def predict(args):
device = torch.device(args.device)
cls_embed = torch.load(args.embedding_save_path)
model = textCNN(args.embedding_size, args.cls_num, args.l1_channels_num)
model.load_state_dict(torch.load(args.model_save_path))
model.eval()
model = model.to(device)
cls_embed = cls_embed.to(device)
cls_embed.eval()
dev_dataset = DataSet(args.predict_data, None, args.batch_size)
dev_dataset.reorderForEval()
towrite = open(args.predict_writeto, "w+")
towrite.write("idx,labels\n")
idx = 0
print("Begin Predict task...")
while (True):
(example, dump), p = dev_dataset.getPredictBatch(False)
example = cls_embed(example, device=device)
# print(example.size())
outs = model(example)
outs = (torch.argmax(outs, -1) + 1).squeeze().tolist()
for out in zip(example[1], outs):
towrite.write("{0},{1}\n".format(out[0], int(out[1])))
idx += 1
if (p): break
towrite.close()
print("Predict task Done!")
def predict(args):
device = torch.device(args.device)
cls_embed = torch.load(args.embedding_save_path)
model = textCNN(args.embedding_size, args.cls_num, args.l1_channels_num)
model.load_state_dict(torch.load(args.model_save_path))
model.eval()
model = model.to(device)
cls_embed = cls_embed.to(device)
cls_embed.eval()
dev_dataset = DataSet(args.predict_data, None, args.batch_size)
towrite = open(args.predict_writeto, "w+")
towrite.write("idx,labels\n")
idx = 0
print("Begin Predict task...")
while (True):
example, p = dev_dataset.getPredictBatch()
example = cls_embed(example, device=device)
# print(example.size())
out = model(example)
out = torch.argmax(out, -1).item() + 1
towrite.write("{0},{1}\n".format(idx, out))
idx += 1
if (p): break
towrite.close()
print("Predict task Done!")
def read_data_sets(validation_size=0.1):
test_images = np.array([el['img'] for el in test_data])
test_labels = np.array([el['label'] for el in test_data])
test_labels = np.eye(meta['n_classes'])[test_labels]
train_images = np.array([el['img'] for el in train_data])
train_labels = np.array([el['label'] for el in train_data])
train_labels = np.eye(meta['n_classes'])[train_labels]
if 0 <= validation_size < 1.0:
validation_size = int(validation_size * len(train_images))
if not 0 <= validation_size <= len(train_images):
raise ValueError(
'Validation size should be between 0 and {}. Received: {}.'
.format(len(train_images), validation_size))
# Shuffle data
perm = np.arange(len(train_labels))
np.random.shuffle(perm)
train_images = train_images[perm]
train_labels = train_labels[perm]
# Split training set in training and validation set
validation_images = train_images[:validation_size]
validation_labels = train_labels[:validation_size]
train_images = train_images[validation_size:]
train_labels = train_labels[validation_size:]
train = DataSet(train_images, train_labels, dtype=np.float32)
validation = DataSet(validation_images,
validation_labels,
dtype=np.float32)
test = DataSet(test_images, test_labels, dtype=np.float32)
return base.Datasets(train=train, validation=validation, test=test)
def main():
imgs = tf.placeholder(tf.float32, [None, IMAGE_WIDTH * IMAGE_HEIGHT])
keys = tf.placeholder(tf.float32, [None, N_CLASS])
train_model = create_CNN(imgs, Weight_Dicts, Biases_Dict, Dropout_Dict)
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(train_model, keys))
optimizer = tf.train.AdamOptimizer(0.01).minimize(cost)
# Evaluate the train model
correct_model = tf.equal(tf.argmax(train_model, 1), tf.argmax(keys, 1))
accuracy = tf.reduce_mean(tf.cast(correct_model, tf.float32))
init = tf.initialize_all_variables()
obj = DataSet()
obj.load()
with tf.Session() as sess:
sess.run(init)
step = 1
while step * BATCH_SIZE < TRAINING_ITERS:
batch_imgs, batch_keys = obj.next_batch(BATCH_SIZE)
sess.run(optimizer, feed_dict = {imgs : batch_imgs, keys : batch_keys})
if step % DISPLAY_STEP == 0:
acc = sess.run(accuracy, feed_dict = {imgs : batch_imgs, keys : batch_keys})
loss = sess.run(cost, feed_dict = {imgs : batch_imgs, keys : batch_keys})
print "Iter " + str(step * BATCH_SIZE) + ", MiniBatch Loss = " + "{:.6f}".format(loss) + ", Training Accuracy = " + "{:.5f}".format(acc)
step = step + 1
def __init__(self, args):
self.args = {}
self.args['dataset'] = args.dataset_name
self.args["batch_size"] = args.batch_size
self.args['cuda'] = args.cuda
self.args['device'] = args.device
self.args['epoch'] = args.epoch
self.args['in_length'] = args.obs_length
self.args['out_length'] = args.pred_length
self.args['save_name'] = args.save_name
self.args['load_name'] = args.load_name
# self.args['nll_only'] = True
self.args["learning_rate"] = 1e-4
self.args["w_decay"] = 1e-4
self.args['name'] = 'test.tar'
self.args["optim"] = 'Adam'
self.args['train_loss'] = 'MSE'
self.wandb = False
if args.wandb:
self.wandb = True
print("Wandb is initialized...")
wandb.init(project="vanilla_gru",\
# name="obs: {}, pred: {}".format(args.obs_length, args.pred_length),
config=self.args)
self.net = NNPred(args)
if self.args['cuda']:
self.net = self.net.cuda(self.args['device'])
# for training// dataset
self.train_dataset = DataSet(args, 'train')
self.val_dataset = DataSet(args, 'val')
self.test_dataset = DataSet(args, 'test')
# for i in range(12300, 12500):
# hist, hist_mask, fut, fut_mask, ref_pose, AgentInfo = self.test_dataset[0]
# print(AgentInfo)
# print(hist)
# print(fut)
# # A = fut+ref_pose#// These lines for
# # A[:,0] = ((A[:,0]+1)/2)*(self.test_dataset.max_position_x - self.test_dataset.min_position_x)+ self.test_dataset.min_position_x
# # A[:,1] = ((A[:,1]+1)/2)*(self.test_dataset.max_position_y - self.test_dataset.min_position_y)+ self.test_dataset.min_position_y
# print(A)
# # print(fut[:,1]+ref_pose[1])
# quit()
self.trainDataloader = DataLoader(self.train_dataset, batch_size=self.args["batch_size"], shuffle=True, \
num_workers=6, collate_fn=self.train_dataset.GetBatch, drop_last=True)
# print("trainDataloader completed!")
self.valDataloader = DataLoader(self.val_dataset, batch_size=self.args["batch_size"], shuffle=True, \
num_workers=6, collate_fn=self.val_dataset.GetBatch, drop_last=True)
# print("valDataloader completed!")
self.testDataloader = DataLoader(self.test_dataset, batch_size=self.args["batch_size"], shuffle=True, \
num_workers=6, collate_fn=self.test_dataset.GetBatch, drop_last=True)
def analyze_result(self, paths):
image_paths = sorted(glob(os.path.join(paths, '*')))
image, wides = DataSet().get_imges(image_paths)
def getlab(x):
result = x.split('_')[-1].replace('.jpg', '')
result = result.replace('.png', '')
return result
labels = map(getlab, image_paths)
inputs = tf.placeholder(tf.float32, [None, 32, None, 1])
width = tf.placeholder(tf.int32, [None])
is_training = tf.placeholder(tf.bool)
logits, sequence_length = self.crnn(inputs, width, is_training)
decoder, probably = tf.nn.ctc_greedy_decoder(logits, sequence_length, merge_repeated=True)
decoder = decoder[0]
dense_decoder = tf.sparse_to_dense(sparse_indices=decoder.indices, output_shape=decoder.dense_shape,
sparse_values=decoder.values, default_value=-1)
with tf.Session() as sess:
saver = tf.train.Saver(tf.global_variables())
saver.restore(sess, config.MODEL_SAVE)
result = []
if image.shape[0] <= config.BATCH_SIZE:
sentence = sess.run(dense_decoder, feed_dict={inputs: image, width: wides, is_training: False})
sentence = sentence.tolist()
decode = dict(zip(config.ONE_HOT.values(), config.ONE_HOT.keys()))
result.extend(sentence)
else:
index = 0
while (index + 1) * config.BATCH_SIZE <= image.shape[0]:
if (index + 1) * config.BATCH_SIZE > image.shape[0]:
end = image.shape[0]
else:
end = (index + 1) * config.BATCH_SIZE
sentence = sess.run(dense_decoder, feed_dict={inputs: image[index * config.BATCH_SIZE:end, ...],
width: wides[index * config.BATCH_SIZE:end, ...],
is_training: True})
sentence = sentence.tolist()
decode = dict(zip(config.ONE_HOT.values(), config.ONE_HOT.keys()))
result.extend(sentence)
index = index + 1
result = list(map(lambda y: ''.join(list(map(lambda x: decode.get(x), y))), result))
result = dict(zip(labels, result))
print(result)
def run_sc_train(config):
"""Load problem."""
if not os.path.exists(config.probfn):
raise ValueError("Problem file not found.")
else:
p = problem.load_problem(config.probfn)
"""Set up model."""
model = setup_model(config, A=p.A)
# Create target Directory if don't exist
dirName = config.modelfn
if not os.path.exists(dirName):
os.mkdir(dirName)
print("Directory ", dirName, " Created ")
else:
print("Directory ", dirName, " already exists")
# model.weights[2].assign(2 * model.weights[2].numpy())
model.weights[2].assign((1234.0, 567.0))
model.weights[3].assign((1234.0, 567.0))
model.save_weights(config.modelfn + '/ckpt')
print('model weights ... ')
print(model.weights[2])
print(model.weights[3])
loaded_model = setup_model(config, A=p.A)
loaded_model.load_weights(config.modelfn + '/ckpt')
print('loaded model weights ... ')
print(loaded_model.weights[2])
print(loaded_model.weights[3])
# loaded_model.load_weights('ckpt')
# model.load_weights('my_model.h5', by_name=False, skip_mismatch=False)
"""Set up input."""
config.SNR = np.inf if config.SNR == 'inf' else float(config.SNR)
data_set = DataSet.DataSet(config, p)
"""Set up training."""
stages = train.setup_sc_training(model, data_set, None, config.init_lr,
config.decay_rate, config.lr_decay)
tfconfig = tf.compat.v1.ConfigProto(allow_soft_placement=True)
tfconfig.gpu_options.allow_growth = True
# start timer
start = time.time()
# train model
model.do_training(stages, data_set, config.modelfn, config.scope,
config.val_step, config.maxit, config.better_wait)
# end timer
end = time.time()
elapsed = end - start
print("elapsed time of training = " + str(timedelta(seconds=elapsed)))
def readDataSetFile(filename, F):
with open(filename) as f:
E = DataSet()
for line in f:
line =line.split()
if len(line) != len(F):
print("Number of attributes in the Training record:"+str(line)+"does not match the number in the attribute file")
raise Exception('DataValidation')
d = Data()
idx= 0
for value in ine:
if value in F[idx].values:
d.addValue(F[idx].name,value)
else:
print('Value='+value+' is not a valid value for attribute='+ F[idx].name)
idx += 1
E.addData(d)
f.close()
def train(config):
model = SelfAttNet(config)
model.train()
dataset = DataSet(cofig)
for epoch in range(config.num_epochs):
for data in dataset:
train_x, train_y = data
train_x = Variable(convert_words(train_x))
true_y = Variable(train_y)
emb_x, P = model(train_x)
def main():
imgs = tf.placeholder(tf.float32, [None, IMAGE_WIDTH * IMAGE_HEIGHT])
keys = tf.placeholder(tf.float32, [None, N_CLASS])
train_model = create_CNN(imgs, Weight_Dicts, Biases_Dict, Dropout_Dict)
# Define loss and optimizer
cost = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(train_model, keys))
optimizer = tf.train.AdamOptimizer(0.01).minimize(cost)
# Evaluate the train model
correct_model = tf.equal(tf.argmax(train_model, 1), tf.argmax(keys, 1))
accuracy = tf.reduce_mean(tf.cast(correct_model, tf.float32))
init = tf.initialize_all_variables()
obj = DataSet()
obj.load()
with tf.Session() as sess:
sess.run(init)
step = 1
while step * BATCH_SIZE < TRAINING_ITERS:
batch_imgs, batch_keys = obj.next_batch(BATCH_SIZE)
sess.run(optimizer, feed_dict={imgs: batch_imgs, keys: batch_keys})
if step % DISPLAY_STEP == 0:
acc = sess.run(accuracy,
feed_dict={
imgs: batch_imgs,
keys: batch_keys
})
loss = sess.run(cost,
feed_dict={
imgs: batch_imgs,
keys: batch_keys
})
print "Iter " + str(
step *
BATCH_SIZE) + ", MiniBatch Loss = " + "{:.6f}".format(
loss) + ", Training Accuracy = " + "{:.5f}".format(acc)
step = step + 1
def main(*args):
# Hyper parameters
learning_rate = 0.001
training_steps = 10000
valid_step = 50
cell_size = 256
num_rnn_layers = 1
dataset = DataSet(FLAGS.dataset)
model = Model(dataset.samples_shape[1],
dataset.labels_shape[1],
dataset.labels_shape[2],
cell_size,
num_rnn_layers,
learning_rate,
cell_type='lstm')
with tf.Session() as sess:
tf.global_variables_initializer().run()
loss = []
for step in range(training_steps):
train_samples, train_labels, train_weights = dataset.get_batch(FLAGS.batch_size, 'train')
train_labels_T = np.transpose(train_labels, (1, 0, 2))
_loss, prediction = model.step(train_samples, train_labels_T, train_weights, sess)
# loss.append(_loss)
if (step % valid_step) == 0:
# print("Average training loss: %s" % np.mean(loss))
# loss = []
valid_samples, valid_labels, valid_weights = dataset.get_batch(FLAGS.batch_size, 'valid')
valid_labels_T = np.transpose(valid_labels, (1, 0, 2))
v_loss, v_prediction = model.step(valid_samples, valid_labels_T, valid_weights, sess, valid=True)
print("Valid loss @ step %s: %s" % (step,v_loss))
for p in v_prediction:
pred = decode_ohe(p)
cleaned_pred = clean_prediction(pred)
print(cleaned_pred)
def output(self, path):
image, wides = DataSet().get_imges([path])
inputs = tf.placeholder(tf.float32, [None, 32, None, 1])
width = tf.placeholder(tf.int32, [None])
is_training = tf.placeholder(tf.bool)
logits, sequence_length = self.crnn(inputs, width, is_training)
decoder_greey, probably_greedy = tf.nn.ctc_greedy_decoder(
logits, sequence_length, merge_repeated=True)
with tf.device('/cpu:0'):
decoders, probably = tf.nn.ctc_beam_search_decoder(
logits,
sequence_length,
beam_width=20,
top_paths=5,
merge_repeated=False)
decoder_list = []
for decoder in decoders:
dense_decoder = tf.sparse_to_dense(
sparse_indices=decoder.indices,
output_shape=decoder.dense_shape,
sparse_values=decoder.values,
default_value=-1)
decoder_list.append(dense_decoder)
# classs = tf.argmax(logits,-1)
# classs = tf.squeeze(classs,axis=-1)
logits = tf.nn.softmax(logits)
# classs = tf.nn.top_k(logits,10)
with tf.Session() as sess:
saver = tf.train.Saver(tf.global_variables())
saver.restore(sess, config.MODEL_SAVE)
t1 = time.time()
decoder_list, logits_, probably_ = sess.run(
[decoder_list, logits, probably],
feed_dict={
inputs: image,
width: wides,
is_training: False
})
t2 = time.time()
print(t2 - t1)
t3 = time.time()
_, _ = sess.run([decoder_greey, logits],
feed_dict={
inputs: image,
width: wides,
is_training: False
})
t4 = time.time()
print(t4 - t3)
t5 = time.time()
logits_ = sess.run(logits,
feed_dict={
inputs: image,
width: wides,
is_training: False
})
logits_ = logits_[:, 0, :]
logits_ = logits_[:, config.NUM_SIGN]
decoder_cpu = beam_search_decoder(logits_, 5)
t6 = time.time()
print(t6 - t5)
for result in decoder_cpu:
def get_char(num):
return config.DECODE[num]
result_0 = map(get_char, result[0])
print(''.join(result_0))
print(result[1])
print(
'------------------------------------------------------------------------------------------------------------'
)
decode = dict(zip(config.ONE_HOT.values(), config.ONE_HOT.keys()))
result_list = []
for sentence in decoder_list:
sentence = sentence.tolist()
result = ''.join(
list(map(lambda x: decode.get(x), sentence[0])))
result_list.append(result)
for i, result in enumerate(result_list):
print(result)
def train_vectors(options, sens=None):
# check vectors and ckpt
checkpoint = '0'
train_vec_dir = os.path.split(options.vectors_path)[0]
ckpt_dir = os.path.join(train_vec_dir, 'ckpt')
ckpt = tf.train.get_checkpoint_state(ckpt_dir)
if ckpt and ckpt.model_checkpoint_path:
cur_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
logger.info(
"model and vectors already exists, checkpoint step = {}".format(
cur_step))
checkpoint = input(
"please input 0 to start a new train, or input a choosed ckpt to restore (-1 for latest ckpt)"
)
if checkpoint == '0':
if ckpt:
tf.gfile.DeleteRecursively(ckpt_dir)
logger.info('start a new embedding train using tensorflow ...')
elif checkpoint == '-1':
logger.info(
'restore a embedding train using tensorflow from latest ckpt...')
else:
logger.info(
'restore a embedding train using tensorflow from ckpt-%s...' %
checkpoint)
if not os.path.exists(train_vec_dir):
os.makedirs(train_vec_dir)
if not os.path.exists(ckpt_dir):
os.makedirs(ckpt_dir)
# generate training examples
logger.info("Generate training examples:")
idx_vocab_freq_file = os.path.join(train_vec_dir, 'vocab.freq')
logger.info('\t corpus_store_path = {}'.format(options.corpus_store_path))
logger.info(
'\t vocab and frequencies file = {}'.format(idx_vocab_freq_file))
logger.info('\t walk_workers to load dataset = {}'.format(
options.walk_workers))
logger.info('\t window_size = {}'.format(options.window_size))
data, labels, idx2vocab, nodes_frequencies = generate_train_data(
options.corpus_store_path,
options.headflag_of_index_file,
options.walk_workers,
options.window_size,
idx_vocab_freq_file,
sens=sens,
always_rebuild=options.always_rebuild)
del sens
gc.collect()
dataset = DataSet(data=data,
labels=labels,
shuffled=not options.unshuffled)
lr_file = os.path.join(train_vec_dir, "lr.info")
np.savetxt(
lr_file,
np.asarray(
[options.learning_rate, options.decay_epochs, options.decay_rate],
dtype=np.float32),
fmt="%.6f")
# train info
logger.info('Train info:')
logger.info('\t total embedding nodes = {}'.format(len(idx2vocab)))
logger.info('\t total training examples = {}'.format(len(data)))
logger.info('\t shuffled in training = {}'.format(not options.unshuffled))
logger.info('\t embedding size = {}'.format(options.embedding_size))
logger.info('\t window size = {}'.format(options.window_size))
logger.info('\t negative = {}'.format(options.negative))
logger.info('\t distortion_power = {}\n'.format(options.distortion_power))
logger.info('\t batch_size = {}'.format(options.batch_size))
logger.info('\t iter_epoches = {}'.format(options.iter_epoches))
logger.info('\t init_learning_rate = {}'.format(options.learning_rate))
logger.info('\t decay_epochs = {}'.format(options.decay_epochs))
logger.info('\t decay_interval = {}'.format(options.decay_interval))
logger.info('\t decay_rate = {}'.format(options.decay_rate))
logger.info('\t loss_interval = {}s'.format(options.loss_interval))
logger.info('\t summary_steps = {}'.format(options.summary_steps))
logger.info('\t summary_interval = {}s'.format(options.summary_interval))
logger.info('\t ckpt_epochs = {}'.format(options.ckpt_epochs))
logger.info('\t ckpt_interval = {}s\n'.format(options.ckpt_interval))
logger.info('\t using_gpu = {}'.format(options.using_gpu))
logger.info('\t visible_device_list = {}'.format(
options.visible_device_list))
logger.info('\t log_device_placement = {}'.format(
options.log_device_placement))
logger.info('\t allow_soft_placement = {}'.format(
options.allow_soft_placement))
logger.info('\t gpu_memory_fraction = {}'.format(
options.gpu_memory_fraction))
logger.info('\t gpu_memory_allow_growth = {}'.format(options.allow_growth))
logger.info('\t train_workers = {}\n'.format(options.train_workers))
logger.info('\t ckpt_dir = {}'.format(ckpt_dir))
logger.info('\t vectors_path = {}'.format(options.vectors_path))
logger.info('\t learning_rate_path = {}'.format(lr_file))
fr_vec = open(os.path.join(train_vec_dir, 'embedding.info'), 'w')
fr_vec.write('embedding info:\n')
fr_vec.write('\t corpus_store_path = {}\n'.format(
options.corpus_store_path))
fr_vec.write(
'\t vocab and frequencies file = {}\n'.format(idx_vocab_freq_file))
fr_vec.write('\t total embedding nodes = {}\n'.format(len(idx2vocab)))
fr_vec.write('\t total training examples = {}\n'.format(len(data)))
fr_vec.write(
'\t shuffled in training = {}\n'.format(not options.unshuffled))
fr_vec.write('\t embedding size = {}\n'.format(options.embedding_size))
fr_vec.write('\t window size = {}\n'.format(options.window_size))
fr_vec.write('\t negative = {}\n'.format(options.negative))
fr_vec.write('\t distortion_power = {}\n\n'.format(
options.distortion_power))
fr_vec.write('\t batch_size = {}\n'.format(options.batch_size))
fr_vec.write('\t iter_epoches = {}\n'.format(options.iter_epoches))
fr_vec.write('\t init_learning_rate = {}\n'.format(options.learning_rate))
fr_vec.write('\t decay_epochs = {}\n'.format(options.decay_epochs))
fr_vec.write('\t decay_interval = {}\n'.format(options.decay_interval))
fr_vec.write('\t decay_rate = {}\n'.format(options.decay_rate))
fr_vec.write('\t loss_interval = {}s\n'.format(options.loss_interval))
fr_vec.write('\t summary_steps = {}\n'.format(options.summary_steps))
fr_vec.write('\t summary_interval = {}s\n'.format(
options.summary_interval))
fr_vec.write('\t ckpt_epochs = {}\n'.format(options.ckpt_epochs))
fr_vec.write('\t ckpt_interval = {}s\n\n'.format(options.ckpt_interval))
fr_vec.write('\t using_gpu = {}\n'.format(options.using_gpu))
fr_vec.write('\t visible_device_list = {}\n'.format(
options.visible_device_list))
fr_vec.write('\t log_device_placement = {}\n'.format(
options.log_device_placement))
fr_vec.write('\t allow_soft_placement = {}\n'.format(
options.allow_soft_placement))
fr_vec.write('\t gpu_memory_fraction = {}\n'.format(
options.gpu_memory_fraction))
fr_vec.write('\t gpu_memory_allow_growth = {}\n'.format(
options.allow_growth))
fr_vec.write('\t train_workers = {}\n\n'.format(options.train_workers))
fr_vec.write('\t ckpt_dir = {}\n'.format(ckpt_dir))
fr_vec.write('\t vectors_path = {}\n'.format(options.vectors_path))
fr_vec.write('\t learning_rate_path = {}\n'.format(lr_file))
fr_vec.close()
visible_devices = str(options.visible_device_list[0])
for dev in options.visible_device_list[1:]:
visible_devices = visible_devices + ',%s' % dev
os.environ['CUDA_VISIBLE_DEVICES'] = visible_devices
# train
logger.info('training...')
time_start = time.time()
train(dataset=dataset,
vectors_path=options.vectors_path,
lr_file=lr_file,
ckpt_dir=ckpt_dir,
checkpoint=checkpoint,
idx2vocab=idx2vocab,
vocab_unigrams=nodes_frequencies,
embedding_size=options.embedding_size,
neg_sampled=options.negative,
distortion_power=options.distortion_power,
batch_size=options.batch_size,
initial_learning_rate=options.learning_rate,
decay_epochs=options.decay_epochs,
decay_rate=options.decay_rate,
iter_epochs=options.iter_epoches,
allow_soft_placement=options.allow_soft_placement,
log_device_placement=options.log_device_placement,
gpu_memory_fraction=options.gpu_memory_fraction,
using_gpu=options.using_gpu,
allow_growth=options.allow_growth,
loss_interval=options.loss_interval,
summary_steps=options.summary_steps,
ckpt_interval=options.ckpt_interval,
ckpt_epochs=options.ckpt_epochs,
summary_interval=options.summary_interval,
decay_interval=options.decay_interval,
train_workers=options.train_workers)
logger.info('train completed in {}s'.format(time.time() - time_start))
return
lambda_f = 0.04
k_of_knn = 10
m_of_knn = 50
SEED = 666
np.random.seed(SEED)
data_dict = sio.loadmat('MNIST')
# normalization
samples = data_dict['fea'] / 256
labels = dense_to_one_hot(data_dict['gnd'], num_classes)
# 有标记数据
# l_index = np.random.randint(5000, size=labeled_data_size)
l_index = equal_proportion_sampling(data_dict['gnd'][:5000], num_classes,
labeled_data_size)
l_dataset = DataSet(samples[l_index], labels[l_index])
# 无标记数据
# u_index = np.arange(5000, 60000)
u_index = np.random.randint(5000, 60000, size=2000)
uindex_dataset = DataSet(u_index, labels[u_index])
sample_data = np.vstack((samples[l_index], samples[u_index]))
sample_label = np.vstack((labels[l_index], labels[u_index]))
# 测试数据
test_dataset = DataSet(samples[60000:], labels[60000:])
neighborIndex, remoteIndex, RBF_matrix = find_neighbors(
samples,
l_index,
def run_sc_test(config):
"""
Test model.
"""
"""Load problem."""
if not os.path.exists(config.probfn):
raise ValueError("Problem file not found.")
else:
p = problem.load_problem(config.probfn)
"""Load testing data."""
xt = np.load(config.xtest)
"""Set up input for testing."""
config.SNR = np.inf if config.SNR == 'inf' else float(config.SNR)
data_set = DataSet.DataSet(config, p)
input_, label_ = (train.setup_input_sc(config.test, p, xt.shape[1], None,
False, config.supp_prob, config.SNR,
config.magdist, **config.distargs))
"""Set up model."""
model = setup_model(config, A=p.A)
xhs_ = model.inference(input_, None)
"""Create session and initialize the graph."""
tfconfig = tf.compat.v1.ConfigProto(allow_soft_placement=True)
tfconfig.gpu_options.allow_growth = True
with tf.compat.v1.Session(config=tfconfig) as sess:
# graph initialization
sess.run(tf.compat.v1.global_variables_initializer())
# load model
model.load_trainable_variables(config.modelfn)
nmse_denom = np.sum(np.square(xt))
supp_gt = xt != 0
lnmse = []
lspar = []
lsperr = []
lflspo = []
lflsne = []
# test model
for xh_ in xhs_:
xh = sess.run(xh_, feed_dict={label_: xt})
# nmse:
loss = np.sum(np.square(xh - xt))
nmse_dB = 10.0 * np.log10(loss / nmse_denom)
print(nmse_dB)
lnmse.append(nmse_dB)
supp = xh != 0.0
# intermediate sparsity
spar = np.sum(supp, axis=0)
lspar.append(spar)
# support error
sperr = np.logical_xor(supp, supp_gt)
lsperr.append(np.sum(sperr, axis=0))
# false positive
flspo = np.logical_and(supp, np.logical_not(supp_gt))
lflspo.append(np.sum(flspo, axis=0))
# false negative
flsne = np.logical_and(supp_gt, np.logical_not(supp))
lflsne.append(np.sum(flsne, axis=0))
res = dict(nmse=np.asarray(lnmse),
spar=np.asarray(lspar),
sperr=np.asarray(lsperr),
flspo=np.asarray(lflspo),
flsne=np.asarray(lflsne))
np.savez(config.resfn, **res)
def train(args):
device = torch.device(args.device)
cls_embed = ModelEmbeddings.load_from_file(args.pretrain_vector)
train_data = DataSet(args.train_data, args.train_labels, args.batch_size,
int(1e7))
train_data.reorderForEval()
# train_data.padtoMaxLen()
print('loading dev set...')
# devSet,devlabels,devNum=DataSet.load_devSet(args.dev_data,args.dev_labels)
dev_dataset = DataSet(args.dev_data, args.dev_labels, args.batch_size,
int(1e7))
dev_dataset.reorderForEval()
print('Done dev loading.')
model = textCNN(args.embedding_size, args.cls_num, args.l1_channels_num)
model.train()
model = model.to(device)
cls_embed.train()
cls_embed = cls_embed.to(device)
optimizer = torch.optim.Adam([{
'params': model.parameters()
}, {
'params': cls_embed.parameters(),
'lr': 1.75 * args.lr
}],
lr=float(args.lr))
Loss_fun = torch.nn.CrossEntropyLoss(reduction='sum')
print('begin Maximum Likelihood training')
epoch = 0
sum_loss = 0
step = 0
tot_step = 0
pi_2 = np.pi / 2
while (True):
optimizer.zero_grad()
if (args.use_cos_batch and epoch):
for param_group in optimizer.param_groups:
param_group['lr'] = args.lr * np.cos(pi_2 * (step / tot_step))
example, p = train_data.getTestBatch()
t = example[0]
l = example[1]
example = None
l = torch.tensor(l, device=device)
# print("Doing word embed")
# print(type(t))
# print(type(l))
# print(l.requires_grad)
t = cls_embed(t, device=device)
# t=t.detach()
# print("Done word embed")
# print("feed into model...")
outPuts = model(t)
# print("Get answer!")
# print("Caluating Loss")
# print(outPuts.size())
# print(l.size())
# print(l)
# print(outPuts)
loss = Loss_fun(outPuts, l)
loss.backward()
optimizer.step()
loss /= len(outPuts)
sum_loss += loss
print("epoch:{0},step:{1},train loss:{2}".format(epoch, step, loss))
step += 1
# print("Doing backPro")
# print("Done backPro")
# print("Setping...")
# print("Done Step!")
# print('Current Batch Loss:{0}'.format(loss))
if (p):
tot_step = step
epoch += p
print("Epoch mean Loss:{0}".format(sum_loss / step))
step = 0
sum_loss = 0
accuary, F1 = test(args, model, dev_dataset, cls_embed,
args.cls_num, device)
if (model.lastScore < F1):
print("F1 score grow from {0} to {1}, save model...".format(
model.lastScore, F1))
model.lastScore = F1
torch.save(model.state_dict(), args.model_save_path)
torch.save(cls_embed, args.embedding_save_path)
args.lr = args.lr * np.exp(args.lr_decay)
for param_group in optimizer.param_groups:
param_group['lr'] = args.lr
else:
args.lr = args.lr / 2
for param_group in optimizer.param_groups:
param_group['lr'] = args.lr
if (epoch == args.max_epoch): break
def main():
global use_gpu,device
# set up some parameters
batch_size=1
lr= 1e-3
logging_path= 'logging/'
num_epoches= 500
epoch_to_save= 10
tsize=10
data_path= '../dataset'
print('loading data sets ...')
dataset_train= DataSet(datapath= data_path)
loader_train= DataLoader(dataset= dataset_train, num_workers=8, batch_size=batch_size, shuffle=True)
print("# of training samples: %d\n" %int(len(dataset_train)))
model= RadarNet(use_gpu=use_gpu,device=device)
print(model)
criterion= ComLoss()
# model.load_state_dict(torch.load('../logging/newest-5_8.pth'))
if use_gpu:
model= model.to(device)
criterion.to(device)
#optimizer
optimizer= torch.optim.Adam(model.parameters(), lr=lr)
scheduler= MultiStepLR(optimizer, milestones=[20,40,60,80], gamma=0.2)
#record
writer= SummaryWriter(logging_path)
#start training
step= 0
for epoch in range(num_epoches):
scheduler.step(epoch)
for param_group in optimizer.param_groups:
print('learning rate %f' %param_group['lr'])
for i, (input_train, target_train) in enumerate(loader_train, 0):
# input size: (4,10,1,200,200)
# target size: (4,10,1,200,200)
model.train()
model.zero_grad()
optimizer.zero_grad()
input_train, target_train= Variable(input_train), Variable(target_train)
if use_gpu:
input_train, target_train= input_train.to(device), target_train.to(device)
out_train= model(input_train)
loss= -criterion(target_train, out_train)
loss.backward()
optimizer.step()
# training track
model.eval()
out_train= model(input_train)
output_train= torch.clamp(out_train, 0, 1)
print("[epoch %d/%d][%d/%d] obj: %.4f "%(epoch+1,num_epoches, i+1,len(loader_train),-loss.item()/tsize))
if step% 10 ==0:
writer.add_scalar('loss', loss.item())
step+=1
# print('memory allocated: ', torch.cuda.memory_allocated(device=device))
# print('max memory allocated: ',torch.cuda.max_memory_allocated(device=device))
#save model
# if epoch % epoch_to_save==0:
# torch.save(model.state_dict(), os.path.join(logging_path,'net_epoch%d.pth'%(epoch+1)))
torch.save(model.state_dict(), os.path.join(logging_path,'newest.pth'))
def train(args):
device = torch.device(args.device)
cls_embed = ModelEmbeddings.load_from_file(args.pretrain_vector)
train_data = DataSet(args.train_data, args.train_labels, args.batch_size)
train_data.padtoMaxLen()
print('loading dev set...')
devSet, devlabels, devNum = DataSet.load_devSet(args.dev_data,
args.dev_labels)
print('Done dev loading.')
model = textCNN(args.embedding_size, args.cls_num, args.l1_channels_num)
model.train()
model = model.to(device)
cls_embed = cls_embed.to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=float(args.lr))
Loss_fun = torch.nn.CrossEntropyLoss()
dev_dataset = DataSet(args.dev_data, args.dev_labels, args.batch_size)
print('begin Maximum Likelihood training')
epoch = 0
sum_loss = 0
step = 0
while (True):
optimizer.zero_grad()
t, l, p = train_data.getTrainBatch()
l = torch.tensor(l, device=device)
# print("Doing word embed")
# print(type(t))
# print(type(l))
# print(l.requires_grad)
t = cls_embed(t, device=device)
# t=t.detach()
# print("Done word embed")
# print("feed into model...")
outPuts = model(t)
# print("Get answer!")
# print("Caluating Loss")
# print(outPuts.size())
# print(l.size())
# print(l)
# print(outPuts)
loss = Loss_fun(outPuts, l)
sum_loss += loss
print("epoch:{0},step:{1},train loss:{2}".format(epoch, step, loss))
step += 1
# print("Doing backPro")
loss.backward()
# print("Done backPro")
# print("Setping...")
optimizer.step()
# print("Done Step!")
# print('Current Batch Loss:{0}'.format(loss))
if (p):
epoch += p
print("Epoch mean Loss:{0}".format(sum_loss / step))
step = 0
sum_loss = 0
accuary, F1 = test(args, model, dev_dataset, cls_embed,
args.cls_num, device)
if (model.lastScore < F1):
model.lastScore = F1
torch.save(model.state_dict(), args.model_save_path)
torch.save(cls_embed, args.embedding_save_path)
if (epoch == args.max_epoch): break
def train_bpnet():
path = "mnist"
# dataset preparation
X_train, y_train = load_mnist(path, "train")
X_test, y_test = load_mnist(path, "t10k")
# dataset defination
train_data = DataSet(X_train, y_train)
test_data = DataSet(X_test, y_test)
# parameters defination
in_size = 784
hid_size = 100
out_size = 10
batch_size = 20
epoches = 150
# model defination
net = BpNet(in_size, hid_size, out_size)
print(train_data.input_data.shape, train_data.target_data.shape)
# determine inputs dtype
x = T.dmatrix("x")
y = T.dmatrix("y")
# defination of the layers
learning_rate = 0.1
prediction = net.forward(x)
# cost function defination
cost = cross_entropy_cost(prediction, y)
# update the grad
list_q = net.update_grad(cost, learning_rate)
# apply gradient descent
train = theano.function(inputs=[x, y], outputs=[cost], updates=list_q)
# prediction
predict = theano.function(inputs=[x], outputs=prediction)
# training model
loss_list = []
percentage_list = []
for k in range(epoches):
Length = len(X_train) // batch_size
sum_loss = 0
for j in range(Length):
out_x = X_train[j * batch_size:(j + 1) * batch_size, :]
out_y = y_train[j * batch_size:(j + 1) * batch_size, :]
err = train(out_x, out_y)
sum_loss += err[0]
out_pre = predict(test_data.input_data)
out_org = test_data.target_data
percentage = test_data_op(out_pre, out_org)
print("epoches:%d loss:%0.4f correct:%0.2f%%" %
(k, sum_loss / Length, percentage * 100))
loss_list.append(sum_loss / Length)
percentage_list.append(percentage)
# ----------------------------------------------------------------
# save the model
model_name = 'bpnet.pkt'
path_save = 'bpnet'
if not os.path.exists(path_save):
os.mkdir(path_save)
f = open(os.path.join(path_save, model_name), 'wb')
pickle.dump(net, f, protocol=pickle.HIGHEST_PROTOCOL)
f.close()
# ----------------------------------------------------------------
# save the loss image
x = np.linspace(0, len(loss_list), len(loss_list))
plt.plot(x, loss_list)
plt.savefig(os.path.join(path_save, "loss.png"))
plt.show()
with open(os.path.join(path_save, "loss.txt"), "w") as fp:
for k in range(len(loss_list)):
fp.write(str(loss_list[k]) + "\n")
x = np.linspace(0, len(percentage_list), len(percentage_list))
plt.plot(x, percentage_list)
plt.savefig(os.path.join(path_save, "percentage.png"))
plt.show()
with open(os.path.join(path_save, "percentage.txt"), "w") as fp:
for k in range(len(percentage_list)):
fp.write(str(percentage_list[k]) + "\n")
import torch.nn.functional as F
import torch.optim as optim
from datetime import datetime
from tensorboardX import SummaryWriter
from utils import DataSet, validate, show_confMat # 自定义类
from net import Net # 导入模型
# 定义超参
EPOCH = 5
BATCH_SIZE = 24
classes_name = [str(c) for c in range(16)]
# --------------------加载数据---------------------
# Indian Pines .mat文件路径(每个文件都是一个单独的类)
path = os.path.join(os.getcwd(), "patch")
training_dataset = DataSet(path=path, train=True)
testing_dataset = DataSet(path=path, train=False)
# Data Loaders
train_loader = torch.utils.data.DataLoader(
dataset=training_dataset,
batch_size=BATCH_SIZE,
shuffle=True
)
test_loader = torch.utils.data.DataLoader(
dataset=testing_dataset,
batch_size=BATCH_SIZE,
shuffle=True
)
# 检查cuda是否可用
def main():
dataset = DataSet(TRAIN, DEV, [TEST])
def do_training_step(model, iteration, task_iterations, batch_size,
train_images, train_labels):
from time import time
from utils import DataSet
iteration *= task_iterations
start = time()
train = DataSet(train_images, train_labels)
rate, factor = model['rate_factor']
learning_rate = rate / factor
neurons = model['neuron_number']
x = tf.placeholder(tf.float32, shape=[None, 784])
y_ = tf.placeholder(tf.float32, shape=[None, 10])
# First Convolutional layer
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
x_image = tf.reshape(x, [-1, 28, 28, 1])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
# Second Convolutional layer
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
# Densely Connected layer
W_fc1 = weight_variable([7 * 7 * 64, neurons])
b_fc1 = bias_variable([neurons])
h_pool2_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
# Dropout
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# Readout
W_fc2 = weight_variable([neurons, 10])
b_fc2 = bias_variable([10])
y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
cross_entropy = tf.reduce_mean(
-tf.reduce_sum(y_ * tf.log(y_conv), reduction_indices=[1]))
train_step = tf.train.AdamOptimizer(
learning_rate=learning_rate).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
saver = tf.train.Saver() # defaults to saving all variables
sess = tf.Session()
if iteration == 0:
init_op = tf.initialize_all_variables()
sess.run(init_op)
else:
try:
saver.restore(sess, model['path'])
import os
os.remove(model['path'])
os.remove("%s.meta" % model['path'])
print("Model %s correctly loaded i:%s" %
(model['path'], iteration))
except Exception as e:
print("No checkpoint for model %s found in iter %s\n%s" %
(model['path'], iteration, e))
sys.exit(1)
if not model:
model = dict()
t1 = time()
import numpy as np
step_times = np.array([])
for i in range(iteration, iteration + task_iterations):
ls = time()
batch_offset = i * batch_size
batch = train.get_batch(batch_offset, batch_size)
train_step.run(session=sess,
feed_dict={
x: batch[0],
y_: batch[1],
keep_prob: 0.5
})
# print("Iteration %s - %s s " % (i, time()-ls))
step_times = np.append(step_times, (time() - ls))
print("Loop\n Avg: %s\n Max: %s\n Min: %s" %
(step_times.mean(), step_times.max(), step_times.min()))
print("Loop time %s" % (time() - t1))
save_path = saver.save(sess, "%s_%s" % (model['base_path'], iteration))
model['path'] = save_path
training_accuracy = accuracy.eval(session=sess,
feed_dict={
x: batch[0],
y_: batch[1],
keep_prob: 1.0
})
model['train_accuracy'] = training_accuracy
end = time()
print(
"Training stats:\n - Neurons's number: %s\n - Learning rate: %s\n - Model: %s\n - Time: %s\n" % \
(neurons, learning_rate, save_path, (end - start)))
return model
return result
def read_image(image, name):
result = detect(image)
draw_result(image, result)
plt.imshow(image)
plt.savefig(os.getcwd() + '/' + name + 'output.png')
if settings.output == 1:
image = cv2.imread(settings.picture_name)
read_image(image, settings.picture_name[-10:])
if settings.output == 2:
labels = DataSet('test').load_labels()
for i in xrange(len(labels)):
print labels[i]['imname']
image = cv2.imread(labels[i]['imname'])
read_image(image, labels[i]['imname'][-10:])
if settings.output == 3:
cap = cv2.VideoCapture(-1)
ret, _ = cap.read()
while ret:
ret, frame = cap.read()
result = detect(frame)
draw_result(frame, result)
cv2.imshow('Camera', frame)
cv2.waitKey(wait)
def read_data(test_rate=0.1, one_hot=True):
"""read .dat data"""
# read data
true_inf = []
fake_inf = []
X = []
i = 1
filee = open('/home/summit/DDI/leftGFSK_DOWN.dat', 'rb')
try:
while True:
if (i != 65):
lines1 = filee.read(1)
lines2 = filee.read(1)
lines3 = filee.read(1)
lines4 = filee.read(1)
lines5 = filee.read(1)
lines6 = filee.read(1)
lines7 = filee.read(1)
lines8 = filee.read(1)
lines9 = filee.read(1)
lines10 = filee.read(1)
lines11 = filee.read(1)
lines12 = filee.read(1)
lines13 = filee.read(1)
lines14 = filee.read(1)
lines15 = filee.read(1)
lines16 = filee.read(1)
k1 = ord(lines1)
k2 = ord(lines2)
k3 = ord(lines3)
k4 = ord(lines4)
k5 = ord(lines5)
k6 = ord(lines6)
k7 = ord(lines7)
k8 = ord(lines8)
k9 = ord(lines9)
k10 = ord(lines10)
k11 = ord(lines11)
k12 = ord(lines12)
k13 = ord(lines13)
k14 = ord(lines14)
k15 = ord(lines15)
k16 = ord(lines16)
if k1 + k2 == 0:
break
X.append(
joint_col(k1, k2, k3, k4, k5, k6, k7, k8, k9, k10, k11,
k12, k13, k14, k15, k16))
a = np.array(X)
#print(i)
i = i + 1
else:
data = np.array(X)
data = data.reshape(data.shape[0], data.shape[1], 1) / 3.
X = []
true_inf.append(data)
i = 1
finally:
filee.close()
true_inf = np.stack(true_inf, axis=0)
X = []
i = 1
filee = open('/home/summit/DDI/leftGFSK_UP.dat', 'rb')
try:
while True:
if (i != 65):
lines1 = filee.read(1)
lines2 = filee.read(1)
lines3 = filee.read(1)
lines4 = filee.read(1)
lines5 = filee.read(1)
lines6 = filee.read(1)
lines7 = filee.read(1)
lines8 = filee.read(1)
lines9 = filee.read(1)
lines10 = filee.read(1)
lines11 = filee.read(1)
lines12 = filee.read(1)
lines13 = filee.read(1)
lines14 = filee.read(1)
lines15 = filee.read(1)
lines16 = filee.read(1)
k1 = ord(lines1)
k2 = ord(lines2)
k3 = ord(lines3)
k4 = ord(lines4)
k5 = ord(lines5)
k6 = ord(lines6)
k7 = ord(lines7)
k8 = ord(lines8)
k9 = ord(lines9)
k10 = ord(lines10)
k11 = ord(lines11)
k12 = ord(lines12)
k13 = ord(lines13)
k14 = ord(lines14)
k15 = ord(lines15)
k16 = ord(lines16)
if k1 + k2 == 0:
break
X.append(
joint_col(k1, k2, k3, k4, k5, k6, k7, k8, k9, k10, k11,
k12, k13, k14, k15, k16))
a = np.array(X)
#print(i)
i = i + 1
else:
data = np.array(X)
data = data.reshape(data.shape[0], data.shape[1], 1) / 3.
X = []
fake_inf.append(data)
i = 1
finally:
filee.close()
fake_inf = np.stack(fake_inf, axis=0)
# split train set and test 划分训练和数测试据集
test_split_true_inf = np.random.rand(true_inf.shape[0]) < test_rate
test_split_fake_inf = np.random.rand(fake_inf.shape[0]) < test_rate
test_true_inf = true_inf[test_split_true_inf, :, :, :]
test_label_true_inf = np.ones([test_true_inf.shape[0]])
train_true_inf = true_inf[np.logical_not(test_split_true_inf), :, :, :]
train_label_true_inf = np.ones([train_true_inf.shape[0]])
test_fake_inf = fake_inf[test_split_fake_inf, :, :, :]
test_label_fake_inf = np.ones([test_fake_inf.shape[0]]) * 2
train_fake_inf = fake_inf[np.logical_not(test_split_fake_inf), :, :, :]
train_label_fake_inf = np.ones([train_fake_inf.shape[0]]) * 2
test_infs = np.concatenate((test_true_inf, test_fake_inf), axis=0)
train_infs = np.concatenate((train_true_inf, train_fake_inf), axis=0)
test_labels = np.concatenate((test_label_true_inf, test_label_fake_inf),
axis=0)
train_labels = np.concatenate((train_label_true_inf, train_label_fake_inf),
axis=0)
if one_hot == True:
test_labels = test_labels.reshape(test_labels.shape[0], 1)
train_labels = train_labels.reshape(train_labels.shape[0], 1)
enc = OneHotEncoder()
enc.fit(test_labels)
test_labels = enc.transform(test_labels).toarray()
train_labels = enc.transform(train_labels).toarray()
#print("test_labels")
#print(test_labels)
#print("test_pics")
#print(test_pics)
#print("train_labels")
#print(train_labels)
#print("train_pics")
#print(train_pics)
data = utils.get_data(train=DataSet(images=train_infs,
labels=train_labels),
test=DataSet(images=test_infs, labels=test_labels))
print("type(data) line156")
print(type(data))
return data
import os
import sys
sys.path.append(os.path.join(os.path.dirname(__file__), './'))
import settings
import models
from utils import DataSet
import os
import time
import tensorflow as tf
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
import numpy as np
sess = tf.InteractiveSession()
model = models.Model()
utils = DataSet('train')
saver = tf.train.Saver(
var_list=tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, scope='yolo'))
sess.run(tf.global_variables_initializer())
try:
saver.restore(sess, os.getcwd() + '/model.ckpt')
print('load from past checkpoint')
except Exception as e:
print(e)
try:
print('load yolo small')
saver.restore(sess, os.getcwd() + '/YOLO_small.ckpt')
print('loaded from YOLO small pretrained')
except Exception as e:
print(e)
print('exit, atleast need a pretrained model')
def test(config):
model = SelfAttNet(config)
model.eval()
dataset = DataSet(cofig)
def do_testing(model, test_images, test_labels):
from time import time
from utils import DataSet
start = time()
rate, factor = model['rate_factor']
learning_rate = rate / factor
neurons = model['neuron_number']
test = DataSet(test_images, test_labels)
x = tf.placeholder(tf.float32, shape=[None, 784])
y_ = tf.placeholder(tf.float32, shape=[None, 10])
# First Convolutional layer
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
x_image = tf.reshape(x, [-1, 28, 28, 1])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
# Second Convolutional layer
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
# Densely Connected layer
W_fc1 = weight_variable([7 * 7 * 64, neurons])
b_fc1 = bias_variable([neurons])
h_pool2_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
# Dropout
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# Readout
W_fc2 = weight_variable([neurons, 10])
b_fc2 = bias_variable([10])
y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
cross_entropy = tf.reduce_mean(
-tf.reduce_sum(y_ * tf.log(y_conv), reduction_indices=[1]))
train_step = tf.train.AdamOptimizer(
learning_rate=learning_rate).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
saver = tf.train.Saver() # defaults to saving all variables
sess = tf.Session()
try:
saver.restore(sess, model['path'])
print("Model %s correctly loaded" % model['path'])
except Exception as e:
print("No checkpoint found\n%s" % e)
sys.exit(1)
test_accuracy = accuracy.eval(session=sess,
feed_dict={
x: test.images,
y_: test.labels,
keep_prob: 1.0
})
model['previous_test'] = model['test_accuracy']
model['test_accuracy'] = test_accuracy
end = time()
print(
"Testing stats:\n - Neurons's number: %s\n - Learning rate: %s\n - Test accuracy: %s\n - Model: %s\n - Time: %s\n" % \
(neurons, learning_rate, test_accuracy, model['path'], (end - start)))
return model
loss = loss / length
print(index, loss)
loss_svm.append(loss)
loss_svm = np.array(loss_svm)
x_list = np.linspace(0, len(loss_svm), len(loss_svm))
plt.plot(x_list, loss_svm)
plt.show()
f = open('RbmSvm.pt', 'wb')
pickle.dump(net, f, protocol=pickle.HIGHEST_PROTOCOL)
f.close()
if __name__ == '__main__':
file_path = "/home/asus/py3env/project/project/data/winequality-red.csv"
dataset = DataSet(file_path,
train=True,
transform=standard_vector,
target_transform=standard_vector)
dataloader = DataLoader(dataset, 10)
params = {
"input_size": 10,
"hidden_size": [100, 500],
"output_size": 1,
"learning_rate": 0.015,
"training_epoches": 120,
"pretrain_times": 7
}
# train_BpNet(dataloader,params)
# train_SvmMlp(dataloader,params)
# train_RbmSvm(dataloader,params)
trainDBNMlp(dataloader, params)
file_path = "/home/asus/py3env/project/project/data/winequality-red.csv"