def main():
training_images, training_labels, testing_images, testing_labels = get_data(CIFAR10_FOLDER)
(training_set, training_labels,
testing_set, testing_labels) = subsample_data(training_images, training_labels,
testing_images, testing_labels,
training_num=5000, testing_num=500)
normalize_data(training_set, testing_set)
cross_validate_all_classifiers(training_set, training_labels,
testing_set, testing_labels)
def read_all_data(self, actions, data_dir, one_hot=False):
"""
Loads data for training/testing and normalizes it.
Args
actions: list of strings (actions) to load
seq_length_in: number of frames to use in the burn-in sequence
seq_length_out: number of frames to use in the output sequence
data_dir: directory to load the data from
one_hot: whether to use one-hot encoding per action
Returns
train_set: dictionary with normalized training data
test_set: dictionary with test data
data_mean: d-long vector with the mean of the training data
data_std: d-long vector with the standard dev of the training data
dim_to_ignore: dimensions that are not used becaused stdev is too small
dim_to_use: dimensions that we are actually using in the model
"""
train_subject_ids = [1, 6, 7, 8, 9, 11]
test_subject_ids = [5]
train_set, complete_train = data_utils.load_data(
data_dir, train_subject_ids, actions, one_hot)
test_set, complete_test = data_utils.load_data(data_dir,
test_subject_ids,
actions, one_hot)
# Compute normalization stats
data_mean, data_std, dim_to_ignore, dim_to_use = data_utils.normalization_stats(
complete_train)
# Normalize -- subtract mean, divide by stdev
train_set = data_utils.normalize_data(train_set, data_mean, data_std,
dim_to_use, actions, one_hot)
test_set = data_utils.normalize_data(test_set, data_mean, data_std,
dim_to_use, actions, one_hot)
print("done reading data.")
self.train_set = train_set
self.test_set = test_set
self.data_mean = data_mean
self.data_std = data_std
self.dim_to_ignore = dim_to_ignore
self.dim_to_use = dim_to_use
self.train_keys = list(self.train_set.keys())
def read_all_data(actions=walking_lst,
seq_length_in=50,
seq_length_out=25,
data_dir="./data/h3.6m/dataset",
one_hot=True):
"""
Loads data for training/testing and normalizes it.
Args
actions: list of strings (actions) to load
seq_length_in: number of frames to use in the burn-in sequence
seq_length_out: number of frames to use in the output sequence
data_dir: directory to load the data from
one_hot: whether to use one-hot encoding per action
Returns
train_set: dictionary with normalized training data
test_set: dictionary with test data
data_mean: d-long vector with the mean of the training data
data_std: d-long vector with the standard dev of the training data
dim_to_ignore: dimensions that are not used becaused stdev is too small
dim_to_use: dimensions that we are actually using in the model
"""
# === Read training data ===
print("Reading training data (seq_len_in: {0}, seq_len_out {1}).".format(
seq_length_in, seq_length_out))
train_subject_ids = [1, 6, 7, 8, 9, 11]
test_subject_ids = [5]
train_set, complete_train = data_utils.load_data(data_dir,
train_subject_ids,
actions, one_hot)
test_set, complete_test = data_utils.load_data(data_dir, test_subject_ids,
actions, one_hot)
# Compute normalization stats
data_mean, data_std, dim_to_ignore, dim_to_use = data_utils.normalization_stats(
complete_train)
# Normalize -- subtract mean, divide by stdev
train_set = data_utils.normalize_data(train_set, data_mean, data_std,
dim_to_use, actions, one_hot)
test_set = data_utils.normalize_data(test_set, data_mean, data_std,
dim_to_use, actions, one_hot)
print("done reading data.")
return train_set, test_set, data_mean, data_std, dim_to_ignore, dim_to_use
def perform_noisy_actions(train_set_noisy, train_set_2d_org, camera_frame,
rcams, predict_14, percent):
#validate(train_set, train_set)
print('Performing noisy actions now..')
train_set_3d_noisy = addNoiseTo3D(train_set_noisy, percent)
#got the 3d data and now do 2d things
train_set_2d_noisy = du.project_to_cameras(train_set_3d_noisy, rcams)
#there can be augmented 2d data
train_set_2d_org.update(train_set_2d_noisy)
# Compute normalization statistics.
complete_train = copy.deepcopy(np.vstack(train_set_2d_org.values()))
data_mean, data_std, dim_to_ignore, dim_to_use = du.normalization_stats(
complete_train, dim=2)
# Divide every dimension independently
train_set_2d_org = du.normalize_data(train_set_2d_org, data_mean, data_std,
dim_to_use)
print("For noisy, mean :")
print(data_mean)
print("For noisy, std :")
print(data_std)
print('noisy actions done..')
return train_set_2d_org, data_mean, data_std
def create_task(self, ind_task, x_tr, y_tr, x_te, y_te):
# select only the good classes
class_min, class_max, i_tr = self.select_index(ind_task, y_tr)
_, _, i_te = self.select_index(ind_task, y_te)
i_tr, i_va = self.get_valid_ind(i_tr)
x_tr = normalize_data(self.dataset, x_tr)
x_te = normalize_data(self.dataset, x_te)
x_tr_t = self.transformation(ind_task, x_tr[i_tr])
x_va_t = self.transformation(ind_task, x_tr[i_va])
x_te_t = self.transformation(ind_task, x_te[i_te])
y_tr_t = self.label_transformation(ind_task, y_tr[i_tr])
y_va_t = self.label_transformation(ind_task, y_tr[i_va])
y_te_t = self.label_transformation(ind_task, y_te[i_te])
return class_min, class_max, x_tr_t, y_tr_t, x_va_t, y_va_t, x_te_t, y_te_t
def predict_on_stocks(array: numpy.array, model_path: str, interval: str,
stock_path: str):
scaler = StandardScaler()
open_data, close_data = init_data(array)
open_data, close_data = normalize_data(open_data, close_data, scaler)
(x_train, y_train, x_test, y_test) = split_data(open_data, close_data)
(x_train, y_train) = shuffle_data(x_train, y_train)
(model, checkpoint_callback) = create_model(model_path)
model.fit(x_train,
y_train,
validation_data=(x_test, y_test),
batch_size=64,
epochs=EPOCHS,
callbacks=[checkpoint_callback])
#test_model(model, x_test, y_test, scaler, interval) // uncomment this if you want to test the ai efficiency
dump(scaler, f'{model_path}/std_scaler.bin', compress=True)
def process_images(names, out_loc, mean=None, sd=None):
print('Names: ', names)
dataset = NORBDataset(dataset_root='/dfs/scratch1/thomasat/datasets/norb', names=names)
Xs = []
Ys = []
print('Dataset names: ', dataset.data.keys())
for name in names:
X, Y = process_data(dataset.data[name])
print('X,Y shape: ', X.shape, Y.shape)
Xs.append(X)
Ys.append(Y)
X = np.vstack(Xs)
Y = np.vstack(Ys)
# Shuffle
idx = np.arange(0, X.shape[0])
np.random.shuffle(idx)
X = X[idx,:]
Y = Y[idx,:]
if mean is None and sd is None:
X, mean, sd = normalize_data(X)
print('X, Y: ', X.shape, Y.shape)
else:
X = apply_normalization(X,mean,sd)
# Save
data_dict = {'X': X, 'Y': Y}
pkl.dump(data_dict, open(out_loc, 'wb'), protocol=2)
return mean,sd
def get_testing_batch():
while True:
for sequence in test_loader:
batch = data_utils.normalize_data(opt, dtype, sequence)
yield batch
def preprocess(self):
self.mappings = enumerate_strings(self.df)
self.df = normalize_data(self.df, self.target)
self.df.head()
enc = OneHotEncoder()
Y = enc.fit_transform(Y).todense()
return X, Y
train_loc = '/dfs/scratch1/thomasat/datasets/convex/convex_train.amat'
test_loc = '/dfs/scratch1/thomasat/datasets/convex/50k/convex_test.amat'
train_out = '/dfs/scratch1/thomasat/datasets/convex/train_normalized'
test_out = '/dfs/scratch1/thomasat/datasets/convex/test_normalized'
train_data = np.genfromtxt(train_loc)
train_X, train_Y = process_data(train_data)
test_data = np.genfromtxt(test_loc)
test_X, test_Y = process_data(test_data)
# Normalize
train_X, mean, sd = normalize_data(train_X)
test_X = apply_normalization(test_X, mean, sd)
# Save
print('test_X, test_Y shape: ', test_X.shape, test_Y.shape)
print('train_X, train_Y shape: ', train_X.shape, train_Y.shape)
train = {'X': train_X, 'Y': train_Y}
test = {'X': test_X, 'Y': test_Y}
pkl.dump(train, open(train_out, 'wb'), protocol=2)
pkl.dump(test, open(test_out, 'wb'), protocol=2)
print('Saved train to: ', train_out)
print('Saved test to: ', test_out)
#!/usr/bin/env python
import data_utils as a1
import numpy as np
import matplotlib.pyplot as plt
(countries, features, values) = a1.load_unicef_data()
targets = values[:,1]
x = values[:,7:]
x = a1.normalize_data(x)
N_TRAIN = 100;
x_train = x[0:N_TRAIN,:]
x_test = x[N_TRAIN:,:]
t_train = targets[0:N_TRAIN]
t_test = targets[N_TRAIN:]
train_err = dict()
test_err = dict()
for i in range(1,7):
(w,train_err[i]) = a1.linear_regression(x_train,t_train,'polynomial',degree = i)
(t_est,test_err[i]) = a1.evaluate_regression(x_test,t_test,w,'polynomial',degree = i)
# Produce a plot of results.
plt.plot(list(train_err.keys()), list(train_err.values()))
plt.plot(list(test_err.keys()), list(test_err.values()))
plt.ylabel('RMS')
plt.legend(['Training error','Test error'])
plt.title('Fit with polynomials, no regularization')
import warnings
import os
# suppress warnings
warnings.filterwarnings('ignore')
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
# read data
data = pd.read_csv("prices-split-adjusted.csv", index_col=0)
data['adj close'] = data.close
data.drop(['close'], 1, inplace=True)
data = data[data.symbol == 'GOOG']
data.drop(['symbol'], 1, inplace=True)
# normalize data
df = normalize_data(data)
# load data
window = 22
x_train, y_train, x_test, y_test = load_data(df, seq_len=window)
# create model and fit dataset
model = lstm_rnn_model([5, window, 1])
model.fit(x_train,
y_train,
batch_size=512,
epochs=90,
validation_split=0.1,
verbose=1)
diff = []
import data_utils
from viz import Ax3DPose
data_dir = './data/h36m/dataset'
train_subject_ids = [1, 6, 7, 8, 9, 11]
test_subject_ids = [5]
actions = [
"walking", "eating", "smoking", "discussion", "directions", "greeting",
"phoning", "posing", "purchases", "sitting", "sittingdown", "takingphoto",
"waiting", "walkingdog", "walkingtogether"
]
one_hot = True
train_set, complete_train = data_utils.load_data(data_dir, train_subject_ids,
actions, one_hot)
test_set, complete_test = data_utils.load_data(data_dir, test_subject_ids,
actions, one_hot)
data_mean, data_std, dim_to_ignore, dim_to_use = data_utils.normalization_stats(
complete_train)
train_set = data_utils.normalize_data(train_set, data_mean, data_std,
dim_to_use, actions, one_hot)
test_set = data_utils.normalize_data(test_set, data_mean, data_std, dim_to_use,
actions, one_hot)
print("done reading data.")
print(train_set[(1, "walking", 1, "even")])
for file_name in sorted(os.listdir(args.input_dir)):
file_path = os.path.abspath(os.path.join(args.input_dir, file_name))
# Extract the cell_id from the file name.
cell_id = get_base_file_name(file_name)
# Load or generate synthetic level set data
# if params_dict['genData']:
if False:
# TODO: data = genSphereLevelSet(DEFAULT_MLE_SPHERE_PARAM_DICT, bounding_box, param_dict, nLevelSet)
meanR = [0, 0, 0]
# TODO: save(PrjCtrl.inputFileLevelSetDataM,'data')
else:
data = data_utils.load_raw3d_data(file_path)
log_fh.write("First 5 data points before normalization: {}\n".format(
data[:5]))
data, meanR = data_utils.normalize_data(data, log_fh)
log_fh.write(
"\nFirst 5 data points after normalization: {}\n\n".format(
data[:5]))
log_fh.write("mean radius {}".format(meanR))
# TODO: nLevelSet = data.shape[0]
# Set summary parameters
param_ss = param_ss.ParamSS(data.shape[0], meanR)
# Starting value for parameters
if param_dict['randomStart']:
mles_param_dict = mle_sphere.mle_sphere(data, cell_id, param_dict,
log_fh)
else:
mles_param_dict = DEFAULT_MLE_SPHERE_PARAM_DICT
def sample(self, input_):
"""Sample predictions for srnn's seeds"""
actions = ["posing"]
if True:
# === Create the model ===
# print("Creating %d layers of %d units." % (args.num_layers, args.size))
# sampling = True
# model = create_model(actions, sampling)
if not self.args.use_cpu:
self.model = self.model.cuda()
# print("Model created")
# Load all the data
# train_set, test_set, data_mean, data_std, dim_to_ignore, dim_to_use = read_all_data(
# actions, args.seq_length_in, args.seq_length_out, args.data_dir, not args.omit_one_hot )
#"++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++"
nactions = len(actions)
subjects = [5]
testData = {}
tmp = input_
# start = time.time()
for subj in subjects:
for action_idx in np.arange(len(actions)):
action = actions[action_idx]
for subact in [1]: # subactions
action_sequence = tmp
n, d = action_sequence.shape
even_list = range(0, n, 2)
if not self.args.omit_one_hot:
# Add a one-hot encoding at the end of the representation
the_sequence = np.zeros(
(len(even_list), d + nactions), dtype=float)
the_sequence[:,
0:d] = action_sequence[even_list, :]
the_sequence[:, d + action_idx] = 1
testData[(subj, action, subact,
'even')] = the_sequence
else:
testData[(subj, action, subact,
'even')] = action_sequence[even_list, :]
test_set = data_utils.normalize_data(testData, self.data_mean,
self.data_std,
self.dim_to_use, actions,
not self.args.omit_one_hot)
#"++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++"
# === Read and denormalize the gt with srnn's seeds, as we'll need them
# many times for evaluation in Euler Angles ===
#srnn_gts_expmap = self.get_srnn_gts( actions, self.model, test_set, self.data_mean,
#self.data_std, self.dim_to_ignore, not self.args.omit_one_hot, to_euler=False )
#srnn_gts_exmap是ground truth!!
# print(data_mean.shape)
# print(data_std.shape)
# # srnn_gts_euler = get_srnn_gts( actions, model, test_set, data_mean,
# data_std, dim_to_ignore, not args.omit_one_hot )
# Clean and create a new h5 file of samples
# SAMPLES_FNAME = 'samples.h5'
# try:
# os.remove( SAMPLES_FNAME )
# except OSError:
# pass
# Predict and save for each action
for action in actions:
# Make prediction with srnn' seeds
encoder_inputs, decoder_inputs = self.model.get_batch_srnn(
test_set, action, False)
# print("shape:",encoder_inputs.shape)
# print(decoder_inputs.shape)
encoder_inputs = torch.from_numpy(encoder_inputs).float()
decoder_inputs = torch.from_numpy(decoder_inputs).float()
#decoder_outputs = torch.from_numpy(decoder_outputs).float()
if not self.args.use_cpu:
encoder_inputs = encoder_inputs.cuda()
decoder_inputs = decoder_inputs.cuda()
#decoder_outputs = decoder_outputs.cuda()
encoder_inputs = Variable(encoder_inputs)
decoder_inputs = Variable(decoder_inputs)
#decoder_outputs = Variable(decoder_outputs)
srnn_poses = self.model(encoder_inputs, decoder_inputs)
# print(encoder_inputs.shape)
# print(decoder_inputs.shape)
#srnn_loss = (srnn_poses - decoder_outputs)**2
#srnn_loss.cpu().data.numpy()
#srnn_loss = srnn_loss.mean()
srnn_poses = srnn_poses.cpu().data.numpy()
srnn_poses = srnn_poses.transpose([1, 0, 2])
#srnn_loss = srnn_loss.cpu().data.numpy()
# denormalizes too
srnn_pred_expmap = data_utils.revert_output_format(
srnn_poses, self.data_mean, self.data_std,
self.dim_to_ignore, actions, not self.args.omit_one_hot)
return srnn_pred_expmap[0]
def main(_):
actions_all = data_utils.define_actions("All")
actions = data_utils.define_actions("Discussion")
# Load camera parameters
SUBJECT_IDS = [1, 5, 6, 7, 8, 9, 11]
rcams = cameras.load_cameras(FLAGS.cameras_path, SUBJECT_IDS)
# Load 3d data and load (or create) 2d projections
train_set_3d, test_set_3d, data_mean_3d, data_std_3d, dim_to_ignore_3d, dim_to_use_3d, train_root_positions, test_root_positions = data_utils.read_3d_data(
actions, FLAGS.data_dir, FLAGS.camera_frame, rcams, FLAGS.predict_14)
train_set_3d = data_utils.remove_first_frame(train_set_3d)
test_set_3d = data_utils.remove_first_frame(test_set_3d)
train_root_positions = data_utils.remove_first_frame(train_root_positions)
test_root_positions = data_utils.remove_first_frame(test_root_positions)
print("Finished Read 3D Data")
# train_set_2d, test_set_2d, data_mean_2d, data_std_2d, dim_to_ignore_2d, dim_to_use_2d = data_utils.read_2d_predictions(actions_all, FLAGS.data_dir)
# train_set_2d, test_set_2d, data_mean_2d, data_std_2d, dim_to_ignore_2d, dim_to_use_2d = data_utils.transform_to_2d_biframe_prediction(train_set_2d,
# test_set_2d,
# data_mean_2d,
# data_std_2d,
# dim_to_ignore_2d,
# dim_to_use_2d)
train_set_2d, test_set_2d, data_mean_2d, data_std_2d, dim_to_ignore_2d, dim_to_use_2d = data_utils.create_2d_data(
actions_all, FLAGS.data_dir, rcams)
train_set_2d, test_set_2d, data_mean_2d, data_std_2d, dim_to_ignore_2d, dim_to_use_2d = data_utils.transform_to_2d_biframe_prediction(
train_set_2d, test_set_2d, data_mean_2d, data_std_2d, dim_to_ignore_2d,
dim_to_use_2d)
SH_TO_GT_PERM = np.array(
[SH_NAMES.index(h) for h in H36M_NAMES if h != '' and h in SH_NAMES])
assert np.all(SH_TO_GT_PERM == np.array(
[6, 2, 1, 0, 3, 4, 5, 7, 8, 9, 13, 14, 15, 12, 11, 10]))
test_set = {}
manipulation_dir = os.path.dirname(FLAGS.data_dir)
manipulation_dir = os.path.dirname(manipulation_dir)
manipulation_dir += '/manipulation_video/'
manipulation_folders = glob.glob(manipulation_dir + '*')
subj = 1
action = 'manipulation-video'
for folder in manipulation_folders:
seqname = os.path.basename(folder)
with h5py.File(folder + '/' + seqname + '.h5', 'r') as h5f:
poses = h5f['poses'][:]
# Permute the loaded data to make it compatible with H36M
poses = poses[:, SH_TO_GT_PERM, :]
# Reshape into n x (32*2) matrix
poses = np.reshape(poses, [poses.shape[0], -1])
poses_final = np.zeros([poses.shape[0], len(H36M_NAMES) * 2])
dim_to_use_x = np.where(
np.array([x != '' and x != 'Neck/Nose'
for x in H36M_NAMES]))[0] * 2
dim_to_use_y = dim_to_use_x + 1
dim_to_use = np.zeros(len(SH_NAMES) * 2, dtype=np.int32)
dim_to_use[0::2] = dim_to_use_x
dim_to_use[1::2] = dim_to_use_y
poses_final[:, dim_to_use] = poses
print(seqname, poses_final.shape)
poses_final[poses_final == 0.] = 0.1
test_set[(subj, action, seqname)] = poses_final
test_set = data_utils.uni_frame_to_bi_frame(test_set)
test_set_2d = data_utils.normalize_data(test_set, data_mean_2d,
data_std_2d, dim_to_use_2d)
for key in test_set.keys():
test_set[key] = test_set[key][0::2, :]
dim_to_use_12_manipulation_joints = np.array([
3, 4, 5, 6, 7, 8, 9, 10, 11, 18, 19, 20, 21, 22, 23, 24, 25, 26, 51,
52, 53, 54, 55, 56, 57, 58, 59, 75, 76, 77, 78, 79, 80, 81, 82, 83
])
print("Finished Normalize Manipualtion Videos")
device_count = {"GPU": 0} if FLAGS.use_cpu else {"GPU": 1}
with tf.Session(config=tf.ConfigProto(device_count=device_count)) as sess:
# === Create the model ===
print("Creating %d layers of %d units." %
(FLAGS.num_layers, FLAGS.linear_size))
batch_size = FLAGS.batch_size #Intial code is 64*2
model = predict_3dpose_biframe.create_model(sess, actions_all,
batch_size)
print("Model loaded")
j = 0
for key2d in test_set_2d.keys():
(subj, b, fname) = key2d
# if fname != specific_seqname + '.h5':
# continue
print("Subject: {}, action: {}, fname: {}".format(subj, b, fname))
enc_in = test_set_2d[key2d]
n2d, _ = enc_in.shape
# Split into about-same-size batches
enc_in = np.array_split(enc_in, n2d // 1)
all_poses_3d = []
for bidx in range(len(enc_in)):
# Dropout probability 0 (keep probability 1) for sampling
dp = 1.0
anything = np.zeros((enc_in[bidx].shape[0], 48))
_, _, poses3d = model.step(sess,
enc_in[bidx],
anything,
dp,
isTraining=False)
# Denormalize
enc_in[bidx] = data_utils.unNormalizeData(
enc_in[bidx], data_mean_2d, data_std_2d, dim_to_ignore_2d)
poses3d = data_utils.unNormalizeData(poses3d, data_mean_3d,
data_std_3d,
dim_to_ignore_3d)
all_poses_3d.append(poses3d)
# Put all the poses together
enc_in, poses3d = map(np.vstack, [enc_in, all_poses_3d])
enc_in, poses3d = map(np.vstack, [enc_in, poses3d])
poses3d_12_manipulation = poses3d[:,
dim_to_use_12_manipulation_joints]
annotated_images = glob.glob(manipulation_dir + fname +
'/info/*.xml')
annotated_images = sorted(annotated_images)
# 1080p = 1,920 x 1,080
fig = plt.figure(j, figsize=(10, 10))
gs1 = gridspec.GridSpec(3, 3)
gs1.update(wspace=-0, hspace=0.1) # set the spacing between axes.
plt.axis('off')
subplot_idx = 1
nsamples = 3
for i in np.arange(nsamples):
# Plot 2d Detection
ax1 = plt.subplot(gs1[subplot_idx - 1])
img = mpimg.imread(
manipulation_dir + fname + '/skeleton_cropped/' +
os.path.basename(annotated_images[i]).split('_')[0] +
'.jpg')
ax1.imshow(img)
# Plot 2d pose
ax2 = plt.subplot(gs1[subplot_idx])
# p2d = enc_in[i,:]
# viz.show2Dpose( p2d, ax2 )
# ax2.invert_yaxis()
ax2.imshow(img)
# Plot 3d predictions
# Compute first the procrustion and print error
gt = getJ3dPosFromXML(annotated_images[i])
A = poses3d_12_manipulation[i, :].reshape(gt.shape)
_, Z, T, b, c = procrustes.compute_similarity_transform(
gt, A, compute_optimal_scale=True)
sqerr = np.sqrt(np.sum((gt - (b * A.dot(T)) - c)**2, axis=1))
print("{0} - {1} - Mean Error (mm) : {2}".format(
fname, os.path.basename(annotated_images[i]),
np.mean(sqerr)))
ax3 = plt.subplot(gs1[subplot_idx + 1], projection='3d')
temp = poses3d[i, :].reshape((32, 3))
temp = c + temp.dot(T) #Do not scale
# p3d = temp.reshape((1, 96))
p3d = poses3d[i, :]
viz.show3Dpose(p3d, ax3, lcolor="#9b59b6", rcolor="#2ecc71")
ax3.invert_zaxis()
ax3.invert_yaxis()
subplot_idx = subplot_idx + 3
plt.show()
j += 1
print("Normalized: " + str(NORMALIZED))
print("Center Data: " + str(CENTER_DATA))
if (".h5" in TEST_FILE):
TEST_DATA, TEST_LABELS = data_utils.load_h5(TEST_FILE)
else:
TEST_DATA, TEST_LABELS = data_utils.load_data(TEST_FILE,
NUM_POINT,
with_bg_pl=WITH_BG)
if (CENTER_DATA):
TEST_DATA = data_utils.center_data(TEST_DATA)
if (NORMALIZED):
TEST_DATA = data_utils.normalize_data(TEST_DATA)
def log_string(out_str):
LOG_FOUT.write(out_str + '\n')
LOG_FOUT.flush()
print(out_str)
def corrupt(batch_data):
output = []
for i in range(batch_data.shape[0]):
pc = batch_data[i, :, :]
pc = pc[pc[:, 2] > THRESH, :]
output.append(pc)
def read_all_data(actions, data_dir, one_hot, GT=False):
"""
Loads data for training/testing and normalizes it.
Args
Returns
"""
# === Read training data ===
print("Reading training data")
#####
#need to add one-hot vector to each frame later
#####
for i, action in enumerate(actions):
action_seq = np.load(data_dir + '/' + action + '.npz')['seq']
action_seq_len = np.load(data_dir + '/' + action + '.npz')['seq_len']
all_seq = np.concatenate(
(all_seq, action_seq), axis=0) if i > 0 else action_seq
all_seq_len = np.concatenate((all_seq_len, action_seq_len), axis=0) \
if i > 0 else action_seq_len
for i in range(len(all_seq)):
if all_seq[i, 0, 0, 0, 0] > all_seq[i, 1, 0, 0, 0]:
all_seq[i, :, :, :, 1] = -all_seq[i, :, :, :, 1]
"""
all_seq: [data_index, skeleton_num, frame_len, joints, xyz]
"""
all_seq = data_utils.rotate_data(all_seq)
shape = all_seq.shape
all_seq = np.reshape(all_seq, [shape[0], shape[1], shape[2], -1])
np.savez('val.npz', seq=all_seq)
from sklearn.model_selection import train_test_split
train_seq, test_seq, train_seq_len, test_seq_len = train_test_split(
all_seq, all_seq_len, test_size=0.25, random_state=1)
if GT:
return test_seq
for i, (seq, seq_len) in enumerate(zip(train_seq, train_seq_len)):
try:
complete_seq = np.concatenate((complete_seq, seq[: ,:int(seq_len)]), axis=1) if i > 0 \
else seq[:, :int(seq_len)]
except TypeError:
import pdb
pdb.set_trace()
complete_real_person, complete_character = complete_seq
'''
#for data_visualization
np.savez('all_data_mirror.npz',
real_person=complete_real_person,
character=complete_character,
ground_truth=complete_character,
loss=0)
sys.exit()
'''
# Compute normalization stats
rp_stats = data_utils.normalization_stats(complete_real_person,
FLAGS.dim_to_compressed)
ch_stats = data_utils.normalization_stats(complete_character,
FLAGS.dim_to_compressed)
# Normalize -- subtract mean, divide by stdev
train_shape = train_seq.shape
test_shape = test_seq.shape
if rp_stats[4] is not None:
normalized_train_seq = np.zeros([
train_shape[0], train_shape[1], train_shape[2],
rp_stats[4].get_params()['n_components']
])
normalized_test_seq = np.zeros([
test_shape[0], test_shape[1], test_shape[2],
rp_stats[4].get_params()['n_components']
])
else:
normalized_train_seq = np.zeros(train_shape)
normalized_test_seq = np.zeros(test_shape)
normalized_train_seq[:, 0] = data_utils.normalize_data(
train_seq[:, 0], rp_stats, actions, one_hot)
normalized_train_seq[:, 1] = data_utils.normalize_data(
train_seq[:, 1], ch_stats, actions, one_hot)
normalized_test_seq[:,
0] = data_utils.normalize_data(test_seq[:,
0], rp_stats,
actions, one_hot)
normalized_test_seq[:,
1] = data_utils.normalize_data(test_seq[:,
1], ch_stats,
actions, one_hot)
print("done reading data.")
return normalized_train_seq, normalized_test_seq, train_seq_len, test_seq_len, rp_stats, ch_stats, \
max(all_seq_len)
