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 show_the_most_violated_poses():
from mpl_toolkits.mplot3d import Axes3D
import imgproc
saved_model_path = '/public/sijinli2/ibuffer/2015-01-16/net2_test_for_stat'
saved_model_path = '/opt/visal/tmp/for_sijin/Data/saved/theano_models/FCJ0_act_14_graph_0029_test_norm_cumulate_update'
data_path = '/opt/visal/tmp/for_sijin/Data/H36M/H36MExp/folder_SP_t004_act_14/batches.meta'
meta = mio.unpickle(data_path)
all_pose = meta['feature_list'][0]
ssolver = Solver.get_saved_model(saved_model_path)
stat = ssolver['model_state']['stat']
cnt_sample = stat['sample_candidate_counts']
mvc = stat['most_violated_counts']
ntrain = cnt_sample.size
sorted_indexes = sorted(range(ntrain), key=lambda k: mvc[k], reverse=True)
show_num = int(144)
selected_indexes = sorted_indexes[:show_num]
max_show_row = int(16)
n_row = (show_num - 1)// max_show_row + 1
nc = 0
selected_pose = all_pose[:,selected_indexes]
limbs = h36m.part_idx
fig = pl.figure()
params = {'elev':-89, 'azim':-107, 'linewidth':3}
selected_cnt = mvc[selected_indexes]
print n_row, max_show_row
for r in range(n_row):
for c in range(max_show_row):
if nc == show_num:
break
p = selected_pose[...,nc].reshape((3,17),order='F').T
nc = nc + 1
# pl.subplot(n_row, max_show_row, c)
ax = fig.add_subplot(n_row, max_show_row, nc, projection='3d')
imgproc.turn_off_axis()
dutils.show_3d_skeleton(p, limbs, params)
pl.title('mvc={}'.format(selected_cnt[nc-1]))
pl.show()
def show_the_most_violated_poses():
from mpl_toolkits.mplot3d import Axes3D
import imgproc
saved_model_path = '/public/sijinli2/ibuffer/2015-01-16/net2_test_for_stat'
saved_model_path = '/opt/visal/tmp/for_sijin/Data/saved/theano_models/FCJ0_act_14_graph_0029_test_norm_cumulate_update'
data_path = '/opt/visal/tmp/for_sijin/Data/H36M/H36MExp/folder_SP_t004_act_14/batches.meta'
meta = mio.unpickle(data_path)
all_pose = meta['feature_list'][0]
ssolver = Solver.get_saved_model(saved_model_path)
stat = ssolver['model_state']['stat']
cnt_sample = stat['sample_candidate_counts']
mvc = stat['most_violated_counts']
ntrain = cnt_sample.size
sorted_indexes = sorted(range(ntrain), key=lambda k: mvc[k], reverse=True)
show_num = int(144)
selected_indexes = sorted_indexes[:show_num]
max_show_row = int(16)
n_row = (show_num - 1) // max_show_row + 1
nc = 0
selected_pose = all_pose[:, selected_indexes]
limbs = h36m.part_idx
fig = pl.figure()
params = {'elev': -89, 'azim': -107, 'linewidth': 3}
selected_cnt = mvc[selected_indexes]
print n_row, max_show_row
for r in range(n_row):
for c in range(max_show_row):
if nc == show_num:
break
p = selected_pose[..., nc].reshape((3, 17), order='F').T
nc = nc + 1
# pl.subplot(n_row, max_show_row, c)
ax = fig.add_subplot(n_row, max_show_row, nc, projection='3d')
imgproc.turn_off_axis()
dutils.show_3d_skeleton(p, limbs, params)
pl.title('mvc={}'.format(selected_cnt[nc - 1]))
pl.show()
def estimate_pose_main_process(self, input_dic, output_dic):
import imgproc
load_next = True
data, raw_img = input_dic['next_data'], input_dic['raw_img']
ndata = data[0].shape[-1]
# output_dic['num_cases'] += [data[0].shape[-1]]
buf = np.require(np.zeros((data[0].shape[-1], input_dic['data_dim']),\
dtype=n.single), \
requirements='C')
data += [buf]
start_t = time()
self.libmodel.startFeatureWriter(data, input_dic['output_layer_idx'])
if load_next:
input_dic['next_data'], input_dic['raw_img'], input_dic['bnd'] = \
self.get_hmlpe_posedata_from_camera(input_dic['camera'], self.test_data_provider)
self.finish_batch()
print '[%.6f seconds]' % (time() - start_t)
if input_dic['target_type'] in input_dic['convert_dic']:
output_dic['est'] = input_dic['convert_dic'][
input_dic['target_type']](buf.T)
else:
output_dic['est'] = buf.T
if not load_next:
return
sys.stdout.flush()
tmp = input_dic['raw_img']
input_dic['camera_im'].set_data(tmp)
input_dic['camera_fig'].canvas.draw()
s = int(np.sqrt(data[0].shape[0]))
if input_dic['target_type'] == 'hmlpe_2d':
img = Image.fromarray(
np.require(input_dic['raw_img'], dtype=np.uint8))
sx, sy = data[0].shape[1], data[0].shape[0]
output_dic['est'] = output_dic['est'].reshape((2, -1, ndata),
order='F')
njoints = output_dic['est'].shape[1]
cur_bnd = input_dic['bnd']
bnd_sx = np.tile(np.asarray([(v[2]+1.0) \
for v in cur_bnd]).reshape((1,ndata)),\
(njoints, 1)).reshape((1,njoints,ndata),order='F')
bnd_sy = np.tile(np.asarray([(v[3]+1.0) \
for v in cur_bnd]).reshape((1,ndata)),\
(njoints, 1)).reshape((1,njoints,ndata),order='F')
bnd_s = np.concatenate((bnd_sx, bnd_sy), axis=0)
bnd_ax = np.tile(np.asarray([v[0] \
for v in cur_bnd]).reshape((1,ndata)),\
(njoints, 1)).reshape((1,njoints,ndata),order='F')
bnd_ay = np.tile(np.asarray([v[1] \
for v in cur_bnd]).reshape((1,ndata)),\
(njoints, 1)).reshape((1,njoints,ndata),order='F')
bnd_a = np.concatenate((bnd_ax, bnd_ay), axis=0)
output_dic['est'] = output_dic['est'] * bnd_s + bnd_a
draw = ImageDraw.Draw(img)
# draw bnd
for b in cur_bnd:
draw.rectangle((b[0], b[1], b[0] + b[2], b[1] + b[3]))
# draw center rectangle
hx, hy = img.size
draw.rectangle((hx / 2 - hy / 2, 0, hx / 2 + hy / 2, hy),
outline=(255, 0, 0))
self.draw2d_skelenton(output_dic['est'], hmlpe.part_idx, draw)
input_dic['pose_ax'].set_data(np.asarray(img))
input_dic['pose_fig'].canvas.draw()
else:
## Plot pose
input_dic['pose_ax'].cla()
#input_dic['pose_ax'].view_init(azim=-92, elev=-46)
vlim = 0.4
input_dic['pose_ax'].set_xlim([-vlim, vlim])
input_dic['pose_ax'].set_ylim([-vlim, vlim])
input_dic['pose_ax'].set_zlim([-vlim, vlim])
self.plot_skelenton(output_dic['est'], h36m.part_idx,
input_dic['pose_ax'])
imgproc.turn_off_axis(input_dic['pose_ax'])
input_dic['pose_fig'].canvas.draw()
if 'outputdir' in input_dic:
outputdir = input_dic['outputdir']
savecnt = input_dic['savecnt']
print outputdir
for i in range(2):
plt.figure(i)
plt.savefig(
iu.fullfile(outputdir, 'fig_%02d_%06d.jpg' % (i, savecnt)))
input_dic['savecnt'] = savecnt + 1
return input_dic['camera_im'], input_dic['pose_ax']
def estimate_pose_main_process(self, input_dic, output_dic):
import imgproc
load_next = True
data, raw_img = input_dic['next_data'], input_dic['raw_img']
ndata = data[0].shape[-1]
# output_dic['num_cases'] += [data[0].shape[-1]]
buf = np.require(np.zeros((data[0].shape[-1], input_dic['data_dim']),\
dtype=n.single), \
requirements='C')
data += [buf]
start_t = time()
self.libmodel.startFeatureWriter(data, input_dic['output_layer_idx'])
if load_next:
input_dic['next_data'], input_dic['raw_img'], input_dic['bnd'] = \
self.get_hmlpe_posedata_from_camera(input_dic['camera'], self.test_data_provider)
self.finish_batch()
print '[%.6f seconds]' % (time() - start_t)
if input_dic['target_type'] in input_dic['convert_dic']:
output_dic['est'] = input_dic['convert_dic'][input_dic['target_type']](buf.T)
else:
output_dic['est'] = buf.T
if not load_next:
return
sys.stdout.flush()
tmp = input_dic['raw_img']
input_dic['camera_im'].set_data(tmp)
input_dic['camera_fig'].canvas.draw()
s = int(np.sqrt(data[0].shape[0]))
if input_dic['target_type'] == 'hmlpe_2d':
img = Image.fromarray(np.require(input_dic['raw_img'],dtype=np.uint8))
sx,sy = data[0].shape[1], data[0].shape[0]
output_dic['est'] = output_dic['est'].reshape((2,-1,ndata), order='F')
njoints = output_dic['est'].shape[1]
cur_bnd = input_dic['bnd']
bnd_sx = np.tile(np.asarray([(v[2]+1.0) \
for v in cur_bnd]).reshape((1,ndata)),\
(njoints, 1)).reshape((1,njoints,ndata),order='F')
bnd_sy = np.tile(np.asarray([(v[3]+1.0) \
for v in cur_bnd]).reshape((1,ndata)),\
(njoints, 1)).reshape((1,njoints,ndata),order='F')
bnd_s = np.concatenate((bnd_sx,bnd_sy),axis=0)
bnd_ax = np.tile(np.asarray([v[0] \
for v in cur_bnd]).reshape((1,ndata)),\
(njoints, 1)).reshape((1,njoints,ndata),order='F')
bnd_ay = np.tile(np.asarray([v[1] \
for v in cur_bnd]).reshape((1,ndata)),\
(njoints, 1)).reshape((1,njoints,ndata),order='F')
bnd_a = np.concatenate((bnd_ax,bnd_ay),axis=0)
output_dic['est'] = output_dic['est'] * bnd_s + bnd_a
draw = ImageDraw.Draw(img)
# draw bnd
for b in cur_bnd:
draw.rectangle((b[0],b[1],b[0]+b[2],b[1]+b[3]))
# draw center rectangle
hx,hy = img.size
draw.rectangle((hx/2 - hy/2,0, hx/2+hy/2, hy ), outline=(255,0,0))
self.draw2d_skelenton(output_dic['est'], hmlpe.part_idx, draw)
input_dic['pose_ax'].set_data(np.asarray(img))
input_dic['pose_fig'].canvas.draw()
else:
## Plot pose
input_dic['pose_ax'].cla()
#input_dic['pose_ax'].view_init(azim=-92, elev=-46)
vlim = 0.4
input_dic['pose_ax'].set_xlim([-vlim,vlim])
input_dic['pose_ax'].set_ylim([-vlim,vlim])
input_dic['pose_ax'].set_zlim([-vlim,vlim])
self.plot_skelenton(output_dic['est'], h36m.part_idx, input_dic['pose_ax'])
imgproc.turn_off_axis(input_dic['pose_ax'])
input_dic['pose_fig'].canvas.draw()
if 'outputdir' in input_dic:
outputdir = input_dic['outputdir']
savecnt = input_dic['savecnt']
print outputdir
for i in range(2):
plt.figure(i)
plt.savefig(iu.fullfile(outputdir, 'fig_%02d_%06d.jpg' % (i,savecnt)))
input_dic['savecnt'] = savecnt + 1
return input_dic['camera_im'], input_dic['pose_ax']
