def __init__(self, test_id, data_dir, provider, checkpoint_dir, train_range, test_range, test_freq,
save_freq, batch_size, num_epoch, image_size, image_color, learning_rate, params):
self.origin_test_range = test_range
if len(test_range) != 1:
test_range = [test_range[0]]
AutoStopTrainer.__init__(self, test_id, data_dir, provider, checkpoint_dir, train_range, test_range, test_freq,
save_freq, batch_size, num_epoch, image_size, image_color, learning_rate, False)
self.conv_params = []
self.fc_params = []
self.softmax_param = None
self.params = params
conv = True
for ld in self.params:
if ld['type'] in ['conv', 'rnorm', 'pool', 'neuron'] and conv:
self.conv_params.append(ld)
elif ld['type'] == 'fc' or (not conv and ld['type'] == 'neuron'):
self.fc_params.append(ld)
conv = False
else:
self.softmax_param = ld
self.conv_stack = FastNet.split_conv_to_stack(self.conv_params)
self.fc_stack = FastNet.split_fc_to_stack(self.fc_params)
pprint.pprint(self.conv_stack)
pprint.pprint(self.fc_stack)
self.fakefc_param = self.fc_stack[-1][0]
def _finish_init(self):
self.curr_model = []
self.complete_model = self.init_model
self.fc_params = []
self.conv_params = []
self.final_num_epoch = self.num_epoch
conv = True
for ld in self.init_model:
if ld['type'] in ['conv', 'rnorm', 'pool', 'neuron'] and conv:
#self.conv_params.append(ld)
self.curr_model.append(ld)
elif ld['type'] == 'fc' or (not conv and ld['type'] == 'neuron'):
self.fc_params.append(ld)
conv = False
else:
self.softmax_param = ld
#self.conv_stack = FastNet.split_conv_to_stack(self.conv_params)
#for i in range(3):
# self.curr_model.extend(self.conv_stack[i])
self.fc_stack = FastNet.split_fc_to_stack(self.fc_params)
#tmp = self.conv_stack[3:]
#tmp.extend(self.fc_stack)
#self.stack = tmp
self.stack = self.fc_stack
self.curr_model.append(self.stack[-1][0])
self.curr_model.append(self.softmax_param)
del self.stack[-1]
pprint.pprint(self.stack)
self.layerwised = True
self.num_epoch = 1
self.net = FastNet(self.learning_rate, self.image_shape,
self.curr_model)
def _finish_init(self):
self.curr_model = []
self.complete_model = self.init_model
self.fc_params = []
self.conv_params = []
self.final_num_epoch = self.num_epoch
conv = True
for ld in self.init_model:
if ld['type'] in ['conv', 'rnorm', 'pool', 'neuron'] and conv:
#self.conv_params.append(ld)
self.curr_model.append(ld)
elif ld['type'] == 'fc' or (not conv and ld['type'] == 'neuron'):
self.fc_params.append(ld)
conv = False
else:
self.softmax_param = ld
#self.conv_stack = FastNet.split_conv_to_stack(self.conv_params)
#for i in range(3):
# self.curr_model.extend(self.conv_stack[i])
self.fc_stack = FastNet.split_fc_to_stack(self.fc_params)
#tmp = self.conv_stack[3:]
#tmp.extend(self.fc_stack)
#self.stack = tmp
self.stack = self.fc_stack
self.curr_model.append(self.stack[-1][0])
self.curr_model.append(self.softmax_param)
del self.stack[-1]
pprint.pprint(self.stack)
self.layerwised = True
self.num_epoch = 1
self.net = FastNet(self.learning_rate, self.image_shape, self.curr_model)
