def setUp(self):
unittest.TestCase.setUp(self)
self.material = Argon()
self.initialize_material()
self.real_xtarget = 3.525
self.reciprocal_xtarget = 1.94
self.fourier_filter_cutoff = 1.5
filename = self.material.reciprocal_space_filename
self.kwargs_for_files = {
'Files': [{
'Filename': get_data_path(filename),
'ReciprocalFunction': 'S(Q)',
'Qmin': 0.02,
'Qmax': 15.0,
'Y': {
'Offset': 0.0,
'Scale': 1.0
},
'X': {
'Offset': 0.0
}
}, {
'Filename':
get_data_path(self.material.reciprocal_space_filename),
'ReciprocalFunction':
'S(Q)',
'Qmin':
1.90,
'Qmax':
35.2,
'Y': {
'Offset': 0.0,
'Scale': 1.0
},
'X': {
'Offset': 0.0
}
}]
}
self.kwargs_for_stog_input = {
'NumberDensity': self.material.kwargs['rho'],
'<b_coh>^2': self.material.kwargs['<b_coh>^2'],
'<b_tot^2>': self.material.kwargs['<b_tot^2>'],
'FourierFilter': {
'Cutoff': self.fourier_filter_cutoff
},
'OmittedXrangeCorrection': False,
'Rdelta': self.r[1] - self.r[0],
'Rmin': min(self.r),
'Rmax': max(self.r)
}
def test_no_val_end_module(tmpdir):
"""Tests use case where trainer saves the model, and user loads it from tags independently."""
tutils.reset_seed()
class CurrentTestModel(LightningValidationStepMixin,
LightningTestModelBase):
pass
hparams = tutils.get_hparams()
model = CurrentTestModel(hparams)
# logger file to get meta
logger = tutils.get_test_tube_logger(tmpdir, False)
trainer_options = dict(max_epochs=1,
logger=logger,
checkpoint_callback=ModelCheckpoint(tmpdir))
# fit model
trainer = Trainer(**trainer_options)
result = trainer.fit(model)
# traning complete
assert result == 1, 'amp + ddp model failed to complete'
# save model
new_weights_path = os.path.join(tmpdir, 'save_test.ckpt')
trainer.save_checkpoint(new_weights_path)
# load new model
tags_path = tutils.get_data_path(logger, path_dir=tmpdir)
tags_path = os.path.join(tags_path, 'meta_tags.csv')
model_2 = LightningTestModel.load_from_metrics(
weights_path=new_weights_path, tags_csv=tags_path)
model_2.eval()
def test_model_saving_loading(tmpdir):
"""Tests use case where trainer saves the model, and user loads it from tags independently."""
tutils.reset_seed()
hparams = tutils.get_hparams()
model = LightningTestModel(hparams)
# logger file to get meta
logger = tutils.get_test_tube_logger(tmpdir, False)
trainer_options = dict(
max_epochs=1,
logger=logger,
checkpoint_callback=ModelCheckpoint(tmpdir)
)
# fit model
trainer = Trainer(**trainer_options)
result = trainer.fit(model)
# traning complete
assert result == 1, 'amp + ddp model failed to complete'
# make a prediction
for dataloader in model.test_dataloader():
for batch in dataloader:
break
x, y = batch
x = x.view(x.size(0), -1)
# generate preds before saving model
model.eval()
pred_before_saving = model(x)
# save model
new_weights_path = os.path.join(tmpdir, 'save_test.ckpt')
trainer.save_checkpoint(new_weights_path)
# load new model
tags_path = tutils.get_data_path(logger, path_dir=tmpdir)
tags_path = os.path.join(tags_path, 'meta_tags.csv')
model_2 = LightningTestModel.load_from_metrics(weights_path=new_weights_path,
tags_csv=tags_path)
model_2.eval()
# make prediction
# assert that both predictions are the same
new_pred = model_2(x)
assert torch.all(torch.eq(pred_before_saving, new_pred)).item() == 1
def test_running_test_pretrained_model_ddp(tmpdir):
"""Verify `test()` on pretrained model."""
if not tutils.can_run_gpu_test():
return
tutils.reset_seed()
tutils.set_random_master_port()
hparams = tutils.get_hparams()
model = LightningTestModel(hparams)
# exp file to get meta
logger = tutils.get_test_tube_logger(tmpdir, False)
# exp file to get weights
checkpoint = tutils.init_checkpoint_callback(logger)
trainer_options = dict(
show_progress_bar=False,
max_epochs=1,
train_percent_check=0.4,
val_percent_check=0.2,
checkpoint_callback=checkpoint,
logger=logger,
gpus=[0, 1],
distributed_backend='ddp'
)
# fit model
trainer = Trainer(**trainer_options)
result = trainer.fit(model)
log.info(os.listdir(tutils.get_data_path(logger, path_dir=tmpdir)))
# correct result and ok accuracy
assert result == 1, 'training failed to complete'
pretrained_model = tutils.load_model(logger,
trainer.checkpoint_callback.filepath,
module_class=LightningTestModel)
# run test set
new_trainer = Trainer(**trainer_options)
new_trainer.test(pretrained_model)
for dataloader in model.test_dataloader():
tutils.run_prediction(dataloader, pretrained_model)
def test_loading_meta_tags(tmpdir):
tutils.reset_seed()
from argparse import Namespace
hparams = tutils.get_hparams()
# save tags
logger = tutils.get_test_tube_logger(tmpdir, False)
logger.log_hyperparams(Namespace(some_str='a_str', an_int=1, a_float=2.0))
logger.log_hyperparams(hparams)
logger.save()
# load tags
path_expt_dir = tutils.get_data_path(logger, path_dir=tmpdir)
tags_path = os.path.join(path_expt_dir, 'meta_tags.csv')
tags = load_hparams_from_tags_csv(tags_path)
assert tags.batch_size == 32 and tags.hidden_dim == 1000
def test_stog_read_dataset(self):
# Number of decimal places for precision
places = 5
# Load S(Q) for Argon from test data
stog = StoG(
**{
'<b_coh>^2': self.kwargs['<b_coh>^2'],
'<b_tot^2>': self.kwargs['<b_tot^2>']
})
info = {
'Filename': get_data_path(self.material.reciprocal_space_filename),
'ReciprocalFunction': 'S(Q)',
'Qmin': 0.02,
'Qmax': 35.2,
'Y': {
'Offset': 0.0,
'Scale': 1.0
},
'X': {
'Offset': 0.0
}
}
info['index'] = 0
stog.read_dataset(info)
# Check S(Q) data against targets
self.assertEqual(stog.df_individuals.iloc[self.first].name,
self.reciprocal_xtarget)
self.assertAlmostEqual(
stog.df_individuals.iloc[self.first]['S(Q)_%d' % info['index']],
self.sq_target[0],
places=places)
self.assertAlmostEqual(
stog.df_sq_individuals.iloc[self.first]['S(Q)_%d' % info['index']],
self.sq_target[0],
places=places)
