from datascience.data.loader import occurrence_loader
from datascience.data.datasets import EnvironmentalDataset
from datascience.ml.light_gbm import fit
from datascience.ml.metrics import ValidationAccuracy
train, val, test = occurrence_loader(EnvironmentalDataset, source='glc18', limit=100, size_patch=1)
fit(train, test, val, validation_params={'metrics': (ValidationAccuracy(),)})
from datascience.data.datasets import EnvironmentalDataset
from datascience.ml.neural.supervised import fit
model_params = {
'n_labels': 6823,
'n_input': 77,
'exp': True, # poisson loss,
'normalize_weight': 2. # poisson loss
}
model = load_create_nn(model_class=InceptionEnv, model_params=model_params)
# loading dataset
train, val, test = occurrence_loader(
EnvironmentalDataset,
source='glc18',
id_name='patch_id',
label_name='species_glc_id',
limit=1000
)
training_params['loss'] = CategoricalPoissonLoss()
training_params['log_modulo'] = 1
training_params['iterations'] = [10]
training_params['lr'] = 0.01
validation_params['metrics'] = (ValidationAccuracy(1),) # let us just analyse convergence first
fit(model, train=train, val=val, test=test, training_params=training_params, validation_params=validation_params)
train, val, test, _ = generator.country_dataset_one_fold(
painter_val=painter_val, painter_test=painter_test)
model = create_model(model_class=initialize_model,
model_params=model_params)
mmodel = model.module if type(model) is torch.nn.DataParallel else model
mmodel.aux_logits = False
training_params = {
'iterations': [100, 130, 150, 160],
'batch_size': 256,
}
optim_params = {'lr': 0.001}
validation_params = {'metrics': (ValidationAccuracy(1), )}
model_selection_params = {'cross_validation': True, 'min_epochs': 50}
stats = fit(model,
train=train,
val=val,
test=test,
training_params=training_params,
validation_params=validation_params,
optim_params=optim_params,
model_selection_params=model_selection_params)
score = stats.final_metric().metric_score()
score = score if test[0][1] == 1. else 1. - score
# write the score in a csv
'im_shape': train[0][0].shape,
'conv_layers': (64,), # (150, 150),
'linear_layers': tuple(), # (128, 128),
'pooling': torch.nn.AvgPool2d,
'conv_size': 3
}
model = create_model(model_class=CustomizableCNN, model_params=model_params)
training_params = {
'iterations': [120], # iterations with learning rate decay
'log_modulo': -1, # print loss once per epoch
'val_modulo': 1, # run a validation on the validation set every 5 epochs
'batch_size': 512
}
optim_params = {
'lr': 0.01,
'momentum': 0.0
}
validation_params = {
'metrics': (ValidationAccuracy(1),),
'vcallback': (FilterVarianceCallback(averaged=False, window_size=10),) # (AlignmentMetricCallback(),NewStatCallback(train),)
}
fit(
model, train, test, training_params=training_params, validation_params=validation_params, optim_params=optim_params
)