iicd/xautodl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add super/norm layers in xcore

Browse Source
This commit is contained in:
D-X-Y
2021-05-06 16:38:58 +08:00
parent ff5e544240
commit 4c14c7b85b
6 changed files with 392 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
tests/test_super_norm.py
View File

@@ -51,3 +51,35 @@ class TestSuperSimpleNorm(unittest.TestCase):
output_shape = (20, abstract_child["1"]["_out_features"].value)
outputs = model(inputs)
self.assertEqual(tuple(outputs.shape), output_shape)
def test_super_simple_learn_norm(self):
out_features = spaces.Categorical(12, 24, 36)
bias = spaces.Categorical(True, False)
model = super_core.SuperSequential(
super_core.SuperSimpleLearnableNorm(),
super_core.SuperIdentity(),
super_core.SuperLinear(10, out_features, bias=bias),
)
print("The simple super module is:\n{:}".format(model))
model.apply_verbose(True)
print(model.super_run_type)
self.assertTrue(model[1].bias)
inputs = torch.rand(20, 10)
print("Input shape: {:}".format(inputs.shape))
outputs = model(inputs)
self.assertEqual(tuple(outputs.shape), (20, 36))
abstract_space = model.abstract_search_space
abstract_space.clean_last()
abstract_child = abstract_space.random()
print("The abstract searc space:\n{:}".format(abstract_space))
print("The abstract child program:\n{:}".format(abstract_child))
model.set_super_run_type(super_core.SuperRunMode.Candidate)
model.apply_candidate(abstract_child)
output_shape = (20, abstract_child["1"]["_out_features"].value)
outputs = model(inputs)
self.assertEqual(tuple(outputs.shape), output_shape)