def test_Embedding_ASM_act_14_exp_2_ACCV_fc_j0():
"""
just check the pose displaying
"""
from mpl_toolkits.mplot3d import Axes3D
import imgproc
import iread.h36m_hmlpe as h36m
data_path = "/opt/visal/tmp/for_sijin/Data/H36M/H36MExp/folder_Embedding_ASM_act_14_exp_2_ACCV_fc_j0/batches.meta"
data_path1 = "/opt/visal/tmp/for_sijin/Data/H36M/H36MExp/folder_SP_t004_act_14/batches.meta"
meta = mio.unpickle(data_path)
meta1 = mio.unpickle(data_path1)
print "Len of feature list is {} \t dims = {}".format(len(meta["feature_list"]), meta["feature_dim"])
for i, e in enumerate(meta["feature_list"]):
print "idx {}:\t shapes = {}".format(i, e.shape)
f0 = meta["feature_list"][0]
f0_1 = meta1["feature_list"][0]
ndata = f0.shape[-1]
limbs, params = h36m.part_idx, {"elev": -89, "azim": -107, "linewidth": 3}
fig = pl.figure()
idx = 0
fig.add_subplot(2, 1, 1, projection="3d")
p = f0[..., idx].reshape((-1, 1), order="F") * 1200
p1 = f0_1[..., idx].reshape((-1, 1), order="F")
print p
pp = df.convert_relskel2rel(p).reshape((-1, 1), order="F")
diff = pp.reshape((-1, 1), order="F") - p1
imgproc.turn_off_axis()
dutils.show_3d_skeleton(p1, limbs, params)
pl.show()
print """
def test_Embedding_ASM_act_14_exp_2_ACCV_fc_j0():
"""
just check the pose displaying
"""
from mpl_toolkits.mplot3d import Axes3D
import imgproc
import iread.h36m_hmlpe as h36m
data_path = '/opt/visal/tmp/for_sijin/Data/H36M/H36MExp/folder_Embedding_ASM_act_14_exp_2_ACCV_fc_j0/batches.meta'
data_path1 = '/opt/visal/tmp/for_sijin/Data/H36M/H36MExp/folder_SP_t004_act_14/batches.meta'
meta = mio.unpickle(data_path)
meta1 = mio.unpickle(data_path1)
print 'Len of feature list is {} \t dims = {}'.format(
len(meta['feature_list']), meta['feature_dim'])
for i, e in enumerate(meta['feature_list']):
print 'idx {}:\t shapes = {}'.format(i, e.shape)
f0 = meta['feature_list'][0]
f0_1 = meta1['feature_list'][0]
ndata = f0.shape[-1]
limbs, params = h36m.part_idx, {'elev': -89, 'azim': -107, 'linewidth': 3}
fig = pl.figure()
idx = 0
fig.add_subplot(2, 1, 1, projection='3d')
p = f0[..., idx].reshape((-1, 1), order='F') * 1200
p1 = f0_1[..., idx].reshape((-1, 1), order='F')
print p
pp = df.convert_relskel2rel(p).reshape((-1, 1), order='F')
diff = pp.reshape((-1, 1), order='F') - p1
imgproc.turn_off_axis()
dutils.show_3d_skeleton(p1, limbs, params)
pl.show()
print '''
def do_accveval(self):
images_folder = self.op.get_value('images_folder')
# get all jpg file in images_folder
allfiles = iu.getfilelist(images_folder, '.*\.jpg')
images_path = [iu.fullfile(images_folder, p) for p in allfiles]
n_image = len(images_path)
images = self.load_images(images_path)
mean_image_path = self.op.get_value('mean_image_path')
mean_image = sio.loadmat(mean_image_path)['cropped_mean_image']
mean_image_arr = mean_image.reshape((-1, 1), order='F')
input_images = images - mean_image_arr
# pack input images into batch data
data = [
input_images,
np.zeros((51, n_image), dtype=np.single),
np.zeros((1700, n_image), dtype=np.single)
]
# allocate the buffer for prediction
pred_buffer = np.zeros((n_image, 51), dtype=np.single)
data.append(pred_buffer)
ext_data = [
np.require(elem, dtype=np.single, requirements='C')
for elem in data
]
# run the model
## get the joint prediction layer indexes
self.pred_layer_idx = self.get_layer_idx('fc_j2', check_type='fc')
self.libmodel.startFeatureWriter(ext_data, self.pred_layer_idx)
self.finish_batch()
raw_pred = ext_data[-1].T
pred = dhmlpe_features.convert_relskel2rel(raw_pred) * 1200.0
# show the first prediction
show_idx = 0
img = np.array(Image.open(images_path[show_idx]))
fig = pl.figure(0)
ax1 = fig.add_subplot(121)
ax1.imshow(img)
ax2 = fig.add_subplot(122, projection='3d')
cur_pred = pred[..., show_idx].reshape((3, -1), order='F')
part_idx = iread.h36m_hmlpe.part_idx
params = {'elev': -94, 'azim': -86, 'linewidth': 6, 'order': 'z'}
dutils.show_3d_skeleton(cur_pred.T, part_idx, params)
def do_accveval(self):
images_folder = self.op.get_value('images_folder')
# get all jpg file in images_folder
allfiles = iu.getfilelist(images_folder, '.*\.jpg')
images_path = [iu.fullfile(images_folder, p) for p in allfiles]
n_image = len(images_path)
images = self.load_images(images_path)
mean_image_path = self.op.get_value('mean_image_path')
mean_image = sio.loadmat(mean_image_path)['cropped_mean_image']
mean_image_arr = mean_image.reshape((-1,1),order='F')
input_images = images - mean_image_arr
# pack input images into batch data
data = [input_images, np.zeros((51,n_image),dtype=np.single),
np.zeros((1700,n_image), dtype=np.single)]
# allocate the buffer for prediction
pred_buffer = np.zeros((n_image, 51),dtype=np.single)
data.append(pred_buffer)
ext_data = [np.require(elem,dtype=np.single, requirements='C') for elem in data]
# run the model
## get the joint prediction layer indexes
self.pred_layer_idx = self.get_layer_idx('fc_j2',check_type='fc')
self.libmodel.startFeatureWriter(ext_data, self.pred_layer_idx)
self.finish_batch()
raw_pred = ext_data[-1].T
pred = dhmlpe_features.convert_relskel2rel(raw_pred) * 1200.0
# show the first prediction
show_idx = 0
img = np.array(Image.open(images_path[show_idx]))
fig = pl.figure(0)
ax1 = fig.add_subplot(121)
ax1.imshow(img)
ax2 = fig.add_subplot(122,projection='3d')
cur_pred = pred[..., show_idx].reshape((3,-1),order='F')
part_idx = iread.h36m_hmlpe.part_idx
params = {'elev':-94, 'azim':-86, 'linewidth':6, 'order':'z'}
dutils.show_3d_skeleton(cur_pred.T, part_idx, params)
def convert_relskel2rel(cls, x):
import dhmlpe_features as df
return df.convert_relskel2rel(x)
def convert_relskel2rel(cls, x):
import dhmlpe_features as df
return df.convert_relskel2rel(x)