def convert(cls, npy_model, fluid_path):
import paddle.v2.fluid as fluid
data_layer = fluid.layers.data(name="data",
shape=[3, 368, 368],
dtype="float32")
feed_data = {"data": data_layer}
net = cls(feed_data)
place = fluid.CPUPlace()
exe = fluid.Executor(place)
exe.run(fluid.default_startup_program())
net.load(data_path=npy_model, exe=exe, place=place)
fluid.io.save_persistables(executor=exe, dirname=fluid_path)
def run_benchmark(model, args):
if args.use_cprof:
pr = cProfile.Profile()
pr.enable()
start_time = time.time()
word_dict = paddle.dataset.imdb.word_dict()
print("load word dict successfully")
dict_dim = len(word_dict)
data = fluid.layers.data(name="words",
shape=[1],
dtype="int64",
lod_level=1)
label = fluid.layers.data(name="label", shape=[1], dtype="int64")
prediction = model(data, dict_dim)
cost = fluid.layers.cross_entropy(input=prediction, label=label)
avg_cost = fluid.layers.mean(x=cost)
adam_optimizer = fluid.optimizer.Adam(learning_rate=0.002)
adam_optimizer.minimize(avg_cost)
accuracy = fluid.evaluator.Accuracy(input=prediction, label=label)
train_reader = paddle.batch(paddle.reader.shuffle(
paddle.dataset.imdb.train(word_dict), buf_size=25000),
batch_size=args.batch_size)
place = core.CPUPlace() if args.device == 'CPU' else core.CUDAPlace(0)
exe = fluid.Executor(place)
exe.run(fluid.default_startup_program())
for it, pass_id in enumerate(xrange(args.pass_num)):
accuracy.reset(exe)
if iter == args.iterations:
break
for data in train_reader():
tensor_words = to_lodtensor(map(lambda x: x[0], data), place)
label = np.array(map(lambda x: x[1], data)).astype("int64")
label = label.reshape([args.batch_size, 1])
tensor_label = fluid.LoDTensor()
tensor_label.set(label, place)
loss, acc = exe.run(fluid.default_main_program(),
feed={
"words": tensor_words,
"label": tensor_label
},
fetch_list=[avg_cost] + accuracy.metrics)
pass_acc = accuracy.eval(exe)
print("Iter: %d, loss: %s, acc: %s, pass_acc: %s" %
(it, str(loss), str(acc), str(pass_acc)))
def run_benchmark(model, args):
if args.use_cprof:
pr = cProfile.Profile()
pr.enable()
start_time = time.time()
word_dict = paddle.dataset.imdb.word_dict()
print("load word dict successfully")
dict_dim = len(word_dict)
data = fluid.layers.data(name="words",
shape=[args.seq_len * args.batch_size, 1],
append_batch_size=False,
dtype="int64",
lod_level=1)
label = fluid.layers.data(name="label",
shape=[args.batch_size, 1],
append_batch_size=False,
dtype="int64")
prediction = model(data, dict_dim)
cost = fluid.layers.cross_entropy(input=prediction, label=label)
avg_cost = fluid.layers.mean(x=cost)
adam_optimizer = fluid.optimizer.Adam(learning_rate=0.002)
adam_optimizer.minimize(avg_cost)
accuracy = fluid.evaluator.Accuracy(input=prediction, label=label)
train_reader = paddle.batch(
paddle.reader.shuffle(paddle.dataset.imdb.train(word_dict),
buf_size=25000), # only for speed
batch_size=args.batch_size)
place = fluid.CPUPlace() if args.device == 'CPU' else fluid.GPUPlace(0)
exe = fluid.Executor(place)
exe.run(fluid.default_startup_program())
for it, pass_id in enumerate(xrange(args.pass_num)):
accuracy.reset(exe)
if it == args.iterations:
break
for batch_id, data in enumerate(train_reader()):
chopped_data = chop_data(data,
chop_len=args.seq_len,
batch_size=args.batch_size)
tensor_words, tensor_label = prepare_feed_data(chopped_data, place)
loss, acc = exe.run(fluid.default_main_program(),
feed={
"words": tensor_words,
"label": tensor_label
},
fetch_list=[avg_cost] + accuracy.metrics)
pass_acc = accuracy.eval(exe)
print("pass=%d, batch=%d, loss=%f, acc=%f, pass_acc=%f" %
(it, batch_id, loss, acc, pass_acc))
def run_benchmark(model, args):
if args.use_cprof:
pr = cProfile.Profile()
pr.enable()
start_time = time.time()
images = fluid.layers.data(name='pixel', shape=[1, 28, 28], dtype=DTYPE)
label = fluid.layers.data(name='label', shape=[1], dtype='int64')
predict = model(images)
cost = fluid.layers.cross_entropy(input=predict, label=label)
avg_cost = fluid.layers.mean(x=cost)
opt = fluid.optimizer.AdamOptimizer(
learning_rate=0.001, beta1=0.9, beta2=0.999)
opt.minimize(avg_cost)
accuracy = fluid.evaluator.Accuracy(input=predict, label=label)
train_reader = paddle.batch(
paddle.dataset.mnist.train(), batch_size=args.batch_size)
place = fluid.CPUPlace()
exe = fluid.Executor(place)
exe.run(fluid.default_startup_program())
for pass_id in range(args.pass_num):
accuracy.reset(exe)
pass_start = time.clock()
for batch_id, data in enumerate(train_reader()):
img_data = np.array(
map(lambda x: x[0].reshape([1, 28, 28]), data)).astype(DTYPE)
y_data = np.array(map(lambda x: x[1], data)).astype("int64")
y_data = y_data.reshape([len(y_data), 1])
start = time.clock()
outs = exe.run(fluid.default_main_program(),
feed={"pixel": img_data,
"label": y_data},
fetch_list=[avg_cost] + accuracy.metrics)
end = time.clock()
loss = np.array(outs[0])
acc = np.array(outs[1])
print("pass=%d, batch=%d, loss=%f, error=%f, elapse=%f" %
(pass_id, batch_id, loss, 1 - acc, (end - start) / 1000))
pass_end = time.clock()
test_avg_acc = eval_test(exe, accuracy, avg_cost)
pass_acc = accuracy.eval(exe)
print("pass=%d, test_avg_acc=%f, test_avg_acc=%f, elapse=%f" %
(pass_id, pass_acc, test_avg_acc, (pass_end - pass_start) / 1000))
def test_nvprof(self):
if not fluid.core.is_compile_gpu():
return
epoc = 8
dshape = [4, 3, 28, 28]
data = layers.data(name='data', shape=[3, 28, 28], dtype='float32')
conv = layers.conv2d(data, 20, 3, stride=[1, 1], padding=[1, 1])
place = fluid.GPUPlace(0)
exe = fluid.Executor(place)
exe.run(fluid.default_startup_program())
with profiler.cuda_profiler("cuda_profiler.txt", 'csv') as nvprof:
for i in range(epoc):
input = np.random.random(dshape).astype('float32')
exe.run(fluid.default_main_program(), feed={'data': input})
def main():
BATCH_SIZE = 100
PASS_NUM = 5
word_dict = paddle.dataset.imdb.word_dict()
print "load word dict successfully"
dict_dim = len(word_dict)
class_dim = 2
data = fluid.layers.data(name="words",
shape=[1],
dtype="int64",
lod_level=1)
label = fluid.layers.data(name="label", shape=[1], dtype="int64")
cost, accuracy, acc_out = stacked_lstm_net(data,
label,
input_dim=dict_dim,
class_dim=class_dim)
train_data = paddle.batch(paddle.reader.shuffle(
paddle.dataset.imdb.train(word_dict), buf_size=1000),
batch_size=BATCH_SIZE)
place = fluid.CPUPlace()
exe = fluid.Executor(place)
feeder = fluid.DataFeeder(feed_list=[data, label], place=place)
exe.run(fluid.default_startup_program())
for pass_id in xrange(PASS_NUM):
accuracy.reset(exe)
for data in train_data():
cost_val, acc_val = exe.run(fluid.default_main_program(),
feed=feeder.feed(data),
fetch_list=[cost, acc_out])
pass_acc = accuracy.eval(exe)
print("cost=" + str(cost_val) + " acc=" + str(acc_val) +
" pass_acc=" + str(pass_acc))
if cost_val < 1.0 and acc_val > 0.8:
exit(0)
exit(1)
def load(self, data_path, exe=None, place=None, ignore_missing=False):
'''Load network weights.
data_path: The path to the numpy-serialized network weights
ignore_missing: If true, serialized weights for missing layers are ignored.
'''
fluid = import_fluid()
#load fluid mode directly
if os.path.isdir(data_path):
assert (exe is not None), \
'must provide a executor to load fluid model'
fluid.io.load_persistables_if_exist(executor=exe,
dirname=data_path)
return True
#load model from a npy file
if exe is None or place is None:
if self.paddle_env is None:
place = fluid.CPUPlace()
exe = fluid.Executor(place)
self.paddle_env = {'place': place, 'exe': exe}
exe = exe.run(fluid.default_startup_program())
else:
place = self.paddle_env['place']
exe = self.paddle_env['exe']
data_dict = np.load(data_path).item()
for op_name in data_dict:
if op_name not in self.layers.keys():
continue
layer = self.layers[op_name]
for param_name, data in data_dict[op_name].iteritems():
try:
name = '%s_%s' % (op_name, param_name)
v = fluid.global_scope().find_var(name)
w = v.get_tensor()
w.set(data, place)
except ValueError:
if not ignore_missing:
raise
return True
def main():
BATCH_SIZE = 100
PASS_NUM = 5
word_dict = paddle.dataset.imdb.word_dict()
print "load word dict successfully"
dict_dim = len(word_dict)
class_dim = 2
cost, acc = lstm_net(dict_dim=dict_dim, class_dim=class_dim)
train_data = paddle.batch(paddle.reader.shuffle(
paddle.dataset.imdb.train(word_dict), buf_size=BATCH_SIZE * 10),
batch_size=BATCH_SIZE)
place = fluid.CPUPlace()
exe = fluid.Executor(place)
exe.run(fluid.default_startup_program())
for pass_id in xrange(PASS_NUM):
for data in train_data():
chopped_data = chop_data(data)
tensor_words, tensor_label = prepare_feed_data(chopped_data, place)
outs = exe.run(fluid.default_main_program(),
feed={
"words": tensor_words,
"label": tensor_label
},
fetch_list=[cost, acc])
cost_val = np.array(outs[0])
acc_val = np.array(outs[1])
print("cost=" + str(cost_val) + " acc=" + str(acc_val))
if acc_val > 0.7:
exit(0)
exit(1)
def main():
BATCH_SIZE = 100
PASS_NUM = 5
word_dict = paddle.dataset.imdb.word_dict()
print "load word dict successfully"
dict_dim = len(word_dict)
class_dim = 2
data = fluid.layers.data(
name="words", shape=[1], dtype="int64", lod_level=1)
label = fluid.layers.data(name="label", shape=[1], dtype="int64")
cost, accuracy, acc_out = stacked_lstm_net(
data, label, input_dim=dict_dim, class_dim=class_dim)
train_data = paddle.batch(
paddle.reader.shuffle(
paddle.dataset.imdb.train(word_dict), buf_size=1000),
batch_size=BATCH_SIZE)
place = fluid.CPUPlace()
exe = fluid.Executor(place)
feeder = fluid.DataFeeder(feed_list=[data, label], place=place)
exe.run(fluid.default_startup_program())
for pass_id in xrange(PASS_NUM):
accuracy.reset(exe)
for data in train_data():
cost_val, acc_val = exe.run(fluid.default_main_program(),
feed=feeder.feed(data),
fetch_list=[cost, acc_out])
pass_acc = accuracy.eval(exe)
print("cost=" + str(cost_val) + " acc=" + str(acc_val) +
" pass_acc=" + str(pass_acc))
if cost_val < 1.0 and acc_val > 0.8:
exit(0)
exit(1)
def main():
BATCH_SIZE = 100
PASS_NUM = 5
word_dict = paddle.dataset.imdb.word_dict()
print "load word dict successfully"
dict_dim = len(word_dict)
class_dim = 2
cost, acc = lstm_net(dict_dim=dict_dim, class_dim=class_dim)
train_data = paddle.batch(
paddle.reader.shuffle(
paddle.dataset.imdb.train(word_dict), buf_size=BATCH_SIZE * 10),
batch_size=BATCH_SIZE)
place = fluid.CPUPlace()
exe = fluid.Executor(place)
exe.run(fluid.default_startup_program())
for pass_id in xrange(PASS_NUM):
for data in train_data():
chopped_data = chop_data(data)
tensor_words, tensor_label = prepare_feed_data(chopped_data, place)
outs = exe.run(fluid.default_main_program(),
feed={"words": tensor_words,
"label": tensor_label},
fetch_list=[cost, acc])
cost_val = np.array(outs[0])
acc_val = np.array(outs[1])
print("cost=" + str(cost_val) + " acc=" + str(acc_val))
if acc_val > 0.7:
exit(0)
exit(1)
def run_benchmark(model, args):
if args.use_cprof:
pr = cProfile.Profile()
pr.enable()
start_time = time.time()
class_dim = 102
dshape = [3, 224, 224] if args.order == 'NCHW' else [224, 224, 3]
input = fluid.layers.data(name='data', shape=dshape, dtype='float32')
label = fluid.layers.data(name='label', shape=[1], dtype='int64')
predict = model(input, class_dim)
cost = fluid.layers.cross_entropy(input=predict, label=label)
avg_cost = fluid.layers.mean(x=cost)
optimizer = fluid.optimizer.Momentum(learning_rate=0.01, momentum=0.9)
opts = optimizer.minimize(avg_cost)
accuracy = fluid.evaluator.Accuracy(input=predict, label=label)
train_reader = paddle.batch(paddle.reader.shuffle(
paddle.dataset.flowers.train(), buf_size=5120),
batch_size=args.batch_size)
place = fluid.CPUPlace() if args.device == 'CPU' else fluid.GPUPlace(0)
exe = fluid.Executor(place)
exe.run(fluid.default_startup_program())
iter = 0
for pass_id in range(args.pass_num):
accuracy.reset(exe)
if iter == args.iterations:
break
for data in train_reader():
if iter == args.iterations:
break
image = np.array(map(lambda x: x[0].reshape(dshape),
data)).astype('float32')
label = np.array(map(lambda x: x[1], data)).astype('int64')
label = label.reshape([-1, 1])
loss, acc = exe.run(fluid.default_main_program(),
feed={
'data': image,
'label': label
},
fetch_list=[avg_cost] + accuracy.metrics)
pass_acc = accuracy.eval(exe)
print("Iter: %d, loss: %s, acc: %s, pass_acc: %s" %
(iter, str(loss), str(acc), str(pass_acc)))
iter += 1
duration = time.time() - start_time
examples_per_sec = args.iterations * args.batch_size / duration
sec_per_batch = duration / args.batch_size
print('\nTotal examples: %d, total time: %.5f' %
(args.iterations * args.batch_size, duration))
print('%.5f examples/sec, %.5f sec/batch \n' %
(examples_per_sec, sec_per_batch))
if args.use_cprof:
pr.disable()
s = StringIO.StringIO()
sortby = 'cumulative'
ps = pstats.Stats(pr, stream=s).sort_stats(sortby)
ps.print_stats()
print(s.getvalue())
label=next_word,
main_program=inference_program)
test_target = [avg_cost] + test_accuracy.metrics + test_accuracy.states
inference_program = fluid.io.get_inference_program(
test_target, main_program=inference_program)
train_reader = paddle.batch(paddle.dataset.imikolov.train(word_dict, N),
BATCH_SIZE)
test_reader = paddle.batch(paddle.dataset.imikolov.test(word_dict, N),
BATCH_SIZE)
place = fluid.GPUPlace(0)
exe = fluid.Executor(place)
feeder = fluid.DataFeeder(
feed_list=[first_word, second_word, third_word, forth_word, next_word],
place=place)
exe.run(fluid.default_startup_program())
for pass_id in range(PASS_NUM):
batch_id = 0
accuracy.reset(exe)
print("begin")
print(time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()))
time_begin = datetime.datetime.now()
for data in train_reader():
if batch_id % 100 == 0 and batch_id != 0:
loss, acc = exe.run(fluid.default_main_program(),
feed=feeder.feed(data),
fetch_list=[avg_cost] + accuracy.metrics)
pass_acc = accuracy.eval(exe)
print("pass_id=" + str(pass_id) + " batch_id=" + str(batch_id) +
" cost=" + str(loss[0]) + " avg_cost=" +
optimizer = fluid.optimizer.Adam(learning_rate=0.01)
optimizer.minimize(avg_cost)
accuracy = fluid.evaluator.Accuracy(input=predict, label=label)
BATCH_SIZE = 50
PASS_NUM = 3
train_reader = paddle.batch(
paddle.reader.shuffle(
paddle.dataset.mnist.train(), buf_size=500),
batch_size=BATCH_SIZE)
place = fluid.CPUPlace()
exe = fluid.Executor(place)
feeder = fluid.DataFeeder(feed_list=[images, label], place=place)
exe.run(fluid.default_startup_program())
for pass_id in range(PASS_NUM):
accuracy.reset(exe)
for data in train_reader():
loss, acc = exe.run(fluid.default_main_program(),
feed=feeder.feed(data),
fetch_list=[avg_cost] + accuracy.metrics)
pass_acc = accuracy.eval(exe)
print("pass_id=" + str(pass_id) + " acc=" + str(acc) + " pass_acc=" +
str(pass_acc))
# print loss, acc
if loss < 10.0 and pass_acc > 0.9:
# if avg cost less than 10.0 and accuracy is larger than 0.9, we think our code is good.
exit(0)
def main(window_size, dict_size=10000, emb_size=32, num_neg_samples=10,
batch_size=512, with_parallel_do=False, sparse_update=True):
assert window_size % 2 == 1
words = []
for i in xrange(window_size):
words.append(fluid.layers.data(name='word_{0}'.format(i), shape=[1],
dtype='int64'))
dict_size = min(MAX_DICT_SIZE, dict_size)
label_word = int(window_size / 2) + 1
def networks(word_list):
embs = []
for i in xrange(window_size):
if i == label_word:
continue
emb = fluid.layers.embedding(
input=word_list[i],
size=[dict_size, emb_size],
param_attr='emb.w',
is_sparse=sparse_update)
embs.append(emb)
embs = fluid.layers.concat(input=embs, axis=1)
loss = fluid.layers.nce(input=embs,
label=word_list[label_word],
num_total_classes=dict_size,
param_attr='nce.w',
bias_attr='nce.b',
num_neg_samples=num_neg_samples)
avg_loss = fluid.layers.mean(x=loss)
avg_loss /= num_neg_samples + 1
return avg_loss
if with_parallel_do:
for_loop = fluid.layers.ParallelDo(fluid.layers.get_places())
with for_loop.do():
word_list = []
for w in words:
word_list.append(for_loop.read_input(w))
for_loop.write_output(networks(word_list))
avg_loss = fluid.layers.mean(x=for_loop())
else:
avg_loss = networks(words)
adam = fluid.optimizer.Adagrad(learning_rate=1e-3)
adam.minimize(loss=avg_loss)
place = fluid.CPUPlace()
exe = fluid.Executor(place)
feeder = fluid.DataFeeder(feed_list=words, place=place)
exe.run(fluid.default_startup_program())
reader = paddle.batch(
paddle.reader.buffered(
reader_creator(window_size=window_size,
word_limit=dict_size - 1,
path="./preprocessed"), 4000), batch_size)
for pass_id in xrange(100):
fluid.io.save_params(exe, dirname='model_{0}'.format(pass_id))
for batch_id, data in enumerate(reader()):
avg_loss_np = exe.run(feed=feeder.feed(data), fetch_list=[avg_loss])
print "Pass ID {0}, Batch ID {1}, Loss {2}".format(pass_id,
batch_id,
avg_loss_np[0])
def main(args):
""" main
"""
model_path = args.pretrained_model
paddle.init(use_gpu=args.with_gpu)
#1, define network topology
input_size = cfg.INPUT_SIZE
output_size = cfg.INPUT_SIZE / cfg.STRIDE
image = fluid.layers.data(name='image',
shape=[3, input_size, input_size],
dtype='float32')
vecmap = fluid.layers.data(name='vecmap',
shape=[cfg.VEC_NUM, output_size, output_size],
dtype='float32')
heatmap = fluid.layers.data(
name='heatmap',
shape=[cfg.HEATMAP_NUM, output_size, output_size],
dtype='float32')
vecmask = fluid.layers.data(name='vecmask',
shape=[cfg.VEC_NUM, output_size, output_size],
dtype='float32')
heatmask = fluid.layers.data(
name='heatmask',
shape=[cfg.HEATMAP_NUM, output_size, output_size],
dtype='float32')
net = MyNet({'data': image})
vec1 = net.layers['conv5_5_CPM_L1']
heatmap1 = net.layers['conv5_5_CPM_L2']
vec2 = net.layers['Mconv7_stage2_L1']
heatmap2 = net.layers['Mconv7_stage2_L2']
vec3 = net.layers['Mconv7_stage3_L1']
heatmap3 = net.layers['Mconv7_stage3_L2']
vec4 = net.layers['Mconv7_stage4_L1']
heatmap4 = net.layers['Mconv7_stage4_L2']
vec5 = net.layers['Mconv7_stage5_L1']
heatmap5 = net.layers['Mconv7_stage5_L2']
vec6 = net.layers['Mconv7_stage6_L1']
heatmap6 = net.layers['Mconv7_stage6_L2']
loss1_1 = get_mask_loss(vec1, vecmap, vecmask)
loss1_2 = get_mask_loss(heatmap1, heatmap, heatmask)
loss2_1 = get_mask_loss(vec2, vecmap, vecmask)
loss2_2 = get_mask_loss(heatmap2, heatmap, heatmask)
loss3_1 = get_mask_loss(vec3, vecmap, vecmask)
loss3_2 = get_mask_loss(heatmap3, heatmap, heatmask)
loss4_1 = get_mask_loss(vec4, vecmap, vecmask)
loss4_2 = get_mask_loss(heatmap4, heatmap, heatmask)
loss5_1 = get_mask_loss(vec5, vecmap, vecmask)
loss5_2 = get_mask_loss(heatmap5, heatmap, heatmask)
loss6_1 = get_mask_loss(vec6, vecmap, vecmask)
loss6_2 = get_mask_loss(heatmap6, heatmap, heatmask)
loss1 = loss1_1 + loss2_1 + loss3_1 + loss4_1 + loss5_1 + loss6_1
cost1 = fluid.layers.mean(x=loss1)
loss2 = loss1_2 + loss2_2 + loss3_2 + loss4_2 + loss5_2 + loss6_2
cost2 = fluid.layers.mean(x=loss2)
avg_cost = cost1 + cost2
#avg_cost = fluid.layers.mean(x=cost)
model_save_dir = '../models/checkpoints'
global_step = layers.create_global_var(shape=[1],
value=0.0,
dtype='float32',
persistable=True,
force_cpu=True)
lr_rate = lr_decay.piecewise_decay(global_step,
values=cfg.LEARNING_RATE_SECTION,
boundaries=cfg.BATCH_SECTION)
# set learning_rate batch_size num_passes model_save_dir
optimizer = fluid.optimizer.Momentum(
learning_rate=cfg.LEARNING_RATE,
global_step=global_step,
momentum=cfg.MOMENTUM,
regularization=fluid.regularizer.L2Decay(cfg.WEIGHT_DECAY))
opts = optimizer.minimize(avg_cost)
inference_program = fluid.default_main_program().clone()
with fluid.program_guard(inference_program):
test_target = [avg_cost]
inference_program = fluid.io.get_inference_program(test_target)
place = fluid.CUDAPlace(3) if args.with_gpu is True else fluid.CPUPlace()
exe = fluid.Executor(place)
exe.run(fluid.default_startup_program())
train_reader = paddle.batch(CocoFolder.CocoFolder(
cfg.TRAIN_DATA_PATH, [
cfg.TRAIN_IMAGELIST_FILE, cfg.TRAIN_MASKLIST_FILE,
cfg.TRAIN_KPTJSON_FILE
], cfg.STRIDE,
Mytransforms.Compose([
Mytransforms.RandomResized(),
Mytransforms.RandomRotate(cfg.RANDOM_ROTATE_ANGLE),
Mytransforms.RandomCrop(cfg.INPUT_SIZE),
Mytransforms.RandomHorizontalFlip(),
])).reader,
batch_size=cfg.BATCH_SIZE)
feeder = fluid.DataFeeder(
place=place, feed_list=[image, vecmap, heatmap, vecmask, heatmask])
if not model_path:
pass
elif model_path.find('.npy') > 0:
net.load(data_path=model_path, exe=exe, place=place)
else:
net.load(data_path=model_path, exe=exe)
for pass_id in range(cfg.NUM_PASSES):
for batch_id, data in enumerate(train_reader()):
loss, step_v, lr_rate_v = exe.run(fluid.default_main_program(),
feed=feeder.feed(data),
fetch_list=[avg_cost] +
[global_step] + [lr_rate])
print("Pass {0}, batch {1}, loss {2}, step {3}, lr{4}".format(
pass_id, batch_id, loss[0], step_v[0], lr_rate_v[0]))
if batch_id % 3000 == 0:
model_path = os.path.join(model_save_dir,
'batch' + str(batch_id))
print 'save models to %s' % (model_path)
fluid.io.save_inference_model(model_path, ['image'],
[vec6, heatmap6], exe)
'''
test loss needed
for data in test_reader():
loss = exe.run(inference_program,
feed=feeder.feed(data),
fetch_list=[avg_cost])
'''
print("End pass {0}".format(pass_id))
if pass_id % 1 == 0:
model_path = os.path.join(model_save_dir, 'pass' + str(pass_id))
print 'save models to %s' % (model_path)
fluid.io.save_inference_model(model_path, ['image'],
[vec6, heatmap6], exe)
def main():
if args.data_set == "cifar10":
classdim = 10
if args.data_format == 'NCHW':
data_shape = [3, 32, 32]
else:
data_shape = [32, 32, 3]
else:
classdim = 102
if args.data_format == 'NCHW':
data_shape = [3, 224, 224]
else:
data_shape = [224, 224, 3]
# Input data
images = fluid.layers.data(name='pixel', shape=data_shape, dtype='float32')
label = fluid.layers.data(name='label', shape=[1], dtype='int64')
# Train program
net = vgg16_bn_drop(images)
predict = fluid.layers.fc(input=net, size=classdim, act='softmax')
cost = fluid.layers.cross_entropy(input=predict, label=label)
avg_cost = fluid.layers.mean(x=cost)
# Evaluator
accuracy = fluid.evaluator.Accuracy(input=predict, label=label)
# inference program
inference_program = fluid.default_main_program().clone()
with fluid.program_guard(inference_program):
test_target = accuracy.metrics + accuracy.states
inference_program = fluid.io.get_inference_program(test_target)
# Optimization
optimizer = fluid.optimizer.Adam(learning_rate=args.learning_rate)
opts = optimizer.minimize(avg_cost)
fluid.memory_optimize(fluid.default_main_program())
# Initialize executor
place = core.CPUPlace() if args.device == 'CPU' else core.CUDAPlace(0)
exe = fluid.Executor(place)
# Parameter initialization
exe.run(fluid.default_startup_program())
# data reader
train_reader = paddle.batch(
paddle.reader.shuffle(
paddle.dataset.cifar.train10()
if args.data_set == 'cifar10' else paddle.dataset.flowers.train(),
buf_size=5120),
batch_size=args.batch_size)
test_reader = paddle.batch(
paddle.dataset.cifar.test10()
if args.data_set == 'cifar10' else paddle.dataset.flowers.test(),
batch_size=args.batch_size)
# test
def test(exe):
accuracy.reset(exe)
for batch_id, data in enumerate(test_reader()):
img_data = np.array(map(lambda x: x[0].reshape(data_shape),
data)).astype("float32")
y_data = np.array(map(lambda x: x[1], data)).astype("int64")
y_data = y_data.reshape([-1, 1])
exe.run(inference_program,
feed={"pixel": img_data,
"label": y_data})
return accuracy.eval(exe)
iters = 0
for pass_id in range(args.num_passes):
# train
start_time = time.time()
num_samples = 0
accuracy.reset(exe)
for batch_id, data in enumerate(train_reader()):
img_data = np.array(map(lambda x: x[0].reshape(data_shape),
data)).astype("float32")
y_data = np.array(map(lambda x: x[1], data)).astype("int64")
y_data = y_data.reshape([-1, 1])
loss, acc = exe.run(fluid.default_main_program(),
feed={"pixel": img_data,
"label": y_data},
fetch_list=[avg_cost] + accuracy.metrics)
iters += 1
num_samples += len(data)
print(
"Pass = %d, Iters = %d, Loss = %f, Accuracy = %f" %
(pass_id, iters, loss, acc)
) # The accuracy is the accumulation of batches, but not the current batch.
pass_elapsed = time.time() - start_time
pass_train_acc = accuracy.eval(exe)
pass_test_acc = test(exe)
print(
"Pass = %d, Training performance = %f imgs/s, Train accuracy = %f, Test accuracy = %f\n"
% (pass_id, num_samples / pass_elapsed, pass_train_acc,
pass_test_acc))
def main():
# define network topology
word = fluid.layers.data(name='word_data',
shape=[1],
dtype='int64',
lod_level=1)
predicate = fluid.layers.data(name='verb_data',
shape=[1],
dtype='int64',
lod_level=1)
ctx_n2 = fluid.layers.data(name='ctx_n2_data',
shape=[1],
dtype='int64',
lod_level=1)
ctx_n1 = fluid.layers.data(name='ctx_n1_data',
shape=[1],
dtype='int64',
lod_level=1)
ctx_0 = fluid.layers.data(name='ctx_0_data',
shape=[1],
dtype='int64',
lod_level=1)
ctx_p1 = fluid.layers.data(name='ctx_p1_data',
shape=[1],
dtype='int64',
lod_level=1)
ctx_p2 = fluid.layers.data(name='ctx_p2_data',
shape=[1],
dtype='int64',
lod_level=1)
mark = fluid.layers.data(name='mark_data',
shape=[1],
dtype='int64',
lod_level=1)
feature_out = db_lstm(**locals())
target = fluid.layers.data(name='target',
shape=[1],
dtype='int64',
lod_level=1)
crf_cost = fluid.layers.linear_chain_crf(input=feature_out,
label=target,
param_attr=fluid.ParamAttr(
name='crfw',
learning_rate=mix_hidden_lr))
avg_cost = fluid.layers.mean(x=crf_cost)
# TODO(qiao)
# check other optimizers and check why out will be NAN
sgd_optimizer = fluid.optimizer.SGD(learning_rate=0.0001)
sgd_optimizer.minimize(avg_cost)
# TODO(qiao)
# add dependency track and move this config before optimizer
crf_decode = fluid.layers.crf_decoding(
input=feature_out, param_attr=fluid.ParamAttr(name='crfw'))
precision, recall, f1_score = fluid.layers.chunk_eval(
input=crf_decode,
label=target,
chunk_scheme="IOB",
num_chunk_types=int(math.ceil((label_dict_len - 1) / 2.0)))
train_data = paddle.batch(paddle.reader.shuffle(
paddle.dataset.conll05.test(), buf_size=8192),
batch_size=BATCH_SIZE)
place = fluid.CPUPlace()
feeder = fluid.DataFeeder(feed_list=[
word, ctx_n2, ctx_n1, ctx_0, ctx_p1, ctx_p2, predicate, mark, target
],
place=place)
exe = fluid.Executor(place)
exe.run(fluid.default_startup_program())
embedding_param = fluid.g_scope.find_var(embedding_name).get_tensor()
embedding_param.set(
load_parameter(conll05.get_embedding(), word_dict_len, word_dim),
place)
batch_id = 0
for pass_id in xrange(PASS_NUM):
for data in train_data():
outs = exe.run(fluid.default_main_program(),
feed=feeder.feed(data),
fetch_list=[avg_cost, precision, recall, f1_score])
avg_cost_val = np.array(outs[0])
precision_val = np.array(outs[1])
recall_val = np.array(outs[2])
f1_score_val = np.array(outs[3])
if batch_id % 10 == 0:
print("avg_cost=" + str(avg_cost_val))
print("precision_val=" + str(precision_val))
print("recall_val:" + str(recall_val))
print("f1_score_val:" + str(f1_score_val))
# exit early for CI
exit(0)
batch_id = batch_id + 1
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import numpy as np
import argparse
import time
import paddle.v2 as paddle
import paddle.v2.fluid as fluid
import paddle.v2.fluid.profiler as profiler
SEED = 1
DTYPE = "float32"
# random seed must set before configuring the network.
fluid.default_startup_program().random_seed = SEED
def parse_args():
parser = argparse.ArgumentParser("mnist model benchmark.")
parser.add_argument(
'--batch_size', type=int, default=128, help='The minibatch size.')
parser.add_argument(
'--iterations', type=int, default=35, help='The number of minibatches.')
parser.add_argument(
'--pass_num', type=int, default=5, help='The number of passes.')
parser.add_argument(
'--device',
type=str,
default='GPU',
choices=['CPU', 'GPU'],
help='The device type.')
def main(dict_path):
word_dict = load_vocab(dict_path)
word_dict["<unk>"] = len(word_dict)
dict_dim = len(word_dict)
print("The dictionary size is : %d" % dict_dim)
data, label, prediction, avg_cost = conv_net(dict_dim)
sgd_optimizer = fluid.optimizer.SGD(learning_rate=conf.learning_rate)
sgd_optimizer.minimize(avg_cost)
accuracy = fluid.evaluator.Accuracy(input=prediction, label=label)
inference_program = fluid.default_main_program().clone()
with fluid.program_guard(inference_program):
test_target = accuracy.metrics + accuracy.states
inference_program = fluid.io.get_inference_program(test_target)
# The training data set.
train_reader = paddle.batch(
paddle.reader.shuffle(
paddle.dataset.imdb.train(word_dict), buf_size=51200),
batch_size=conf.batch_size)
# The testing data set.
test_reader = paddle.batch(
paddle.reader.shuffle(
paddle.dataset.imdb.test(word_dict), buf_size=51200),
batch_size=conf.batch_size)
if conf.use_gpu:
place = fluid.CUDAPlace(0)
else:
place = fluid.CPUPlace()
exe = fluid.Executor(place)
feeder = fluid.DataFeeder(feed_list=[data, label], place=place)
exe.run(fluid.default_startup_program())
def test(exe):
accuracy.reset(exe)
for batch_id, data in enumerate(test_reader()):
input_seq = to_lodtensor(map(lambda x: x[0], data), place)
y_data = np.array(map(lambda x: x[1], data)).astype("int64")
y_data = y_data.reshape([-1, 1])
acc = exe.run(inference_program,
feed={"words": input_seq,
"label": y_data})
test_acc = accuracy.eval(exe)
return test_acc
total_time = 0.
for pass_id in xrange(conf.num_passes):
accuracy.reset(exe)
start_time = time.time()
for batch_id, data in enumerate(train_reader()):
cost_val, acc_val = exe.run(
fluid.default_main_program(),
feed=feeder.feed(data),
fetch_list=[avg_cost, accuracy.metrics[0]])
pass_acc = accuracy.eval(exe)
if batch_id and batch_id % conf.log_period == 0:
print("Pass id: %d, batch id: %d, cost: %f, pass_acc %f" %
(pass_id, batch_id, cost_val, pass_acc))
end_time = time.time()
total_time += (end_time - start_time)
pass_test_acc = test(exe)
print("Pass id: %d, test_acc: %f" % (pass_id, pass_test_acc))
print("Total train time: %f" % (total_time))
def main():
# define network topology
word = fluid.layers.data(
name='word_data', shape=[1], dtype='int64', lod_level=1)
predicate = fluid.layers.data(
name='verb_data', shape=[1], dtype='int64', lod_level=1)
ctx_n2 = fluid.layers.data(
name='ctx_n2_data', shape=[1], dtype='int64', lod_level=1)
ctx_n1 = fluid.layers.data(
name='ctx_n1_data', shape=[1], dtype='int64', lod_level=1)
ctx_0 = fluid.layers.data(
name='ctx_0_data', shape=[1], dtype='int64', lod_level=1)
ctx_p1 = fluid.layers.data(
name='ctx_p1_data', shape=[1], dtype='int64', lod_level=1)
ctx_p2 = fluid.layers.data(
name='ctx_p2_data', shape=[1], dtype='int64', lod_level=1)
mark = fluid.layers.data(
name='mark_data', shape=[1], dtype='int64', lod_level=1)
feature_out = db_lstm(**locals())
target = fluid.layers.data(
name='target', shape=[1], dtype='int64', lod_level=1)
crf_cost = fluid.layers.linear_chain_crf(
input=feature_out,
label=target,
param_attr=fluid.ParamAttr(
name='crfw', learning_rate=mix_hidden_lr))
avg_cost = fluid.layers.mean(x=crf_cost)
# TODO(qiao)
# check other optimizers and check why out will be NAN
sgd_optimizer = fluid.optimizer.SGD(learning_rate=0.0001)
sgd_optimizer.minimize(avg_cost)
# TODO(qiao)
# add dependency track and move this config before optimizer
crf_decode = fluid.layers.crf_decoding(
input=feature_out, param_attr=fluid.ParamAttr(name='crfw'))
precision, recall, f1_score = fluid.layers.chunk_eval(
input=crf_decode,
label=target,
chunk_scheme="IOB",
num_chunk_types=int(math.ceil((label_dict_len - 1) / 2.0)))
train_data = paddle.batch(
paddle.reader.shuffle(
paddle.dataset.conll05.test(), buf_size=8192),
batch_size=BATCH_SIZE)
place = fluid.CPUPlace()
feeder = fluid.DataFeeder(
feed_list=[
word, ctx_n2, ctx_n1, ctx_0, ctx_p1, ctx_p2, predicate, mark, target
],
place=place)
exe = fluid.Executor(place)
exe.run(fluid.default_startup_program())
embedding_param = fluid.g_scope.find_var(embedding_name).get_tensor()
embedding_param.set(
load_parameter(conll05.get_embedding(), word_dict_len, word_dim), place)
batch_id = 0
for pass_id in xrange(PASS_NUM):
for data in train_data():
outs = exe.run(fluid.default_main_program(),
feed=feeder.feed(data),
fetch_list=[avg_cost, precision, recall, f1_score])
avg_cost_val = np.array(outs[0])
precision_val = np.array(outs[1])
recall_val = np.array(outs[2])
f1_score_val = np.array(outs[3])
if batch_id % 10 == 0:
print("avg_cost=" + str(avg_cost_val))
print("precision_val=" + str(precision_val))
print("recall_val:" + str(recall_val))
print("f1_score_val:" + str(f1_score_val))
# exit early for CI
exit(0)
batch_id = batch_id + 1
def run_benchmark(model, args):
if args.use_cprof:
pr = cProfile.Profile()
pr.enable()
start_time = time.time()
# Input data
images = fluid.layers.data(name='pixel', shape=[1, 28, 28], dtype=DTYPE)
label = fluid.layers.data(name='label', shape=[1], dtype='int64')
# Train program
predict = model(images)
cost = fluid.layers.cross_entropy(input=predict, label=label)
avg_cost = fluid.layers.mean(x=cost)
# Evaluator
accuracy = fluid.evaluator.Accuracy(input=predict, label=label)
# inference program
inference_program = fluid.default_main_program().clone()
with fluid.program_guard(inference_program):
test_target = accuracy.metrics + accuracy.states
inference_program = fluid.io.get_inference_program(test_target)
# Optimization
opt = fluid.optimizer.AdamOptimizer(learning_rate=0.001,
beta1=0.9,
beta2=0.999)
opt.minimize(avg_cost)
fluid.memory_optimize(fluid.default_main_program())
# Initialize executor
place = fluid.CPUPlace() if args.device == 'CPU' else fluid.CUDAPlace(0)
exe = fluid.Executor(place)
# Parameter initialization
exe.run(fluid.default_startup_program())
# Reader
train_reader = paddle.batch(paddle.dataset.mnist.train(),
batch_size=args.batch_size)
for pass_id in range(args.pass_num):
accuracy.reset(exe)
pass_start = time.time()
for batch_id, data in enumerate(train_reader()):
img_data = np.array(map(lambda x: x[0].reshape([1, 28, 28]),
data)).astype(DTYPE)
y_data = np.array(map(lambda x: x[1], data)).astype("int64")
y_data = y_data.reshape([len(y_data), 1])
start = time.time()
outs = exe.run(
fluid.default_main_program(),
feed={
"pixel": img_data,
"label": y_data
},
fetch_list=[avg_cost] + accuracy.metrics
) # The accuracy is the accumulation of batches, but not the current batch.
end = time.time()
loss = np.array(outs[0])
acc = np.array(outs[1])
print("pass=%d, batch=%d, loss=%f, error=%f, elapse=%f" %
(pass_id, batch_id, loss, 1 - acc, (end - start) / 1000))
pass_end = time.time()
train_avg_acc = accuracy.eval(exe)
test_avg_acc = eval_test(exe, accuracy, inference_program)
print("pass=%d, train_avg_acc=%f, test_avg_acc=%f, elapse=%f" %
(pass_id, train_avg_acc, test_avg_acc,
(pass_end - pass_start) / 1000))
