mirror of
https://github.com/wassname/pytorch-lightning.git
synced 2026-09-09 11:32:07 +08:00
proper checkpoint implementation (#1043)
* enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * enabled early stopping/checkpooiunt even without val step * name formatting * version * testing * add test * fix test * Update model_checkpoint.py * doctests * pylint * tests * debug * debug * enabled early stopping/checkpooiunt even without val step * fix MNIST download (#1044) * fix MNIST download * simple * name formatting * version * testing * add test * fix test * doctests * tests * debug * debug * rebased 1041 * rebased 1041 * tests * rebased 1041 * rebased 1041 * rebased 1041 * rebased 1041 * rebased 1041 * rebased 1041 * rebased 1041 * rebased 1041 * rebased 1041 * rebased 1041 * rebased 1041 * rebased 1041 * rebased 1041 Co-authored-by: Jirka Borovec <Borda@users.noreply.github.com>
This commit is contained in:
William Falcon
co-authored by
Jirka Borovec
Jirka Borovec
parent
165b9fb3f3
commit
bcb45d906d
+27
-50
@@ -256,66 +256,57 @@ def mocked_device_count_0(monkeypatch):
|
||||
monkeypatch.setattr(torch.cuda, 'device_count', device_count)
|
||||
|
||||
|
||||
test_num_gpus_data = [
|
||||
@pytest.mark.gpus_param_tests
|
||||
@pytest.mark.parametrize(["gpus", "expected_num_gpus", "distributed_backend"], [
|
||||
pytest.param(None, 0, None, id="None - expect 0 gpu to use."),
|
||||
pytest.param(0, 0, None, id="Oth gpu, expect 1 gpu to use."),
|
||||
pytest.param(1, 1, None, id="1st gpu, expect 1 gpu to use."),
|
||||
pytest.param(-1, PRETEND_N_OF_GPUS, "ddp", id="-1 - use all gpus"),
|
||||
pytest.param('-1', PRETEND_N_OF_GPUS, "ddp", id="'-1' - use all gpus"),
|
||||
pytest.param(3, 3, "ddp", id="3rd gpu - 1 gpu to use (backend:ddp)")
|
||||
]
|
||||
|
||||
|
||||
@pytest.mark.gpus_param_tests
|
||||
@pytest.mark.parametrize(["gpus", "expected_num_gpus", "distributed_backend"], test_num_gpus_data)
|
||||
])
|
||||
def test_trainer_gpu_parse(mocked_device_count, gpus, expected_num_gpus, distributed_backend):
|
||||
assert Trainer(gpus=gpus, distributed_backend=distributed_backend).num_gpus == expected_num_gpus
|
||||
|
||||
|
||||
test_num_gpus_data_0 = [
|
||||
@pytest.mark.gpus_param_tests
|
||||
@pytest.mark.parametrize(["gpus", "expected_num_gpus", "distributed_backend"], [
|
||||
pytest.param(None, 0, None, id="None - expect 0 gpu to use."),
|
||||
pytest.param(None, 0, "ddp", id="None - expect 0 gpu to use."),
|
||||
]
|
||||
|
||||
|
||||
@pytest.mark.gpus_param_tests
|
||||
@pytest.mark.parametrize(["gpus", "expected_num_gpus", "distributed_backend"], test_num_gpus_data_0)
|
||||
])
|
||||
def test_trainer_num_gpu_0(mocked_device_count_0, gpus, expected_num_gpus, distributed_backend):
|
||||
assert Trainer(gpus=gpus, distributed_backend=distributed_backend).num_gpus == expected_num_gpus
|
||||
|
||||
|
||||
test_root_gpu_data = [
|
||||
@pytest.mark.gpus_param_tests
|
||||
@pytest.mark.parametrize(['gpus', 'expected_root_gpu', "distributed_backend"], [
|
||||
pytest.param(None, None, "ddp", id="None is None"),
|
||||
pytest.param(0, None, "ddp", id="O gpus, expect gpu root device to be None."),
|
||||
pytest.param(1, 0, "ddp", id="1 gpu, expect gpu root device to be 0."),
|
||||
pytest.param(-1, 0, "ddp", id="-1 - use all gpus, expect gpu root device to be 0."),
|
||||
pytest.param('-1', 0, "ddp", id="'-1' - use all gpus, expect gpu root device to be 0."),
|
||||
pytest.param(3, 0, "ddp", id="3 gpus, expect gpu root device to be 0.(backend:ddp)")]
|
||||
|
||||
|
||||
@pytest.mark.gpus_param_tests
|
||||
@pytest.mark.parametrize(['gpus', 'expected_root_gpu', "distributed_backend"], test_root_gpu_data)
|
||||
pytest.param(3, 0, "ddp", id="3 gpus, expect gpu root device to be 0.(backend:ddp)")
|
||||
])
|
||||
def test_root_gpu_property(mocked_device_count, gpus, expected_root_gpu, distributed_backend):
|
||||
assert Trainer(gpus=gpus, distributed_backend=distributed_backend).root_gpu == expected_root_gpu
|
||||
|
||||
|
||||
test_root_gpu_data_for_0_devices_passing = [
|
||||
@pytest.mark.gpus_param_tests
|
||||
@pytest.mark.parametrize([
|
||||
'gpus', 'expected_root_gpu', "distributed_backend"], [
|
||||
pytest.param(None, None, None, id="None is None"),
|
||||
pytest.param(None, None, "ddp", id="None is None"),
|
||||
pytest.param(0, None, "ddp", id="None is None"),
|
||||
]
|
||||
|
||||
|
||||
@pytest.mark.gpus_param_tests
|
||||
@pytest.mark.parametrize([
|
||||
'gpus', 'expected_root_gpu', "distributed_backend"], test_root_gpu_data_for_0_devices_passing)
|
||||
])
|
||||
def test_root_gpu_property_0_passing(
|
||||
mocked_device_count_0, gpus, expected_root_gpu, distributed_backend):
|
||||
assert Trainer(gpus=gpus, distributed_backend=distributed_backend).root_gpu == expected_root_gpu
|
||||
|
||||
|
||||
# Asking for a gpu when non are available will result in a MisconfigurationException
|
||||
test_root_gpu_data_for_0_devices_raising = [
|
||||
@pytest.mark.gpus_param_tests
|
||||
@pytest.mark.parametrize([
|
||||
'gpus', 'expected_root_gpu', "distributed_backend"], [
|
||||
pytest.param(1, None, "ddp"),
|
||||
pytest.param(3, None, "ddp"),
|
||||
pytest.param(3, None, "ddp"),
|
||||
@@ -323,34 +314,27 @@ test_root_gpu_data_for_0_devices_raising = [
|
||||
pytest.param([0, 1], None, "ddp"),
|
||||
pytest.param(-1, None, "ddp"),
|
||||
pytest.param('-1', None, "ddp")
|
||||
]
|
||||
|
||||
|
||||
@pytest.mark.gpus_param_tests
|
||||
@pytest.mark.parametrize([
|
||||
'gpus', 'expected_root_gpu', "distributed_backend"], test_root_gpu_data_for_0_devices_raising)
|
||||
])
|
||||
def test_root_gpu_property_0_raising(
|
||||
mocked_device_count_0, gpus, expected_root_gpu, distributed_backend):
|
||||
with pytest.raises(MisconfigurationException):
|
||||
Trainer(gpus=gpus, distributed_backend=distributed_backend).root_gpu
|
||||
|
||||
|
||||
test_determine_root_gpu_device_data = [
|
||||
@pytest.mark.gpus_param_tests
|
||||
@pytest.mark.parametrize(['gpus', 'expected_root_gpu'], [
|
||||
pytest.param(None, None, id="No gpus, expect gpu root device to be None"),
|
||||
pytest.param([0], 0, id="Oth gpu, expect gpu root device to be 0."),
|
||||
pytest.param([1], 1, id="1st gpu, expect gpu root device to be 1."),
|
||||
pytest.param([3], 3, id="3rd gpu, expect gpu root device to be 3."),
|
||||
pytest.param([1, 2], 1, id="[1, 2] gpus, expect gpu root device to be 1."),
|
||||
]
|
||||
|
||||
|
||||
@pytest.mark.gpus_param_tests
|
||||
@pytest.mark.parametrize(['gpus', 'expected_root_gpu'], test_determine_root_gpu_device_data)
|
||||
])
|
||||
def test_determine_root_gpu_device(gpus, expected_root_gpu):
|
||||
assert determine_root_gpu_device(gpus) == expected_root_gpu
|
||||
|
||||
|
||||
test_parse_gpu_ids_data = [
|
||||
@pytest.mark.gpus_param_tests
|
||||
@pytest.mark.parametrize(['gpus', 'expected_gpu_ids'], [
|
||||
pytest.param(None, None),
|
||||
pytest.param(0, None),
|
||||
pytest.param(1, [0]),
|
||||
@@ -362,16 +346,13 @@ test_parse_gpu_ids_data = [
|
||||
pytest.param('3', [3]),
|
||||
pytest.param('1, 3', [1, 3]),
|
||||
pytest.param('-1', list(range(PRETEND_N_OF_GPUS)), id="'-1' - use all gpus"),
|
||||
]
|
||||
|
||||
|
||||
@pytest.mark.gpus_param_tests
|
||||
@pytest.mark.parametrize(['gpus', 'expected_gpu_ids'], test_parse_gpu_ids_data)
|
||||
])
|
||||
def test_parse_gpu_ids(mocked_device_count, gpus, expected_gpu_ids):
|
||||
assert parse_gpu_ids(gpus) == expected_gpu_ids
|
||||
|
||||
|
||||
test_parse_gpu_invalid_inputs_data = [
|
||||
@pytest.mark.gpus_param_tests
|
||||
@pytest.mark.parametrize(['gpus'], [
|
||||
pytest.param(0.1),
|
||||
pytest.param(-2),
|
||||
pytest.param(False),
|
||||
@@ -380,11 +361,7 @@ test_parse_gpu_invalid_inputs_data = [
|
||||
pytest.param([None]),
|
||||
pytest.param(['0']),
|
||||
pytest.param((0, 1)),
|
||||
]
|
||||
|
||||
|
||||
@pytest.mark.gpus_param_tests
|
||||
@pytest.mark.parametrize(['gpus'], test_parse_gpu_invalid_inputs_data)
|
||||
])
|
||||
def test_parse_gpu_fail_on_unsupported_inputs(mocked_device_count, gpus):
|
||||
with pytest.raises(MisconfigurationException):
|
||||
parse_gpu_ids(gpus)
|
||||
|
||||
Reference in New Issue
Block a user