tests

Author: Sceki

kessler/model.py

@@ -308,14 +308,14 @@ def make_chaser(self):
             mean_anomaly = pyro.sample('c_mean_anomaly', self._prior_dict['mean_anomaly_prior'])
             tle = self._c_tle.copy()
             tle.update({'mean_anomaly': mean_anomaly})
-            pyro.deterministic('c_mean_motion',tle.mean_motion)
-            pyro.deterministic('c_eccentricity',tle.eccentricity)
-            pyro.deterministic('c_inclination',tle.inclination)
-            pyro.deterministic('c_argument_of_perigee',tle.argument_of_perigee)
-            pyro.deterministic('c_raan',tle.raan)
-            pyro.deterministic('c_mean_motion_first_derivative',tle.mean_motion_first_derivative)
-            pyro.deterministic('c_mean_motion_second_derivative',tle.mean_motion_second_derivative)
-            pyro.deterministic('c_b_star',tle.b_star)
+            pyro.deterministic('c_mean_motion',torch.tensor(tle.mean_motion))
+            pyro.deterministic('c_eccentricity',torch.tensor(tle.eccentricity))
+            pyro.deterministic('c_inclination',torch.tensor(tle.inclination))
+            pyro.deterministic('c_argument_of_perigee',torch.tensor(tle.argument_of_perigee))
+            pyro.deterministic('c_raan',torch.tensor(tle.raan))
+            pyro.deterministic('c_mean_motion_first_derivative',torch.tensor(tle.mean_motion_first_derivative))
+            pyro.deterministic('c_mean_motion_second_derivative',torch.tensor(tle.mean_motion_second_derivative))
+            pyro.deterministic('c_b_star',torch.tensor(tle.b_star))
             return tle
 
     def generate_cdm(self, 

tests/test_util.py

@@ -139,11 +139,11 @@ def test_TruncatedNormal(self):
         max=0.68639
 
         categorical=Categorical(probs=probs)
-        batched_truncated_normal = kessler.util.TruncatedNormal(loc=locs, scale=scales, min=min, max=max)
+        batched_truncated_normal = kessler.util.TruncatedNormal(loc=locs, scale=scales, low=min, high=max)
         mix_truncated=MixtureSameFamily(categorical, batched_truncated_normal)
-        self.assertAlmostEqual(mix_truncated.log_prob(torch.tensor(0.0001)).item(), 7.382209300994873, places=8)
-        self.assertAlmostEqual(mix_truncated.log_prob(torch.tensor(0.001)).item(), 5.485926151275635, places=8)
-        self.assertAlmostEqual(mix_truncated.log_prob(torch.tensor(0.01)).item(), 1.863307237625122, places=8)
-        self.assertAlmostEqual(mix_truncated.log_prob(torch.tensor(0.1)).item(), -2.458112955093384, places=8)
+        self.assertAlmostEqual(mix_truncated.log_prob(torch.tensor(0.0001)).item(), 7.382209300994873, places=6)
+        self.assertAlmostEqual(mix_truncated.log_prob(torch.tensor(0.001)).item(), 5.485926151275635, places=6)
+        self.assertAlmostEqual(mix_truncated.log_prob(torch.tensor(0.01)).item(), 1.863307237625122, places=6)
+        self.assertAlmostEqual(mix_truncated.log_prob(torch.tensor(0.1)).item(), -2.458112955093384, places=6)