print 'loading pretrained CNN...'
feature_network = HumanConvNet(name='Person CNN',
nout=2,
numpy_rng=numpy_rng,
theano_rng=theano_rng,
batchsize=batchsize)
feature_network.load('convnet_eth_inria_data/human_convnet_val_best.h5')
feature_network.mode.set_value(np.uint8(1))
print "instantiating model..."
model = RATM(name='RATM',
imsize=imsize,
patchsize=patchsize,
nhid=nhid,
numpy_rng=numpy_rng,
eps=1e-4,
hids_scale=1.,
feature_network=feature_network,
input_feature_layer_name=input_feature_layer_name,
metric_feature_layer_name=metric_feature_layer_name,
nchannels=1,
weight_decay=weight_decay)
print "done (with instantiating model)"
def visualize(fname):
n = 5
idx = numpy_rng.permutation(len(val_data['inputs']))[:n]
val_vids = val_data['inputs'][idx]
val_bbs = val_data['targets'][idx]
val_masks = val_data['masks'][idx]
print 'loading pretrained CNN...'
feature_network = HumanConvNet(name='Person CNN',
nout=2,
numpy_rng=numpy_rng,
theano_rng=theano_rng,
batchsize=batchsize)
feature_network.load('convnet_eth_inria_data/human_convnet_val_best.h5')
feature_network.mode.set_value(np.uint8(1))
print "instantiating model..."
model = RATM(name='RATM',
imsize=imsize,
patchsize=patchsize,
nhid=nhid,
numpy_rng=numpy_rng,
eps=1e-4,
hids_scale=1.,
feature_network=feature_network,
input_feature_layer_name=input_feature_layer_name,
metric_feature_layer_name=metric_feature_layer_name,
nchannels=1,
weight_decay=weight_decay)
print "done (with instantiating model)"
model.load('attention_model_kth_{0:02d}left_out_val_best.h5'.format(
args.test_person))
def compute_avg_IoU(inputs, targets, masks):
bbs = targets
vids = inputs
max_nframes = np.max(np.where(masks > .5)[1])
persons=[args.test_person], actions=('jogging', 'running', 'walking'))
test_data = test_data_provider.get_batch()
print 'loading pretrained CNN...'
feature_network = HumanConvNet(
name='Person CNN', nout=2, numpy_rng=numpy_rng,
theano_rng=theano_rng, batchsize=batchsize)
feature_network.load('convnet_eth_inria_data/human_convnet_val_best.h5')
feature_network.mode.set_value(np.uint8(1))
print "instantiating model..."
model = RATM(name='RATM', imsize=imsize,
patchsize=patchsize, nhid=nhid,
numpy_rng=numpy_rng, eps=1e-4,
hids_scale=1.,
feature_network=feature_network,
input_feature_layer_name=input_feature_layer_name,
metric_feature_layer_name=metric_feature_layer_name,
nchannels=1,
weight_decay=weight_decay)
print "done (with instantiating model)"
model.load(
'attention_model_kth_{0:02d}left_out_val_best.h5'.format(
args.test_person))
def compute_avg_IoU(inputs, targets, masks):
bbs = targets
vids = inputs
max_nframes = np.max(np.where(masks > .5)[1])
persons=[args.test_person], actions=('jogging', 'running', 'walking'))
test_data = test_data_provider.get_batch()
print 'loading pretrained CNN...'
feature_network = HumanConvNet(
name='Person CNN', nout=2, numpy_rng=numpy_rng,
theano_rng=theano_rng, batchsize=batchsize)
feature_network.load('convnet_eth_inria_data/human_convnet_val_best.h5')
feature_network.mode.set_value(np.uint8(1))
print "instantiating model..."
model = RATM(name='RATM', imsize=imsize,
patchsize=patchsize, nhid=nhid,
numpy_rng=numpy_rng, eps=1e-4,
hids_scale=1.,
feature_network=feature_network,
input_feature_layer_name=input_feature_layer_name,
metric_feature_layer_name=metric_feature_layer_name,
nchannels=1,
weight_decay=weight_decay)
print "done (with instantiating model)"
def visualize(fname):
n = 5
idx = numpy_rng.permutation(len(val_data['inputs']))[:n]
val_vids = val_data['inputs'][idx]
val_bbs = val_data['targets'][idx]
val_masks = val_data['masks'][idx]
val_Xs = (val_bbs[:, :, 1::2] + val_bbs[:, :, ::2]) / 2.
