def train_all_tanhgru(seed=0, model_dir='tanhgru'):
"""Training of all tasks with Tanh GRUs."""
model_dir = os.path.join(DATAPATH, model_dir, str(seed))
hp = {'activation': 'tanh', 'rnn_type': 'LeakyGRU'}
rule_prob_map = {'contextdm1': 5, 'contextdm2': 5}
train.train(model_dir,
hp=hp,
ruleset='all',
rule_prob_map=rule_prob_map,
seed=seed)
# Analyses
variance.compute_variance(model_dir)
log = tools.load_log(model_dir)
analysis = clustering.Analysis(model_dir, 'rule')
log['n_cluster'] = analysis.n_cluster
tools.save_log(log)
data_analysis.compute_var_all(model_dir)
setups = [1, 2, 3]
for setup in setups:
taskset.compute_taskspace(model_dir,
setup,
restore=False,
representation='rate')
taskset.compute_replacerule_performance(model_dir, setup, False)
def mante_tanh(seed=0, model_dir='mante_tanh'):
"""Training of only the Mante task."""
hp = {'activation': 'tanh', 'target_perf': 0.9}
model_dir = os.path.join(DATAPATH, model_dir, str(seed))
train.train(model_dir, hp=hp, ruleset='mante', seed=seed)
# Analyses
variance.compute_variance(model_dir)
log = tools.load_log(model_dir)
analysis = clustering.Analysis(model_dir, 'rule')
log['n_cluster'] = analysis.n_cluster
tools.save_log(log)
data_analysis.compute_var_all(model_dir)
def train_vary_hp(i):
"""Vary the hyperparameters.
This experiment loops over a set of hyperparameters.
Args:
i: int, the index of the hyperparameters list
"""
# Ranges of hyperparameters to loop over
hp_ranges = OrderedDict()
# hp_ranges['activation'] = ['softplus', 'relu', 'tanh', 'retanh']
# hp_ranges['rnn_type'] = ['LeakyRNN', 'LeakyGRU']
# hp_ranges['w_rec_init'] = ['diag', 'randortho']
hp_ranges['activation'] = ['softplus']
hp_ranges['rnn_type'] = ['LeakyRNN']
hp_ranges['w_rec_init'] = ['randortho']
hp_ranges['l1_h'] = [0, 1e-9, 1e-8, 1e-7,
1e-6] # TODO(gryang): Change this?
hp_ranges['l2_h'] = [0]
hp_ranges['l1_weight'] = [0, 1e-7, 1e-6, 1e-5]
# TODO(gryang): add the level of overtraining
# Unravel the input index
keys = hp_ranges.keys()
dims = [len(hp_ranges[k]) for k in keys]
n_max = np.prod(dims)
indices = np.unravel_index(i % n_max, dims=dims)
# Set up new hyperparameter
hp = dict()
for key, index in zip(keys, indices):
hp[key] = hp_ranges[key][index]
model_dir = os.path.join(DATAPATH, 'varyhp_reg2', str(i))
rule_prob_map = {'contextdm1': 5, 'contextdm2': 5}
train.train(model_dir,
hp,
ruleset='all',
rule_prob_map=rule_prob_map,
seed=i // n_max)
# Analyses
variance.compute_variance(model_dir)
log = tools.load_log(model_dir)
analysis = clustering.Analysis(model_dir, 'rule')
log['n_cluster'] = analysis.n_cluster
tools.save_log(log)
data_analysis.compute_var_all(model_dir)
def train_all_analysis(seed=0, root_dir='train_all'):
model_dir = os.path.join(DATAPATH, root_dir, str(seed))
# Analyses
variance.compute_variance(model_dir)
variance.compute_variance(model_dir, random_rotation=True)
log = tools.load_log(model_dir)
analysis = clustering.Analysis(model_dir, 'rule')
log['n_cluster'] = analysis.n_cluster
tools.save_log(log)
data_analysis.compute_var_all(model_dir)
for rule in ['dm1', 'contextdm1', 'multidm']:
performance.compute_choicefamily_varytime(model_dir, rule)
setups = [1, 2, 3]
for setup in setups:
taskset.compute_taskspace(model_dir,
setup,
restore=False,
representation='rate')
taskset.compute_replacerule_performance(model_dir, setup, False)
def _base_vary_hp_mante(i, hp_ranges, base_name):
"""Vary hyperparameters for mante tasks."""
# Unravel the input index
keys = hp_ranges.keys()
dims = [len(hp_ranges[k]) for k in keys]
n_max = np.prod(dims)
indices = np.unravel_index(i % n_max, dims=dims)
# Set up new hyperparameter
hp = dict()
for key, index in zip(keys, indices):
hp[key] = hp_ranges[key][index]
model_dir = os.path.join(DATAPATH, base_name, str(i))
train.train(model_dir, hp, ruleset='mante', max_steps=1e7, seed=i // n_max)
# Analyses
variance.compute_variance(model_dir)
log = tools.load_log(model_dir)
analysis = clustering.Analysis(model_dir, 'rule')
log['n_cluster'] = analysis.n_cluster
tools.save_log(log)
data_analysis.compute_var_all(model_dir)
