kernel-elastic-autoencoder 3.3.3__tar.gz → 3.3.5__tar.gz

{kernel_elastic_autoencoder-3.3.3 → kernel_elastic_autoencoder-3.3.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kernel_elastic_autoencoder
-Version: 3.3.3
+Version: 3.3.5
 Summary: Implementation of Kernel-Elastic Autoencoder for Molecular Design (https://doi.org/10.1093/pnasnexus/pgae168)
 License: MIT
 Author: Felix Rotter-McCartney

{kernel_elastic_autoencoder-3.3.3 → kernel_elastic_autoencoder-3.3.5}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "kernel_elastic_autoencoder"
-version = "3.3.3"
+version = "3.3.5"
 description = "Implementation of Kernel-Elastic Autoencoder for Molecular Design (https://doi.org/10.1093/pnasnexus/pgae168)"
 authors = [
     { name = "Felix Rotter-McCartney", email = "felix.rotter@mail.utoronto.ca" }

{kernel_elastic_autoencoder-3.3.3 → kernel_elastic_autoencoder-3.3.5}/src/kernel_elastic_autoencoder/config.py

@@ -58,7 +58,7 @@ class ModelInputConfig(Config):
         description="Vocabulary size of tokenizer. Should be fetched with Tokenizer.vocab_size as specified in the "
         "Tokenizer Protocol.",
     )
-    condition_channels: PositiveInt = Field(
+    condition_channels: NonNegativeInt = Field(
         default=2,
         description="Number of condition channels, should correspond to number of numerical columns in your "
         "dataset/inputs.",

{kernel_elastic_autoencoder-3.3.3 → kernel_elastic_autoencoder-3.3.5}/src/kernel_elastic_autoencoder/model.py

@@ -116,7 +116,7 @@ class Model(
             condition_embeddings,
             padding_mask[:, : self.config_typed.input.max_len - 1],
         )
-        return prediction, prediction_noise, latents_noise
+        return prediction, prediction_noise, latents
 
     def encode(
         self,

{kernel_elastic_autoencoder-3.3.3 → kernel_elastic_autoencoder-3.3.5}/src/kernel_elastic_autoencoder/training.py

@@ -128,11 +128,11 @@ class Trainer:
                 dataloader_train, desc=f"Epoch {epoch}, Train Batch"
             ):
                 optimizer.zero_grad()
-                prediction, prediction_noise, latents_noise = model(
+                prediction, prediction_noise, latents = model(
                     input_ids, conditions, token_mask, condition_mask
                 )
                 loss = loss_fn(
-                    prediction, prediction_noise, input_ids[:, 1:], latents_noise
+                    prediction, prediction_noise, input_ids[:, 1:], latents
                 )
                 accelerator.backward(loss)
                 optimizer.step()
@@ -145,14 +145,14 @@ class Trainer:
                 dataloader_test, desc=f"Epoch {epoch}, Test Batch"
             ):
                 with torch.no_grad():
-                    prediction, prediction_noise, latents_noise = model(
+                    prediction, prediction_noise, latents = model(
                         input_ids,
                         conditions,
                         token_mask,
                         condition_mask,
                     )
                     loss = loss_fn(
-                        prediction, prediction_noise, input_ids[:, 1:], latents_noise
+                        prediction, prediction_noise, input_ids[:, 1:], latents
                     )
                     test_loss = torch.cat([test_loss, loss.detach().unsqueeze(-1)], dim=0)
             accelerator.print(f"Avg. test loss: {test_loss.mean().item()}")