cleanup some unused imports

labml_nn/cfr/kuhn/__init__.py

@@ -41,7 +41,6 @@ import numpy as np
 from labml import experiment
 from labml.configs import option
 from labml_nn.cfr import History as _History, InfoSet as _InfoSet, Action, Player, CFRConfigs
-from labml_nn.cfr.infoset_saver import InfoSetSaver
 
 # Kuhn poker actions are pass (`p`) or bet (`b`)
 ACTIONS = cast(List[Action], ['p', 'b'])

labml_nn/diffusion/ddpm/experiment.ipynb

@@ -71,11 +71,7 @@
     }
    },
    "source": [
-    "import torch\n",
-    "import torch.nn as nn\n",
-    "\n",
     "from labml import experiment\n",
-    "from labml.configs import option\n",
     "from labml_nn.diffusion.ddpm.experiment import Configs"
    ],
    "outputs": [],

labml_nn/normalization/deep_norm/experiment.ipynb

@@ -68,11 +68,7 @@
     }
    },
    "source": [
-    "import torch\n",
-    "import torch.nn as nn\n",
-    "\n",
     "from labml import experiment\n",
-    "from labml.configs import option\n",
     "from labml_nn.normalization.deep_norm.experiment import Configs"
    ],
    "outputs": [],

labml_nn/normalization/weight_standardization/experiment.ipynb

@@ -53,9 +53,6 @@
     "id": "0hJXx_g0wS2C"
    },
    "source": [
-    "import torch\n",
-    "import torch.nn as nn\n",
-    "\n",
     "from labml import experiment\n",
     "from labml_nn.normalization.weight_standardization.experiment import CIFAR10Configs as Configs"
    ],

labml_nn/rl/ppo/__init__.py

@@ -26,8 +26,8 @@ The experiment uses [Generalized Advantage Estimation](gae.html).
 """
 
 import torch
-
 from labml_nn.rl.ppo.gae import GAE
+from torch import nn
 
 
 class ClippedPPOLoss(nn.Module):
@@ -178,7 +178,7 @@ class ClippedPPOLoss(nn.Module):
         return -policy_reward.mean()
 
 
-class ClippedValueFunctionLoss(Module):
+class ClippedValueFunctionLoss(nn.Module):
     """
     ## Clipped Value Function Loss
 

labml_nn/transformers/basic/autoregressive_experiment.ipynb

@@ -71,11 +71,7 @@
     }
    },
    "source": [
-    "import torch\n",
-    "import torch.nn as nn\n",
-    "\n",
     "from labml import experiment\n",
-    "from labml.configs import option\n",
     "from labml_nn.transformers.basic.autoregressive_experiment import Configs"
    ],
    "outputs": [],

labml_nn/transformers/fast_weights/experiment.ipynb

@@ -67,11 +67,7 @@
     "id": "0hJXx_g0wS2C"
    },
    "source": [
-    "import torch\n",
-    "import torch.nn as nn\n",
-    "\n",
     "from labml import experiment\n",
-    "from labml.configs import option\n",
     "from labml_nn.transformers.fast_weights.experiment import Configs"
    ],
    "outputs": [],
@@ -138,21 +134,21 @@
    },
    "source": [
     "experiment.configs(conf,\n",
-    "                # A dictionary of configurations to override\n",
-    "                {'tokenizer': 'character',\n",
-    "                'text': 'tiny_shakespeare',\n",
-    "                'optimizer.learning_rate': 1.0,\n",
-    "                'optimizer.optimizer': 'Noam',\n",
-    "                'prompt': 'It is',\n",
-    "                'prompt_separator': '',\n",
+    "                   # A dictionary of configurations to override\n",
+    "                   {'tokenizer': 'character',\n",
+    "                    'text': 'tiny_shakespeare',\n",
+    "                    'optimizer.learning_rate': 1.0,\n",
+    "                    'optimizer.optimizer': 'Noam',\n",
+    "                    'prompt': 'It is',\n",
+    "                    'prompt_separator': '',\n",
     "\n",
-    "                'train_loader': 'shuffled_train_loader',\n",
-    "                'valid_loader': 'shuffled_valid_loader',\n",
+    "                    'train_loader': 'shuffled_train_loader',\n",
+    "                    'valid_loader': 'shuffled_valid_loader',\n",
     "\n",
-    "                'seq_len': 128,\n",
-    "                'epochs': 128,\n",
-    "                'batch_size': 16,\n",
-    "                'inner_iterations': 25})"
+    "                    'seq_len': 128,\n",
+    "                    'epochs': 128,\n",
+    "                    'batch_size': 16,\n",
+    "                    'inner_iterations': 25})"
    ],
    "outputs": [],
    "execution_count": null

labml_nn/unet/carvana.py

@@ -13,13 +13,12 @@ You can find the download instructions
 Save the training images inside `carvana/train` folder and the masks in `carvana/train_masks` folder.
 """
 
-from torch import nn
 from pathlib import Path
 
-import torch.utils.data
 import torchvision.transforms.functional
 from PIL import Image
 
+import torch.utils.data
 from labml import lab