def sample(model, model_path, sample_path, num=100, output_name='gen/gen'):
pred = PredictConfig(session_init=get_model_loader(model_path),
model=model,
input_names=['z'],
output_names=[output_name, 'z'])
batch_size = 100
#print range(num/batch_size)
#pdb.set_trace()
for i in range(1):
pred = SimpleDatasetPredictor(pred, RandomZData(
(batch_size, opt.Z_DIM)))
n = 0
for o in pred.get_result():
#pdb.set_trace()
o, zs = o[0] + 1, o[1]
o = o * 128.0
o = np.clip(o, 0, 255)
o = o[:, :, :, ::-1]
#viz = stack_patches(o, nr_row=10, nr_col=10, viz=True)
#
for j in range(batch_size):
n = n + 1
pdb.set_trace()
img = o[j]
img = np.dot(img[..., :3], [0.299, 0.587, 0.114])
print img.shape
scipy.misc.imsave('%s%09d.jpeg' % (sample_path, n), img)
print n
if n >= num:
break
def sample(model_path):
pred = PredictConfig(session_init=get_model_loader(model_path),
model=Model(),
input_names=['z'],
output_names=['gen/gen', 'z'])
pred = SimpleDatasetPredictor(pred, RandomZData((100, 100)))
for o in pred.get_result():
o, zs = o[0] + 1, o[1]
o = o * 128.0
o = o[:, :, :, ::-1]
viz = stack_patches(o, nr_row=10, nr_col=10, viz=True)
def sample(model, model_path, output_name='gen/gen'):
pred = PredictConfig(session_init=get_model_loader(model_path),
model=model,
input_names=['z'],
output_names=[output_name, 'z'])
pred = SimpleDatasetPredictor(pred, RandomZData((100, args.z_dim)))
for o in pred.get_result():
o = o[0] + 1
o = o * 128.0
o = np.clip(o, 0, 255)
o = o[:, :, :, ::-1]
stack_patches(o, nr_row=10, nr_col=10, viz=True)
def sample(model_path):
pred = PredictConfig(session_init=get_model_loader(model_path),
model=Model(),
input_names=['label', 'z'],
output_names=['gen/gen'])
ds = MapData(RandomZData((100, 100)),
lambda dp: [np.arange(100) % 10, dp[0]])
pred = SimpleDatasetPredictor(pred, ds)
for o in pred.get_result():
o = o[0] * 255.0
viz = stack_patches(o, nr_row=10, nr_col=10)
viz = cv2.resize(viz, (800, 800))
interactive_imshow(viz)
def sample(model, model_path, output_name='gen/gen'):
pred = PredictConfig(session_init=SmartInit(model_path),
model=model,
input_names=['z'],
output_names=[output_name, 'z'])
pred = SimpleDatasetPredictor(pred, RandomZData((100, args.z_dim)))
i = 0
for o in pred.get_result():
o = o[0] + 1
o = o * 128.0
o = np.clip(o, 0, 255)
o = o[:, :, :, ::-1]
imageio.imwrite("output/" + str(i) + ".png", o[i])
i += 1
def sample(n, model, model_path, output_name='gen/gen', output_filename=None):
pred = PredictConfig(
session_init=get_model_loader(model_path),
model=model,
input_names=['z'],
output_names=[output_name, 'z'])
pred = SimpleDatasetPredictor(
pred, RandomZData((opt.batch_size, opt.z_dim)))
max_iters = n // opt.batch_size
if output_filename is None:
output_filename = opt.exp_name if opt.exp_name else 'generate'
timestamp = datetime.now().strftime('%m%d_%H%M%S')
output_filename += '_{}'.format(timestamp)
results = []
for idx, o in enumerate(pred.get_result()):
results.append(o[0])
if idx + 1 == max_iters:
break
results = np.concatenate(results, axis=0)
ptr = 0
features = {}
for col_id, col_info in enumerate(opt.DATA_INFO['details']):
if col_info['type'] == 'category':
features['f%02d' % col_id] = results[:, ptr:ptr+1]
ptr += 1
elif col_info['type'] == 'value':
gaussian_components = col_info['n']
val = results[:, ptr:ptr+1]
ptr += 1
pro = results[:, ptr:ptr+gaussian_components]
ptr += gaussian_components
features['f%02d' % col_id] = np.concatenate([val, pro], axis=1)
else:
assert 0
np.savez(output_filename, info=json.dumps(opt.DATA_INFO), **features)
