(fluid.default_startup_program())
if cfg.pretrained_model:
def if_exist(var):
return os.path.exists(os.path.join(cfg.pretrained_model, var.name))
fluid.io.load_vars(exe, cfg.pretrained_model, predicate=if_exist)
if cfg.parallel:
build_strategy = fluid.BuildStrategy()
build_strategy.memory_optimize = False
build_strategy.enable_inplace = True
exec_strategy = fluid.ExecutionStrategy()
exec_strategy.num_iteration_per_drop_scope = 10
if num_trainers > 1 and cfg.use_gpu:
dist_utils.prepare_for_multi_process(exe, build_strategy,
fluid.default_main_program())
# the process is fast when num_threads is 1 for multi-process training
exec_strategy.num_threads = 1
train_exe = fluid.ParallelExecutor(use_cuda=bool(cfg.use_gpu),
loss_name=loss.name,
build_strategy=build_strategy,
exec_strategy=exec_strategy)
else:
train_exe = exe
shuffle = True
# NOTE: do not shuffle dataset when using multi-process training
shuffle_seed = None
if num_trainers > 1:
shuffle_seed = 1
if cfg.use_pyreader:
train_reader = reader.train(batch_size=cfg.TRAIN.im_per_batch,
total_batch_size=total_batch_size,
padding_total=cfg.TRAIN.padding_minibatch,
shuffle=shuffle,
shuffle_seed=shuffle_seed)
if num_trainers > 1:
assert shuffle_seed is not None, "If num_trainers > 1, the shuffle_seed must be set, because the order of batch data generated by reader must be the same in the respective processes"
train_reader = fluid.contrib.reader.distributed_batch_reader(
train_reader)
py_reader = model.py_reader
py_reader.decorate_paddle_reader(train_reader)
else:
if num_trainers > 1:
shuffle = False
train_reader = reader.train(batch_size=total_batch_size,
shuffle=shuffle)
feeder = fluid.DataFeeder(place=place, feed_list=model.feeds())
def save_model(postfix):
model_path = os.path.join(cfg.model_save_dir, postfix)
if os.path.isdir(model_path):
shutil.rmtree(model_path)
fluid.io.save_persistables(exe, model_path)
def train_loop_pyreader():
py_reader.start()
train_stats = TrainingStats(cfg.log_window, keys)
try:
start_time = time.time()
for iter_id in range(cfg.max_iter):
prev_start_time = start_time
start_time = time.time()
outs = train_exe.run(fetch_list=[v.name for v in fetch_list])
stats = {
k: np.array(v).mean()
for k, v in zip(keys, outs[:-1])
}
train_stats.update(stats)
logs = train_stats.log()
strs = '{}, iter: {}, lr: {:.5f}, {}, time: {:.3f}'.format(
now_time(), iter_id, np.mean(outs[-1]), logs,
start_time - prev_start_time)
print(strs)
sys.stdout.flush()
if (iter_id + 1) % cfg.TRAIN.snapshot_iter == 0:
save_model("model_iter{}".format(iter_id))
end_time = time.time()
total_time = end_time - first_start_time
last_loss = np.array(outs[0]).mean()
except (StopIteration, fluid.core.EOFException):
py_reader.reset()
def train_loop():
train_stats = TrainingStats(cfg.log_window, keys)
start_time = time.time()
for iter_id, data in enumerate(train_reader()):
prev_start_time = start_time
start_time = time.time()
outs = train_exe.run(fetch_list=[v.name for v in fetch_list],
feed=feeder.feed(data))
stats = {k: np.array(v).mean() for k, v in zip(keys, outs[:-1])}
train_stats.update(stats)
logs = train_stats.log()
stats = '{}, iter: {}, lr: {:.5f}, {}, time: {:.3f}'.format(
now_time(), iter_id, np.mean(outs[-1]), logs,
start_time - prev_start_time)
print(stats)
sys.stdout.flush()
if (iter_id + 1) % cfg.TRAIN.snapshot_iter == 0:
save_model("model_iter{}".format(iter_id))
if (iter_id + 1) == cfg.max_iter:
break
end_time = time.time()
total_time = end_time - start_time
last_loss = np.array(outs[0]).mean()
if cfg.use_pyreader:
train_loop_pyreader()
else:
train_loop()
save_model('model_final')
def infer():
try:
from pycocotools.coco import COCO
from pycocotools.cocoeval import COCOeval, Params
data_path = DatasetPath('val')
test_list = data_path.get_file_list()
coco_api = COCO(test_list)
cid = coco_api.getCatIds()
cat_id_to_num_id_map = {
v: i + 1
for i, v in enumerate(coco_api.getCatIds())
}
category_ids = coco_api.getCatIds()
labels_map = {
cat_id_to_num_id_map[item['id']]: item['name']
for item in coco_api.loadCats(category_ids)
}
labels_map[0] = 'background'
except:
print("The COCO dataset or COCO API is not exist, use the default "
"mapping of class index and real category name on COCO17.")
assert cfg.dataset == 'coco2017'
labels_map = coco17_labels()
image_shape = [3, cfg.TEST.max_size, cfg.TEST.max_size]
class_nums = cfg.class_num
model = model_builder.RCNN(
add_conv_body_func=resnet.add_ResNet50_conv4_body,
add_roi_box_head_func=resnet.add_ResNet_roi_conv5_head,
use_pyreader=False,
mode='infer')
model.build_model(image_shape)
pred_boxes = model.eval_bbox_out()
if cfg.MASK_ON:
masks = model.eval_mask_out()
place = fluid.CUDAPlace(0) if cfg.use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
# yapf: disable
if not os.path.exists(cfg.pretrained_model):
raise ValueError("Model path [%s] does not exist." % (cfg.pretrained_model))
def if_exist(var):
return os.path.exists(os.path.join(cfg.pretrained_model, var.name))
fluid.io.load_vars(exe, cfg.pretrained_model, predicate=if_exist)
# yapf: enable
infer_reader = reader.infer(cfg.image_path)
feeder = fluid.DataFeeder(place=place, feed_list=model.feeds())
dts_res = []
segms_res = []
if cfg.MASK_ON:
fetch_list = [pred_boxes, masks]
else:
fetch_list = [pred_boxes]
data = next(infer_reader())
im_info = [data[0][1]]
result = exe.run(fetch_list=[v.name for v in fetch_list],
feed=feeder.feed(data),
return_numpy=False)
pred_boxes_v = result[0]
if cfg.MASK_ON:
masks_v = result[1]
new_lod = pred_boxes_v.lod()
nmsed_out = pred_boxes_v
image = None
if cfg.MASK_ON:
segms_out = segm_results(nmsed_out, masks_v, im_info)
image = draw_mask_on_image(cfg.image_path, segms_out,
cfg.draw_threshold)
draw_bounding_box_on_image(cfg.image_path, nmsed_out, cfg.draw_threshold,
labels_map, image)
def train():
learning_rate = cfg.learning_rate
image_shape = [3, cfg.TRAIN.max_size, cfg.TRAIN.max_size]
if cfg.enable_ce:
fluid.default_startup_program().random_seed = 1000
fluid.default_main_program().random_seed = 1000
import random
random.seed(0)
np.random.seed(0)
devices = os.getenv("CUDA_VISIBLE_DEVICES") or ""
devices_num = len(devices.split(","))
total_batch_size = devices_num * cfg.TRAIN.im_per_batch
use_random = True
if cfg.enable_ce:
use_random = False
model = model_builder.RCNN(
add_conv_body_func=resnet.add_ResNet50_conv4_body,
add_roi_box_head_func=resnet.add_ResNet_roi_conv5_head,
use_pyreader=cfg.use_pyreader,
use_random=use_random)
model.build_model(image_shape)
losses, keys = model.loss()
loss = losses[0]
fetch_list = losses
boundaries = cfg.lr_steps
gamma = cfg.lr_gamma
step_num = len(cfg.lr_steps)
values = [learning_rate * (gamma**i) for i in range(step_num + 1)]
lr = exponential_with_warmup_decay(learning_rate=learning_rate,
boundaries=boundaries,
values=values,
warmup_iter=cfg.warm_up_iter,
warmup_factor=cfg.warm_up_factor)
optimizer = fluid.optimizer.Momentum(
learning_rate=lr,
regularization=fluid.regularizer.L2Decay(cfg.weight_decay),
momentum=cfg.momentum)
optimizer.minimize(loss)
fetch_list = fetch_list + [lr]
for var in fetch_list:
var.persistable = True
#fluid.memory_optimize(fluid.default_main_program(), skip_opt_set=set(fetch_list))
place = fluid.CUDAPlace(0) if cfg.use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
exe.run(fluid.default_startup_program())
if cfg.pretrained_model:
def if_exist(var):
return os.path.exists(os.path.join(cfg.pretrained_model, var.name))
fluid.io.load_vars(exe, cfg.pretrained_model, predicate=if_exist)
if cfg.parallel:
build_strategy = fluid.BuildStrategy()
build_strategy.memory_optimize = False
build_strategy.enable_inplace = False
exec_strategy = fluid.ExecutionStrategy()
exec_strategy.use_experimental_executor = True
train_exe = fluid.ParallelExecutor(use_cuda=bool(cfg.use_gpu),
loss_name=loss.name,
build_strategy=build_strategy,
exec_strategy=exec_strategy)
else:
train_exe = exe
shuffle = True
if cfg.enable_ce:
shuffle = False
if cfg.use_pyreader:
train_reader = reader.train(batch_size=cfg.TRAIN.im_per_batch,
total_batch_size=total_batch_size,
padding_total=cfg.TRAIN.padding_minibatch,
shuffle=shuffle)
py_reader = model.py_reader
py_reader.decorate_paddle_reader(train_reader)
else:
train_reader = reader.train(batch_size=total_batch_size,
shuffle=shuffle)
feeder = fluid.DataFeeder(place=place, feed_list=model.feeds())
def save_model(postfix):
model_path = os.path.join(cfg.model_save_dir, postfix)
if os.path.isdir(model_path):
shutil.rmtree(model_path)
fluid.io.save_persistables(exe, model_path)
def train_loop_pyreader():
py_reader.start()
train_stats = TrainingStats(cfg.log_window, keys)
try:
start_time = time.time()
prev_start_time = start_time
for iter_id in range(cfg.max_iter):
prev_start_time = start_time
start_time = time.time()
outs = train_exe.run(fetch_list=[v.name for v in fetch_list])
stats = {
k: np.array(v).mean()
for k, v in zip(keys, outs[:-1])
}
train_stats.update(stats)
logs = train_stats.log()
strs = '{}, iter: {}, lr: {:.5f}, {}, time: {:.3f}'.format(
now_time(), iter_id, np.mean(outs[-1]), logs,
start_time - prev_start_time)
print(strs)
sys.stdout.flush()
if (iter_id + 1) % cfg.TRAIN.snapshot_iter == 0:
save_model("model_iter{}".format(iter_id))
end_time = time.time()
total_time = end_time - start_time
last_loss = np.array(outs[0]).mean()
if cfg.enable_ce:
gpu_num = devices_num
epoch_idx = iter_id + 1
loss = last_loss
print("kpis\teach_pass_duration_card%s\t%s" %
(gpu_num, total_time / epoch_idx))
print("kpis\ttrain_loss_card%s\t%s" % (gpu_num, loss))
except (StopIteration, fluid.core.EOFException):
py_reader.reset()
def train_loop():
start_time = time.time()
prev_start_time = start_time
start = start_time
train_stats = TrainingStats(cfg.log_window, keys)
for iter_id, data in enumerate(train_reader()):
prev_start_time = start_time
start_time = time.time()
outs = train_exe.run(fetch_list=[v.name for v in fetch_list],
feed=feeder.feed(data))
stats = {k: np.array(v).mean() for k, v in zip(keys, outs[:-1])}
train_stats.update(stats)
logs = train_stats.log()
strs = '{}, iter: {}, lr: {:.5f}, {}, time: {:.3f}'.format(
now_time(), iter_id, np.mean(outs[-1]), logs,
start_time - prev_start_time)
print(strs)
sys.stdout.flush()
if (iter_id + 1) % cfg.TRAIN.snapshot_iter == 0:
save_model("model_iter{}".format(iter_id))
if (iter_id + 1) == cfg.max_iter:
break
end_time = time.time()
total_time = end_time - start_time
last_loss = np.array(outs[0]).mean()
# only for ce
if cfg.enable_ce:
gpu_num = devices_num
epoch_idx = iter_id + 1
loss = last_loss
print("kpis\teach_pass_duration_card%s\t%s" %
(gpu_num, total_time / epoch_idx))
print("kpis\ttrain_loss_card%s\t%s" % (gpu_num, loss))
return np.mean(every_pass_loss)
if cfg.use_pyreader:
train_loop_pyreader()
else:
train_loop()
save_model('model_final')
def eval():
data_path = DatasetPath('val')
test_list = data_path.get_file_list()
image_shape = [3, cfg.TEST.max_size, cfg.TEST.max_size]
class_nums = cfg.class_num
devices = os.getenv("CUDA_VISIBLE_DEVICES") or ""
devices_num = len(devices.split(","))
total_batch_size = devices_num * cfg.TRAIN.im_per_batch
cocoGt = COCO(test_list)
num_id_to_cat_id_map = {i + 1: v for i, v in enumerate(cocoGt.getCatIds())}
category_ids = cocoGt.getCatIds()
label_list = {
item['id']: item['name']
for item in cocoGt.loadCats(category_ids)
}
label_list[0] = ['background']
model = model_builder.RCNN(
add_conv_body_func=resnet.add_ResNet50_conv4_body,
add_roi_box_head_func=resnet.add_ResNet_roi_conv5_head,
use_pyreader=False,
mode='val')
model.build_model(image_shape)
pred_boxes = model.eval_bbox_out()
if cfg.MASK_ON:
masks = model.eval_mask_out()
place = fluid.CUDAPlace(0) if cfg.use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
exe.run(fluid.default_startup_program())
# yapf: disable
if cfg.pretrained_model:
def if_exist(var):
return os.path.exists(os.path.join(cfg.pretrained_model, var.name))
fluid.io.load_vars(exe, cfg.pretrained_model, predicate=if_exist)
# yapf: enable
test_reader = reader.test(total_batch_size)
feeder = fluid.DataFeeder(place=place, feed_list=model.feeds())
dts_res = []
segms_res = []
if cfg.MASK_ON:
fetch_list = [pred_boxes, masks]
else:
fetch_list = [pred_boxes]
eval_start = time.time()
for batch_id, batch_data in enumerate(test_reader()):
start = time.time()
im_info = []
for data in batch_data:
im_info.append(data[1])
results = exe.run(fetch_list=[v.name for v in fetch_list],
feed=feeder.feed(batch_data),
return_numpy=False)
pred_boxes_v = results[0]
if cfg.MASK_ON:
masks_v = results[1]
new_lod = pred_boxes_v.lod()
nmsed_out = pred_boxes_v
dts_res += get_dt_res(total_batch_size, new_lod[0], nmsed_out,
batch_data, num_id_to_cat_id_map)
if cfg.MASK_ON and np.array(masks_v).shape != (1, 1):
segms_out = segm_results(nmsed_out, masks_v, im_info)
segms_res += get_segms_res(total_batch_size, new_lod[0], segms_out,
batch_data, num_id_to_cat_id_map)
end = time.time()
print('batch id: {}, time: {}'.format(batch_id, end - start))
eval_end = time.time()
total_time = eval_end - eval_start
print('average time of eval is: {}'.format(total_time / (batch_id + 1)))
assert len(dts_res) > 0, "The number of valid bbox detected is zero.\n \
Please use reasonable model and check input data."
if cfg.MASK_ON:
assert len(
segms_res) > 0, "The number of valid mask detected is zero.\n \
Please use reasonable model and check input data."
with io.open("detection_bbox_result.json", 'w') as outfile:
encode_func = unicode if six.PY2 else str
outfile.write(encode_func(json.dumps(dts_res)))
print("start evaluate bbox using coco api")
cocoDt = cocoGt.loadRes("detection_bbox_result.json")
cocoEval = COCOeval(cocoGt, cocoDt, 'bbox')
cocoEval.evaluate()
cocoEval.accumulate()
cocoEval.summarize()
if cfg.MASK_ON:
with io.open("detection_segms_result.json", 'w') as outfile:
encode_func = unicode if six.PY2 else str
outfile.write(encode_func(json.dumps(segms_res)))
print("start evaluate mask using coco api")
cocoDt = cocoGt.loadRes("detection_segms_result.json")
cocoEval = COCOeval(cocoGt, cocoDt, 'segm')
cocoEval.evaluate()
cocoEval.accumulate()
cocoEval.summarize()
'hair drier',
'toothbrush'
] #80
#config.py & (main in utility.py)
args = parse_args()
print_arguments(args)
#Step 1
image_shape = [3, cfg.TEST.max_size, cfg.TEST.max_size]
class_nums = cfg.class_num
#Step 2
model = model_builder.RCNN(
add_conv_body_func=resnet.add_ResNet50_conv4_body,
add_roi_box_head_func=resnet.add_ResNet_roi_conv5_head,
use_pyreader=False,
mode='infer')
model.build_model(image_shape)
model_pred_boxes = model.eval_bbox_out()
model_masks = model.eval_mask_out()
place = fluid.CUDAPlace(0) if cfg.use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
#Step 3
def if_exist(var):
return os.path.exists(os.path.join(cfg.pretrained_model, var.name))
fluid.io.load_vars(exe, cfg.pretrained_model, predicate=if_exist)
def train():
learning_rate = cfg.learning_rate
image_shape = [3, cfg.TRAIN.max_size, cfg.TRAIN.max_size]
num_iterations = cfg.max_iter
devices = os.getenv("CUDA_VISIBLE_DEVICES") or ""
devices_num = len(devices.split(","))
total_batch_size = devices_num * cfg.TRAIN.im_per_batch
model = model_builder.RCNN(
add_conv_body_func=resnet.add_ResNet50_conv4_body,
add_roi_box_head_func=resnet.add_ResNet_roi_conv5_head,
use_pyreader=cfg.use_pyreader,
use_random=False)
model.build_model(image_shape)
losses, keys = model.loss()
loss = losses[0]
fetch_list = [loss]
boundaries = cfg.lr_steps
gamma = cfg.lr_gamma
step_num = len(cfg.lr_steps)
values = [learning_rate * (gamma**i) for i in range(step_num + 1)]
optimizer = fluid.optimizer.Momentum(
learning_rate=exponential_with_warmup_decay(
learning_rate=learning_rate,
boundaries=boundaries,
values=values,
warmup_iter=500,
warmup_factor=1.0 / 3.0),
regularization=fluid.regularizer.L2Decay(0.0001),
momentum=0.9)
optimizer.minimize(loss)
fluid.memory_optimize(fluid.default_main_program())
place = fluid.CUDAPlace(0) if cfg.use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
exe.run(fluid.default_startup_program())
if cfg.pretrained_model:
def if_exist(var):
return os.path.exists(os.path.join(cfg.pretrained_model, var.name))
fluid.io.load_vars(exe, cfg.pretrained_model, predicate=if_exist)
if cfg.parallel:
train_exe = fluid.ParallelExecutor(use_cuda=bool(cfg.use_gpu),
loss_name=loss.name)
if cfg.use_pyreader:
train_reader = reader.train(batch_size=cfg.TRAIN.im_per_batch,
total_batch_size=total_batch_size,
padding_total=cfg.TRAIN.padding_minibatch,
shuffle=False)
py_reader = model.py_reader
py_reader.decorate_paddle_reader(train_reader)
else:
train_reader = reader.train(batch_size=total_batch_size, shuffle=False)
feeder = fluid.DataFeeder(place=place, feed_list=model.feeds())
def run(iterations):
reader_time = []
run_time = []
total_images = 0
for batch_id in range(iterations):
start_time = time.time()
data = next(train_reader())
end_time = time.time()
reader_time.append(end_time - start_time)
start_time = time.time()
if cfg.parallel:
outs = train_exe.run(fetch_list=[v.name for v in fetch_list],
feed=feeder.feed(data))
else:
outs = exe.run(fluid.default_main_program(),
fetch_list=[v.name for v in fetch_list],
feed=feeder.feed(data))
end_time = time.time()
run_time.append(end_time - start_time)
total_images += len(data)
print("Batch {:d}, loss {:.6f} ".format(batch_id,
np.mean(outs[0])))
return reader_time, run_time, total_images
def run_pyreader(iterations):
reader_time = [0]
run_time = []
total_images = 0
py_reader.start()
try:
for batch_id in range(iterations):
start_time = time.time()
if cfg.parallel:
outs = train_exe.run(
fetch_list=[v.name for v in fetch_list])
else:
outs = exe.run(fluid.default_main_program(),
fetch_list=[v.name for v in fetch_list])
end_time = time.time()
run_time.append(end_time - start_time)
total_images += devices_num
print("Batch {:d}, loss {:.6f} ".format(
batch_id, np.mean(outs[0])))
except fluid.core.EOFException:
py_reader.reset()
return reader_time, run_time, total_images
run_func = run if not cfg.use_pyreader else run_pyreader
# warm-up
run_func(2)
# profiling
start = time.time()
if cfg.use_profile:
with profiler.profiler('GPU', 'total', '/tmp/profile_file'):
reader_time, run_time, total_images = run_func(num_iterations)
else:
reader_time, run_time, total_images = run_func(num_iterations)
end = time.time()
total_time = end - start
print(
"Total time: {0}, reader time: {1} s, run time: {2} s, images/s: {3}".
format(total_time, np.sum(reader_time), np.sum(run_time),
total_images / total_time))