def incremental_data_experiment(prmlp,
train_datasets,
test_datasets,
no_of_patches=64,
patch_size=(8, 8),
**kwargs):
ds_train = Dataset()
ds_test = Dataset()
costs = []
test_scores = []
test_ds_name = data_dir + test_datasets[0] + file_suffix
print "Loading the test dataset"
ds_test.setup_pretraining_dataset(data_path=test_ds_name,
train_split_scale=0.5, patch_size=patch_size, normalize_inputs=False)
"""
Perform the test on test dataset for each learnt training dataset.
"""
for x_t_idx in xrange(len(train_datasets)):
train_ds_name = data_dir + train_datasets[x_t_idx] + file_suffix
print "Loading the dataset %s " % (train_ds_name)
ds_train.setup_pretraining_dataset(data_path=train_ds_name,
train_split_scale=1, patch_size=patch_size, normalize_inputs=False)
print "Training on the dataset %d " % (x_t_idx)
cost = train_prmlp(prmlp, ds_train.Xtrain_patches, ds_train.Xtrain_presences, **kwargs["train_args"])
costs.append(cost)
print "Testing on the test dataset."
test_scores_per_ds = test_prmlp(prmlp, ds_test.Xtest_patches, ds_test.Xtest_presences, no_of_patches, **kwargs["test_args"])
test_score_patch_based = prmlp.obj_patch_error_percent
test_scores.append(test_score_patch_based)
all_data_dict = {
"test_scores": test_scores,
"costs": costs
}
numpy.save("/RQusagers/gulcehre/codes/python/experiments/arcade_ds_exps/pretrained_mlp/prmlp_multi_datasets/out/multi_hidden_mlp_240k_lrate_0.025_3hidden_8x8_1epoch.npy", all_data_dict)
ds = Dataset()
data_new =\
"/RQexec/gulcehre/datasets/pentomino/pento_64x64_8x8patches/pento64x64_20k_64patches_seed_112168712_64patches.npy"
data_new_40k =\
"/RQexec/gulcehre/datasets/pentomino/pento_64x64_8x8patches/pento64x64_40k_64patches_seed_975168712_64patches.npy"
data_new_60k =\
"/RQexec/gulcehre/datasets/pentomino/pento_64x64_8x8patches/pento64x64_60k_64patches_seed_975168712_64patches.npy"
data_new_100k =\
"/RQexec/gulcehre/datasets/pentomino/pento_64x64_8x8patches/pento64x64_100k_seed_98313722_64patches.npy"
patch_size=(8, 8)
ds.setup_pretraining_dataset(data_path=data_new_60k, patch_size=patch_size, train_split_scale=0.8, normalize_inputs=False)
x = T.matrix('x')
n_hiddens = [2048]
no_of_patches = 64
no_of_classes = 11
prmlp = PatchBasedMLP(x, n_in=patch_size[0] * patch_size[1],
n_hiddens=n_hiddens, n_out=11, no_of_patches=no_of_patches,
output=0, activation=NeuralActivations.Rectifier, use_adagrad=False)
post_mlp = PostMLP(x, n_in=no_of_classes, n_hiddens=[64],
activation=NeuralActivations.Rectifier, n_out=1, use_adagrad=False)
pre_training(patch_mlp=prmlp, post_mlp=post_mlp, ds=ds)
print "starting post-testing on the dataset"
post_mlp.test(data=pre_test_test_probs,
labels=test_set_labels,
**post_cs_args["test_args"])
if __name__ == "__main__":
print "Loading the dataset"
ds = Dataset()
data_path_40k = "/RQusagers/gulcehre/dataset/pentomino/pieces/pento64x64_40k_seed_39112222.npy"
data_path = "/RQusagers/gulcehre/dataset/pentomino/experiment_data/pento64x64_80k_seed_39112222.npy"
patch_size = (8, 8)
ds.setup_pretraining_dataset(data_path=data_path_40k,
patch_size=patch_size,
normalize_inputs=False)
x = T.matrix('x')
n_hiddens = [1024, 768]
no_of_patches = 64
no_of_classes = 11
prmlp = PatchBasedMLP(x,
n_in=patch_size[0] * patch_size[1],
n_hiddens=n_hiddens,
n_out=11,
no_of_patches=no_of_patches,
activation=NeuralActivations.Rectifier,
use_adagrad=False)
def pre_training_on_multi_datasets(patch_mlp=None, post_mlp=None, train_ds=None, test_ds=None):
ds = Dataset()
print "Loading the dataset"
train_set_patches, train_set_pre, train_set_labels = ds.Xtrain_patches, ds.Xtrain_presences, ds.Ytrain
test_set_patches, test_set_pre, test_set_labels = ds.Xtest_patches, ds.Xtest_presences, ds.Ytrain
cs_args = {
"train_args": {
"L1_reg": 1e-6,
"learning_rate": 0.75,
"L2_reg": 1e-5,
"nepochs": 2,
"cost_type": "crossentropy",
"save_exp_data": False,
"batch_size": 250,
"normalize_weights": False,
},
"test_args": {"save_exp_data": False, "batch_size": 250},
}
post_cs_args = {
"train_args": {
"L1_reg": 1e-6,
"learning_rate": 0.08,
"L2_reg": 1e-5,
"nepochs": 10,
"cost_type": "crossentropy",
"save_exp_data": False,
"batch_size": 250,
"normalize_weights": False,
},
"test_args": {"save_exp_data": False, "batch_size": 250},
}
test_dataset = test_ds[0]
ds.setup_pretraining_dataset(data_path=test_dataset, train_split_scale=0.4, patch_size=(8, 8))
test_patches, test_pre, test_labels = ds.Xtest_patches, ds.Xtest_presences, ds.Ytest
for i in xrange(len(train_ds)):
print "Current training dataset is %s \n" % (train_ds[i])
ds.setup_pretraining_dataset(data_path=train_ds[i], train_split_scale=1.0, patch_size=(8, 8))
train_patches, train_pre, train_labels = ds.Xtrain_patches, ds.Xtrain_presences, ds.Ytrain
test_labels = get_binary_labels(test_labels)
train_labels = get_binary_labels(train_labels)
print "Starting the pretraining phase."
(costs, pre_train_probs) = prmlp.train(train_patches, train_pre, **cs_args["train_args"])
prmlp.save_data()
print "Testing on the training dataset."
(costs, pre_test_train_probs) = prmlp.test(train_patches, train_pre, **cs_args["test_args"])
print "Testing on the test dataset."
(costs, pre_test_test_probs) = prmlp.test(test_patches, test_pre, **cs_args["test_args"])
print "Normalizing patch-mlp's outputs"
pre_train_probs = normalize_data(pre_train_probs)
pre_test_train_probs = normalize_data(pre_test_train_probs)
pre_test_test_probs = normalize_data(pre_test_test_probs)
print "Training post-mlp"
post_mlp.train(data=pre_train_probs, labels=train_labels, **post_cs_args["train_args"])
print "starting post-testing on training dataset"
post_mlp.test(data=pre_test_train_probs, labels=train_labels, **post_cs_args["test_args"])
print "starting post-testing on the dataset"
post_mlp.test(data=pre_test_test_probs, labels=test_labels, **post_cs_args["test_args"])
data_new =\
"/RQexec/gulcehre/datasets/pentomino/pento_64x64_8x8patches/pento64x64_20k_64patches_seed_112168712_64patches.npy"
data_new_40k =\
"/RQexec/gulcehre/datasets/pentomino/pento_64x64_8x8patches/pento64x64_40k_64patches_seed_975168712_64patches.npy"
data_new_60k =\
"/RQexec/gulcehre/datasets/pentomino/pento_64x64_8x8patches/pento64x64_60k_64patches_seed_975168712_64patches.npy"
data_new_100k =\
"/RQexec/gulcehre/datasets/pentomino/pento_64x64_8x8patches/pento64x64_100k_seed_98313722_64patches.npy"
patch_size = (8, 8)
ds.setup_pretraining_dataset(data_path=data_new_100k,
patch_size=patch_size,
train_split_scale=0.8,
normalize_inputs=False)
x = T.matrix('x')
n_hiddens = [2048]
no_of_patches = 64
no_of_classes = 11
prmlp = PatchBasedMLP(x,
n_in=patch_size[0] * patch_size[1],
n_hiddens=n_hiddens,
n_out=11,
no_of_patches=no_of_patches,
activation=NeuralActivations.Rectifier,
use_adagrad=False)
print "starting post-testing on the dataset"
test_error = csvm.test(pre_test_test_probs, test_set_labels, **post_cs_args["test_args"])
print "For testing %s" %(test_error)
# import ipdb; ipdb.set_trace()
if __name__=="__main__":
print "Task has just started."
print "Loading the dataset"
ds = Dataset()
patch_size=(8,8)
ds_path = \
"/RQusagers/gulcehre/dataset/pentomino/experiment_data/pento64x64_80k_seed_39112222.npy"
data_new =\
"/RQusagers/gulcehre/dataset/pentomino/rnd_pieces/pento64x64_5k_seed_43112222_64patches_rnd.npy"
data_new_40k =\
"/RQexec/gulcehre/datasets/pentomino/pento_64x64_8x8patches/pento64x64_40k_64patches_seed_975168712_64patches.npy"
ds.setup_pretraining_dataset(data_path=data_new_40k, patch_size=patch_size, normalize_inputs=False)
pre_input = T.matrix('pre_input')
n_hiddens = [2048]
prmlp = PatchBasedMLP(pre_input, n_in=8*8, n_hiddens=n_hiddens, n_out=11,
no_of_patches=64, activation=NeuralActivations.Rectifier, use_adagrad=False)
csvm = CSVM()
pre_training(prmlp, csvm, ds)
def pre_training_on_multi_datasets(patch_mlp=None,
post_mlp=None,
train_ds=None,
test_ds=None):
ds = Dataset()
print "Loading the dataset"
train_set_patches, train_set_pre, train_set_labels =\
ds.Xtrain_patches, ds.Xtrain_presences, ds.Ytrain
test_set_patches, test_set_pre, test_set_labels = ds.Xtest_patches, ds.Xtest_presences, ds.Ytrain
cs_args = {
"train_args": {
"L1_reg": 1e-6,
"learning_rate": 0.75,
"L2_reg": 1e-5,
"nepochs": 2,
"cost_type": "crossentropy",
"save_exp_data": False,
"batch_size": 250,
"normalize_weights": False
},
"test_args": {
"save_exp_data": False,
"batch_size": 250
}
}
post_cs_args = {
"train_args": {
"L1_reg": 1e-6,
"learning_rate": 0.08,
"L2_reg": 1e-5,
"nepochs": 10,
"cost_type": "crossentropy",
"save_exp_data": False,
"batch_size": 250,
"normalize_weights": False
},
"test_args": {
"save_exp_data": False,
"batch_size": 250
}
}
test_dataset = test_ds[0]
ds.setup_pretraining_dataset(data_path=test_dataset,
train_split_scale=0.4,
patch_size=(8, 8))
test_patches, test_pre, test_labels = ds.Xtest_patches, ds.Xtest_presences, ds.Ytest
for i in xrange(len(train_ds)):
print "Current training dataset is %s \n" % (train_ds[i])
ds.setup_pretraining_dataset(data_path=train_ds[i],
train_split_scale=1.0,
patch_size=(8, 8))
train_patches, train_pre, train_labels = ds.Xtrain_patches, ds.Xtrain_presences, ds.Ytrain
test_labels = get_binary_labels(test_labels)
train_labels = get_binary_labels(train_labels)
print "Starting the pretraining phase."
(costs, pre_train_probs) = prmlp.train(train_patches, train_pre,
**cs_args["train_args"])
prmlp.save_data()
print "Testing on the training dataset."
(costs, pre_test_train_probs) = prmlp.test(train_patches, train_pre,
**cs_args["test_args"])
print "Testing on the test dataset."
(costs, pre_test_test_probs) = prmlp.test(test_patches, test_pre,
**cs_args["test_args"])
print "Normalizing patch-mlp's outputs"
pre_train_probs = normalize_data(pre_train_probs)
pre_test_train_probs = normalize_data(pre_test_train_probs)
pre_test_test_probs = normalize_data(pre_test_test_probs)
print "Training post-mlp"
post_mlp.train(data=pre_train_probs,
labels=train_labels,
**post_cs_args["train_args"])
print "starting post-testing on training dataset"
post_mlp.test(data=pre_test_train_probs,
labels=train_labels,
**post_cs_args["test_args"])
print "starting post-testing on the dataset"
post_mlp.test(data=pre_test_test_probs,
labels=test_labels,
**post_cs_args["test_args"])