From a3cf12c63f9823b6f457df6c1a7c16bd005ae97f Mon Sep 17 00:00:00 2001
From: Giovanni Volpe <46021832+giovannivolpe@users.noreply.github.com>
Date: Sun, 21 Apr 2024 08:54:48 +0200
Subject: [PATCH] u

---
 .../getting-started/GS101_core_objects.ipynb  | 153 ++++----
 .../getting-started/GS111_first_model.ipynb   | 147 +++++---
 .../getting-started/GS121_configure.ipynb     | 347 ++++++++++--------
 3 files changed, 374 insertions(+), 273 deletions(-)

diff --git a/tutorials/getting-started/GS101_core_objects.ipynb b/tutorials/getting-started/GS101_core_objects.ipynb
index 7c232bce..2e32dda5 100644
--- a/tutorials/getting-started/GS101_core_objects.ipynb
+++ b/tutorials/getting-started/GS101_core_objects.ipynb
@@ -147,14 +147,12 @@
    "metadata": {},
    "outputs": [
     {
-     "ename": "AttributeError",
-     "evalue": "module 'deeplay' has no attribute 'LinearBlock'",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[6], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m linear_block \u001b[38;5;241m=\u001b[39m \u001b[43mdl\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mLinearBlock\u001b[49m(in_features\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m10\u001b[39m, out_features\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m5\u001b[39m)\n\u001b[1;32m      3\u001b[0m \u001b[38;5;28mprint\u001b[39m(linear_block)\n",
-      "\u001b[0;31mAttributeError\u001b[0m: module 'deeplay' has no attribute 'LinearBlock'"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "LinearBlock(\n",
+      "  (layer): Layer[Linear](in_features=10, out_features=5, bias=True)\n",
+      ")\n"
      ]
     }
    ],
@@ -173,9 +171,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "LinearBlock(\n",
+      "  (layer): Layer[Linear](in_features=10, out_features=5, bias=True)\n",
+      "  (activation): Layer[ReLU]()\n",
+      ")\n"
+     ]
+    }
+   ],
    "source": [
     "linear_block.activated(nn.ReLU)\n",
     "\n",
@@ -191,11 +200,26 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "LinearBlock(\n",
+      "  (layer): Linear(in_features=10, out_features=5, bias=True)\n",
+      "  (activation): ReLU()\n",
+      ")\n"
+     ]
+    }
+   ],
    "source": [
-    "linear_block_with_activation = dl.LinearBlock(in_features=10, out_features=5, activation=dl.Layer(nn.ReLU)).build()\n",
+    "linear_block_with_activation = dl.LinearBlock(\n",
+    "    in_features=10, \n",
+    "    out_features=5, \n",
+    "    activation=dl.Layer(nn.ReLU),\n",
+    ").build()\n",
     "\n",
     "print(linear_block_with_activation)"
    ]
@@ -218,7 +242,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -227,17 +251,13 @@
      "text": [
       "MultiLayerPerceptron(\n",
       "  (blocks): LayerList(\n",
-      "    (0): LayerActivationNormalizationDropout(\n",
-      "      (layer): Layer[Linear](in_features=10, out_features=32)\n",
+      "    (0): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=10, out_features=32, bias=True)\n",
       "      (activation): Layer[ReLU]()\n",
-      "      (normalization): Layer[Identity](num_features=32)\n",
-      "      (dropout): Layer[Dropout](p=0)\n",
       "    )\n",
-      "    (1): LayerActivationNormalizationDropout(\n",
-      "      (layer): Layer[Linear](in_features=32, out_features=5)\n",
+      "    (1): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=32, out_features=5, bias=True)\n",
       "      (activation): Layer[ReLU]()\n",
-      "      (normalization): Layer[Identity](num_features=5)\n",
-      "      (dropout): Layer[Identity]()\n",
       "    )\n",
       "  )\n",
       ")\n"
@@ -264,19 +284,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
-     "ename": "AttributeError",
-     "evalue": "'LayerActivationNormalizationDropout' object has no attribute 'activated'",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[8], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mmlp_component\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mblocks\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mactivated\u001b[49m(nn\u001b[38;5;241m.\u001b[39mSigmoid)\n\u001b[1;32m      3\u001b[0m \u001b[38;5;28mprint\u001b[39m(mlp_component)\n",
-      "File \u001b[0;32m~/miniconda3/envs/py310/lib/python3.10/site-packages/torch/nn/modules/module.py:1695\u001b[0m, in \u001b[0;36mModule.__getattr__\u001b[0;34m(self, name)\u001b[0m\n\u001b[1;32m   1693\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m name \u001b[38;5;129;01min\u001b[39;00m modules:\n\u001b[1;32m   1694\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m modules[name]\n\u001b[0;32m-> 1695\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mAttributeError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mtype\u001b[39m(\u001b[38;5;28mself\u001b[39m)\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m object has no attribute \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mname\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
-      "\u001b[0;31mAttributeError\u001b[0m: 'LayerActivationNormalizationDropout' object has no attribute 'activated'"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "MultiLayerPerceptron(\n",
+      "  (blocks): LayerList(\n",
+      "    (0): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=10, out_features=32, bias=True)\n",
+      "      (activation): Layer[Sigmoid]()\n",
+      "    )\n",
+      "    (1): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=32, out_features=5, bias=True)\n",
+      "      (activation): Layer[ReLU]()\n",
+      "    )\n",
+      "  )\n",
+      ")\n"
      ]
     }
    ],
@@ -295,7 +321,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
@@ -304,16 +330,12 @@
      "text": [
       "MultiLayerPerceptron(\n",
       "  (blocks): LayerList(\n",
-      "    (0): LayerActivationNormalizationDropout(\n",
-      "      (layer): Layer[Linear](in_features=10, out_features=32)\n",
-      "      (normalization): Layer[Identity](num_features=32)\n",
-      "      (dropout): Layer[Dropout](p=0)\n",
+      "    (0): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=10, out_features=32, bias=True)\n",
       "    )\n",
-      "    (1): LayerActivationNormalizationDropout(\n",
-      "      (layer): Layer[Linear](in_features=32, out_features=5)\n",
+      "    (1): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=32, out_features=5, bias=True)\n",
       "      (activation): Layer[ReLU]()\n",
-      "      (normalization): Layer[Identity](num_features=5)\n",
-      "      (dropout): Layer[Identity]()\n",
       "    )\n",
       "  )\n",
       ")\n"
@@ -337,18 +359,31 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
-     "ename": "AttributeError",
-     "evalue": "module 'deeplay.models' has no attribute 'SmallMLP'",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[10], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m small_mlp \u001b[38;5;241m=\u001b[39m \u001b[43mdl\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmodels\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mSmallMLP\u001b[49m(in_features\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m10\u001b[39m, out_features\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m5\u001b[39m)\n\u001b[1;32m      3\u001b[0m \u001b[38;5;28mprint\u001b[39m(small_mlp)\n",
-      "\u001b[0;31mAttributeError\u001b[0m: module 'deeplay.models' has no attribute 'SmallMLP'"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "SmallMLP(\n",
+      "  (blocks): LayerList(\n",
+      "    (0): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=10, out_features=32, bias=True)\n",
+      "      (activation): Layer[LeakyReLU](negative_slope=0.05)\n",
+      "      (normalization): Layer[BatchNorm1d](num_features=32)\n",
+      "    )\n",
+      "    (1): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=32, out_features=32, bias=True)\n",
+      "      (activation): Layer[LeakyReLU](negative_slope=0.05)\n",
+      "      (normalization): Layer[BatchNorm1d](num_features=32)\n",
+      "    )\n",
+      "    (2): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=32, out_features=5, bias=True)\n",
+      "      (activation): Layer[Identity]()\n",
+      "    )\n",
+      "  )\n",
+      ")\n"
      ]
     }
    ],
@@ -369,21 +404,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 13,
    "metadata": {},
-   "outputs": [
-    {
-     "ename": "NameError",
-     "evalue": "name 'small_mlp' is not defined",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[11], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m classifier \u001b[38;5;241m=\u001b[39m dl\u001b[38;5;241m.\u001b[39mClassifier(\u001b[43msmall_mlp\u001b[49m, optimizer\u001b[38;5;241m=\u001b[39mdl\u001b[38;5;241m.\u001b[39mAdam(lr\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m0.001\u001b[39m))\n",
-      "\u001b[0;31mNameError\u001b[0m: name 'small_mlp' is not defined"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "classifier = dl.Classifier(small_mlp, optimizer=dl.Adam(lr=0.001))"
    ]
@@ -412,7 +435,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.13"
+   "version": "3.12.2"
   }
  },
  "nbformat": 4,
diff --git a/tutorials/getting-started/GS111_first_model.ipynb b/tutorials/getting-started/GS111_first_model.ipynb
index 09d22679..7e7fb4b7 100644
--- a/tutorials/getting-started/GS111_first_model.ipynb
+++ b/tutorials/getting-started/GS111_first_model.ipynb
@@ -22,35 +22,7 @@
    "cell_type": "code",
    "execution_count": 1,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Downloading http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz\n",
-      "Failed to download (trying next):\n",
-      "<urlopen error [Errno 8] nodename nor servname provided, or not known>\n",
-      "\n",
-      "Downloading https://ossci-datasets.s3.amazonaws.com/mnist/train-images-idx3-ubyte.gz\n",
-      "Failed to download (trying next):\n",
-      "<urlopen error [Errno 8] nodename nor servname provided, or not known>\n",
-      "\n"
-     ]
-    },
-    {
-     "ename": "RuntimeError",
-     "evalue": "Error downloading train-images-idx3-ubyte.gz",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mRuntimeError\u001b[0m                              Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[1], line 3\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mtorchvision\u001b[39;00m\n\u001b[0;32m----> 3\u001b[0m mnist_train \u001b[38;5;241m=\u001b[39m \u001b[43mtorchvision\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdatasets\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mMNIST\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m      4\u001b[0m \u001b[43m    \u001b[49m\u001b[43mroot\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mdata\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\n\u001b[1;32m      5\u001b[0m \u001b[43m    \u001b[49m\u001b[43mtrain\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\n\u001b[1;32m      6\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdownload\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\n\u001b[1;32m      7\u001b[0m \u001b[43m    \u001b[49m\u001b[43mtransform\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtorchvision\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtransforms\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mToTensor\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m      8\u001b[0m \u001b[43m)\u001b[49m\n\u001b[1;32m      9\u001b[0m mnist_val \u001b[38;5;241m=\u001b[39m torchvision\u001b[38;5;241m.\u001b[39mdatasets\u001b[38;5;241m.\u001b[39mMNIST(\n\u001b[1;32m     10\u001b[0m     root\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdata\u001b[39m\u001b[38;5;124m\"\u001b[39m, \n\u001b[1;32m     11\u001b[0m     train\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m, \n\u001b[1;32m     12\u001b[0m     download\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m, \n\u001b[1;32m     13\u001b[0m     transform\u001b[38;5;241m=\u001b[39mtorchvision\u001b[38;5;241m.\u001b[39mtransforms\u001b[38;5;241m.\u001b[39mToTensor(),\n\u001b[1;32m     14\u001b[0m )\n",
-      "File \u001b[0;32m~/miniconda3/envs/py310/lib/python3.10/site-packages/torchvision/datasets/mnist.py:99\u001b[0m, in \u001b[0;36mMNIST.__init__\u001b[0;34m(self, root, train, transform, target_transform, download)\u001b[0m\n\u001b[1;32m     96\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m\n\u001b[1;32m     98\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m download:\n\u001b[0;32m---> 99\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdownload\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    101\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_check_exists():\n\u001b[1;32m    102\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mRuntimeError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDataset not found. You can use download=True to download it\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
-      "File \u001b[0;32m~/miniconda3/envs/py310/lib/python3.10/site-packages/torchvision/datasets/mnist.py:195\u001b[0m, in \u001b[0;36mMNIST.download\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    193\u001b[0m     \u001b[38;5;28;01mbreak\u001b[39;00m\n\u001b[1;32m    194\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 195\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mRuntimeError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mError downloading \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mfilename\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n",
-      "\u001b[0;31mRuntimeError\u001b[0m: Error downloading train-images-idx3-ubyte.gz"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "import torchvision\n",
     "\n",
@@ -83,14 +55,27 @@
    "metadata": {},
    "outputs": [
     {
-     "ename": "AttributeError",
-     "evalue": "module 'deeplay.models' has no attribute 'SmallMLP'",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[2], line 3\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mdeeplay\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mdl\u001b[39;00m\n\u001b[0;32m----> 3\u001b[0m model \u001b[38;5;241m=\u001b[39m \u001b[43mdl\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmodels\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mSmallMLP\u001b[49m(in_features\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m784\u001b[39m, out_features\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m10\u001b[39m)\n\u001b[1;32m      5\u001b[0m \u001b[38;5;28mprint\u001b[39m(model)\n",
-      "\u001b[0;31mAttributeError\u001b[0m: module 'deeplay.models' has no attribute 'SmallMLP'"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "SmallMLP(\n",
+      "  (blocks): LayerList(\n",
+      "    (0): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=784, out_features=32, bias=True)\n",
+      "      (activation): Layer[LeakyReLU](negative_slope=0.05)\n",
+      "      (normalization): Layer[BatchNorm1d](num_features=32)\n",
+      "    )\n",
+      "    (1): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=32, out_features=32, bias=True)\n",
+      "      (activation): Layer[LeakyReLU](negative_slope=0.05)\n",
+      "      (normalization): Layer[BatchNorm1d](num_features=32)\n",
+      "    )\n",
+      "    (2): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=32, out_features=10, bias=True)\n",
+      "      (activation): Layer[Identity]()\n",
+      "    )\n",
+      "  )\n",
+      ")\n"
      ]
     }
    ],
@@ -113,7 +98,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -158,7 +143,11 @@
     }
    ],
    "source": [
-    "classifier = dl.CategoricalClassifier(model, num_classes=10, optimizer=dl.Adam(lr=0.001))\n",
+    "classifier = dl.CategoricalClassifier(\n",
+    "    model, \n",
+    "    num_classes=10, \n",
+    "    optimizer=dl.Adam(lr=0.001),\n",
+    ")\n",
     "\n",
     "print(classifier)"
    ]
@@ -174,9 +163,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 68,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/giovannivolpe/miniconda3/envs/dlcc12/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/logger_connector/logger_connector.py:75: Starting from v1.9.0, `tensorboardX` has been removed as a dependency of the `lightning.pytorch` package, due to potential conflicts with other packages in the ML ecosystem. For this reason, `logger=True` will use `CSVLogger` as the default logger, unless the `tensorboard` or `tensorboardX` packages are found. Please `pip install lightning[extra]` or one of them to enable TensorBoard support by default\n"
+     ]
+    },
     {
      "data": {
       "text/html": [
@@ -229,13 +225,16 @@
     },
     {
      "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "7499ec73fa8d4848be598ae3c9a80141",
-       "version_major": 2,
-       "version_minor": 0
-      },
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">/Users/giovannivolpe/miniconda3/envs/dlcc12/lib/python3.12/site-packages/rich/live.py:231: UserWarning: install \n",
+       "\"ipywidgets\" for Jupyter support\n",
+       "  warnings.warn('install \"ipywidgets\" for Jupyter support')\n",
+       "</pre>\n"
+      ],
       "text/plain": [
-       "Output()"
+       "/Users/giovannivolpe/miniconda3/envs/dlcc12/lib/python3.12/site-packages/rich/live.py:231: UserWarning: install \n",
+       "\"ipywidgets\" for Jupyter support\n",
+       "  warnings.warn('install \"ipywidgets\" for Jupyter support')\n"
       ]
      },
      "metadata": {},
@@ -244,13 +243,13 @@
     {
      "data": {
       "text/html": [
-       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">c:\\Users\\bmidt\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\lightning\\pytorch\\trainer\\connectors\\data_\n",
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">/Users/giovannivolpe/miniconda3/envs/dlcc12/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/data_\n",
        "connector.py:441: The 'val_dataloader' does not have many workers which may be a bottleneck. Consider increasing \n",
        "the value of the `num_workers` argument` to `num_workers=7` in the `DataLoader` to improve performance.\n",
        "</pre>\n"
       ],
       "text/plain": [
-       "c:\\Users\\bmidt\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\lightning\\pytorch\\trainer\\connectors\\data_\n",
+       "/Users/giovannivolpe/miniconda3/envs/dlcc12/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/data_\n",
        "connector.py:441: The 'val_dataloader' does not have many workers which may be a bottleneck. Consider increasing \n",
        "the value of the `num_workers` argument` to `num_workers=7` in the `DataLoader` to improve performance.\n"
       ]
@@ -261,23 +260,51 @@
     {
      "data": {
       "text/html": [
-       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">c:\\Users\\bmidt\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\lightning\\pytorch\\trainer\\connectors\\data_\n",
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">/Users/giovannivolpe/miniconda3/envs/dlcc12/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/data_\n",
        "connector.py:441: The 'train_dataloader' does not have many workers which may be a bottleneck. Consider increasing \n",
        "the value of the `num_workers` argument` to `num_workers=7` in the `DataLoader` to improve performance.\n",
        "</pre>\n"
       ],
       "text/plain": [
-       "c:\\Users\\bmidt\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\lightning\\pytorch\\trainer\\connectors\\data_\n",
+       "/Users/giovannivolpe/miniconda3/envs/dlcc12/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/data_\n",
        "connector.py:441: The 'train_dataloader' does not have many workers which may be a bottleneck. Consider increasing \n",
        "the value of the `num_workers` argument` to `num_workers=7` in the `DataLoader` to improve performance.\n"
       ]
      },
      "metadata": {},
      "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
+      ],
+      "text/plain": []
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
     }
    ],
    "source": [
-    "h = classifier.fit(train_data=mnist_train, val_data=mnist_val, max_epochs=10, batch_size=128)"
+    "h = classifier.fit(\n",
+    "    train_data=mnist_train, \n",
+    "    val_data=mnist_val, \n",
+    "    max_epochs=10, \n",
+    "    batch_size=128,\n",
+    ")"
    ]
   },
   {
@@ -289,25 +316,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
        "(<Figure size 1500x500 with 2 Axes>,\n",
-       " array([<AxesSubplot: title={'center': 'Loss'}, xlabel='Step'>,\n",
-       "        <AxesSubplot: title={'center': 'Multiclassaccuracy'}, xlabel='Step'>],\n",
+       " array([<Axes: title={'center': 'Loss'}, xlabel='Step'>,\n",
+       "        <Axes: title={'center': 'Multiclassaccuracy'}, xlabel='Step'>],\n",
        "       dtype=object))"
       ]
      },
-     "execution_count": 16,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     },
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 1500x500 with 2 Axes>"
       ]
@@ -338,7 +365,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -347,7 +374,7 @@
        "<All keys matched successfully>"
       ]
      },
-     "execution_count": 17,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -369,7 +396,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -417,7 +444,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.13"
+   "version": "3.12.2"
   }
  },
  "nbformat": 4,
diff --git a/tutorials/getting-started/GS121_configure.ipynb b/tutorials/getting-started/GS121_configure.ipynb
index fe157d01..998908db 100644
--- a/tutorials/getting-started/GS121_configure.ipynb
+++ b/tutorials/getting-started/GS121_configure.ipynb
@@ -35,14 +35,27 @@
    "metadata": {},
    "outputs": [
     {
-     "ename": "AttributeError",
-     "evalue": "module 'deeplay.models' has no attribute 'SmallMLP'",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[1], line 3\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mdeeplay\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mdl\u001b[39;00m\n\u001b[0;32m----> 3\u001b[0m mlp \u001b[38;5;241m=\u001b[39m \u001b[43mdl\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmodels\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mSmallMLP\u001b[49m(in_features\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m784\u001b[39m, out_features\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m10\u001b[39m)\n\u001b[1;32m      5\u001b[0m \u001b[38;5;28mprint\u001b[39m(mlp)\n",
-      "\u001b[0;31mAttributeError\u001b[0m: module 'deeplay.models' has no attribute 'SmallMLP'"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "SmallMLP(\n",
+      "  (blocks): LayerList(\n",
+      "    (0): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=784, out_features=32, bias=True)\n",
+      "      (activation): Layer[LeakyReLU](negative_slope=0.05)\n",
+      "      (normalization): Layer[BatchNorm1d](num_features=32)\n",
+      "    )\n",
+      "    (1): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=32, out_features=32, bias=True)\n",
+      "      (activation): Layer[LeakyReLU](negative_slope=0.05)\n",
+      "      (normalization): Layer[BatchNorm1d](num_features=32)\n",
+      "    )\n",
+      "    (2): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=32, out_features=10, bias=True)\n",
+      "      (activation): Layer[Identity]()\n",
+      "    )\n",
+      "  )\n",
+      ")\n"
      ]
     }
    ],
@@ -65,14 +78,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "MLP SmallMLP(\n",
+      "mlp=\n",
+      " SmallMLP(\n",
       "  (blocks): LayerList(\n",
       "    (0): LinearBlock(\n",
       "      (layer): Layer[Linear](in_features=784, out_features=32, bias=True)\n",
@@ -90,7 +104,8 @@
       "    )\n",
       "  )\n",
       ")\n",
-      "Created SmallMLP(\n",
+      "created=\n",
+      " SmallMLP(\n",
       "  (blocks): LayerList(\n",
       "    (0): LinearBlock(\n",
       "      (layer): Linear(in_features=784, out_features=32, bias=True)\n",
@@ -129,42 +144,48 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "MLP MultiLayerPerceptron(\n",
+      "mlp=\n",
+      " SmallMLP(\n",
       "  (blocks): LayerList(\n",
       "    (0): LinearBlock(\n",
-      "      (layer): Linear(in_features=728, out_features=32, bias=True)\n",
-      "      (activation): Tanh()\n",
+      "      (layer): Linear(in_features=784, out_features=32, bias=True)\n",
+      "      (activation): LeakyReLU(negative_slope=0.05)\n",
+      "      (normalization): BatchNorm1d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "    )\n",
       "    (1): LinearBlock(\n",
-      "      (layer): Linear(in_features=32, out_features=16, bias=True)\n",
-      "      (activation): Tanh()\n",
+      "      (layer): Linear(in_features=32, out_features=32, bias=True)\n",
+      "      (activation): LeakyReLU(negative_slope=0.05)\n",
+      "      (normalization): BatchNorm1d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "    )\n",
       "    (2): LinearBlock(\n",
-      "      (layer): Linear(in_features=16, out_features=10, bias=True)\n",
-      "      (activation): Tanh()\n",
+      "      (layer): Linear(in_features=32, out_features=10, bias=True)\n",
+      "      (activation): Identity()\n",
       "    )\n",
       "  )\n",
       ")\n",
-      "Built MultiLayerPerceptron(\n",
+      "built=\n",
+      " SmallMLP(\n",
       "  (blocks): LayerList(\n",
       "    (0): LinearBlock(\n",
-      "      (layer): Linear(in_features=728, out_features=32, bias=True)\n",
-      "      (activation): Tanh()\n",
+      "      (layer): Linear(in_features=784, out_features=32, bias=True)\n",
+      "      (activation): LeakyReLU(negative_slope=0.05)\n",
+      "      (normalization): BatchNorm1d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "    )\n",
       "    (1): LinearBlock(\n",
-      "      (layer): Linear(in_features=32, out_features=16, bias=True)\n",
-      "      (activation): Tanh()\n",
+      "      (layer): Linear(in_features=32, out_features=32, bias=True)\n",
+      "      (activation): LeakyReLU(negative_slope=0.05)\n",
+      "      (normalization): BatchNorm1d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "    )\n",
       "    (2): LinearBlock(\n",
-      "      (layer): Linear(in_features=16, out_features=10, bias=True)\n",
-      "      (activation): Tanh()\n",
+      "      (layer): Linear(in_features=32, out_features=10, bias=True)\n",
+      "      (activation): Identity()\n",
       "    )\n",
       "  )\n",
       ")\n"
@@ -187,7 +208,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -196,7 +217,7 @@
        "True"
       ]
      },
-     "execution_count": 27,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -240,7 +261,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -249,23 +270,17 @@
      "text": [
       "MultiLayerPerceptron(\n",
       "  (blocks): LayerList(\n",
-      "    (0): LayerActivationNormalizationDropout(\n",
-      "      (layer): Layer[Linear](in_features=728, out_features=32)\n",
+      "    (0): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=728, out_features=32, bias=True)\n",
       "      (activation): Layer[Tanh]()\n",
-      "      (normalization): Layer[Identity](num_features=32)\n",
-      "      (dropout): Layer[Dropout](p=0)\n",
       "    )\n",
-      "    (1): LayerActivationNormalizationDropout(\n",
-      "      (layer): Layer[Linear](in_features=32, out_features=16)\n",
+      "    (1): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=32, out_features=16, bias=True)\n",
       "      (activation): Layer[Tanh]()\n",
-      "      (normalization): Layer[Identity](num_features=16)\n",
-      "      (dropout): Layer[Dropout](p=0)\n",
       "    )\n",
-      "    (2): LayerActivationNormalizationDropout(\n",
-      "      (layer): Layer[Linear](in_features=16, out_features=10)\n",
+      "    (2): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=16, out_features=10, bias=True)\n",
       "      (activation): Layer[Tanh]()\n",
-      "      (normalization): Layer[Identity](num_features=10)\n",
-      "      (dropout): Layer[Identity]()\n",
       "    )\n",
       "  )\n",
       ")\n"
@@ -290,24 +305,29 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
-     "ename": "AttributeError",
-     "evalue": "Module LayerActivationNormalizationDropout(\n  (layer): Layer[Linear](in_features=728, out_features=32)\n  (activation): Layer[Tanh]()\n  (normalization): Layer[Identity](num_features=32)\n  (dropout): Layer[Dropout](p=0)\n) does not have a method activated. Use selection.hasattr('method_name') to filter modules that have the method.",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
-      "File \u001b[0;32m~/Documents/GitHub/deeplay/deeplay/module.py:1290\u001b[0m, in \u001b[0;36m_MethodForwarder._create_forwarder.<locals>.forwarder\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m   1289\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m-> 1290\u001b[0m     v \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mgetattr\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mmodule\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mname\u001b[49m\u001b[43m)\u001b[49m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m   1291\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmode \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfirst\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n",
-      "File \u001b[0;32m~/miniconda3/envs/py310/lib/python3.10/site-packages/torch/nn/modules/module.py:1695\u001b[0m, in \u001b[0;36mModule.__getattr__\u001b[0;34m(self, name)\u001b[0m\n\u001b[1;32m   1694\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m modules[name]\n\u001b[0;32m-> 1695\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mAttributeError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mtype\u001b[39m(\u001b[38;5;28mself\u001b[39m)\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m object has no attribute \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mname\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
-      "\u001b[0;31mAttributeError\u001b[0m: 'LayerActivationNormalizationDropout' object has no attribute 'activated'",
-      "\nThe above exception was the direct cause of the following exception:\n",
-      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[4], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mmlp\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mblocks\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m:\u001b[49m\u001b[43m]\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mall\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mactivated\u001b[49m\u001b[43m(\u001b[49m\u001b[43mnn\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mTanh\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m      3\u001b[0m \u001b[38;5;28mprint\u001b[39m(mlp)\n",
-      "File \u001b[0;32m~/Documents/GitHub/deeplay/deeplay/module.py:1294\u001b[0m, in \u001b[0;36m_MethodForwarder._create_forwarder.<locals>.forwarder\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m   1292\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m v\n\u001b[1;32m   1293\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mAttributeError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[0;32m-> 1294\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mAttributeError\u001b[39;00m(\n\u001b[1;32m   1295\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mModule \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mmodule\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m does not have a method \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mname\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m   1296\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mUse selection.hasattr(\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mmethod_name\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m) to filter modules that have the method.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m   1297\u001b[0m     ) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n",
-      "\u001b[0;31mAttributeError\u001b[0m: Module LayerActivationNormalizationDropout(\n  (layer): Layer[Linear](in_features=728, out_features=32)\n  (activation): Layer[Tanh]()\n  (normalization): Layer[Identity](num_features=32)\n  (dropout): Layer[Dropout](p=0)\n) does not have a method activated. Use selection.hasattr('method_name') to filter modules that have the method."
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "MultiLayerPerceptron(\n",
+      "  (blocks): LayerList(\n",
+      "    (0): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=728, out_features=32, bias=True)\n",
+      "      (activation): Layer[Tanh]()\n",
+      "    )\n",
+      "    (1): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=32, out_features=16, bias=True)\n",
+      "      (activation): Layer[Tanh]()\n",
+      "    )\n",
+      "    (2): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=16, out_features=10, bias=True)\n",
+      "      (activation): Layer[Tanh]()\n",
+      "    )\n",
+      "  )\n",
+      ")\n"
      ]
     }
    ],
@@ -320,7 +340,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -329,23 +349,17 @@
      "text": [
       "MultiLayerPerceptron(\n",
       "  (blocks): LayerList(\n",
-      "    (0): LayerActivationNormalizationDropout(\n",
-      "      (layer): Layer[Linear](in_features=728, out_features=32)\n",
+      "    (0): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=728, out_features=32, bias=True)\n",
       "      (activation): Layer[Tanh]()\n",
-      "      (normalization): Layer[Identity](num_features=32)\n",
-      "      (dropout): Layer[Dropout](p=0)\n",
       "    )\n",
-      "    (1): LayerActivationNormalizationDropout(\n",
-      "      (layer): Layer[Linear](in_features=32, out_features=16)\n",
+      "    (1): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=32, out_features=16, bias=True)\n",
       "      (activation): Layer[Tanh]()\n",
-      "      (normalization): Layer[Identity](num_features=16)\n",
-      "      (dropout): Layer[Dropout](p=0)\n",
       "    )\n",
-      "    (2): LayerActivationNormalizationDropout(\n",
-      "      (layer): Layer[Linear](in_features=16, out_features=10)\n",
+      "    (2): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=16, out_features=10, bias=True)\n",
       "      (activation): Layer[Tanh]()\n",
-      "      (normalization): Layer[Identity](num_features=10)\n",
-      "      (dropout): Layer[Identity]()\n",
       "    )\n",
       "  )\n",
       ")\n"
@@ -361,9 +375,32 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "MultiLayerPerceptron(\n",
+      "  (blocks): LayerList(\n",
+      "    (0): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=728, out_features=32, bias=True)\n",
+      "      (activation): Layer[Tanh]()\n",
+      "    )\n",
+      "    (1): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=32, out_features=16, bias=True)\n",
+      "      (activation): Layer[Tanh]()\n",
+      "    )\n",
+      "    (2): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=16, out_features=10, bias=True)\n",
+      "      (activation): Layer[Tanh]()\n",
+      "    )\n",
+      "  )\n",
+      ")\n"
+     ]
+    }
+   ],
    "source": [
     "mlp = dl.MultiLayerPerceptron(728, [32, 16], 10)\n",
     "mlp[...].isinstance(dl.LinearBlock).all.activated(nn.Tanh)\n",
@@ -373,9 +410,32 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "MultiLayerPerceptron(\n",
+      "  (blocks): LayerList(\n",
+      "    (0): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=728, out_features=32, bias=True)\n",
+      "      (activation): Layer[Tanh]()\n",
+      "    )\n",
+      "    (1): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=32, out_features=16, bias=True)\n",
+      "      (activation): Layer[Tanh]()\n",
+      "    )\n",
+      "    (2): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=16, out_features=10, bias=True)\n",
+      "      (activation): Layer[Tanh]()\n",
+      "    )\n",
+      "  )\n",
+      ")\n"
+     ]
+    }
+   ],
    "source": [
     "mlp = dl.MultiLayerPerceptron(728, [32, 16], 10)\n",
     "for block in mlp.blocks:\n",
@@ -393,18 +453,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
-     "ename": "AttributeError",
-     "evalue": "module 'deeplay' has no attribute 'LinearBlock'",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[6], line 2\u001b[0m\n\u001b[1;32m      1\u001b[0m block \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m----> 2\u001b[0m     \u001b[43mdl\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mLinearBlock\u001b[49m(\u001b[38;5;241m64\u001b[39m, \u001b[38;5;241m64\u001b[39m)\n\u001b[1;32m      3\u001b[0m     \u001b[38;5;241m.\u001b[39mactivated(nn\u001b[38;5;241m.\u001b[39mGELU)\n\u001b[1;32m      4\u001b[0m     \u001b[38;5;241m.\u001b[39mshortcut()\n\u001b[1;32m      5\u001b[0m     \u001b[38;5;241m.\u001b[39mnormalized(nn\u001b[38;5;241m.\u001b[39mLayerNorm)\n\u001b[1;32m      6\u001b[0m     \u001b[38;5;241m.\u001b[39mbuild()\n\u001b[1;32m      7\u001b[0m )\n\u001b[1;32m      9\u001b[0m \u001b[38;5;28mprint\u001b[39m(block)\n",
-      "\u001b[0;31mAttributeError\u001b[0m: module 'deeplay' has no attribute 'LinearBlock'"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "LinearBlock(\n",
+      "  (shortcut_start): Identity()\n",
+      "  (layer): Linear(in_features=64, out_features=64, bias=True)\n",
+      "  (activation): GELU(approximate='none')\n",
+      "  (shortcut_end): Add()\n",
+      "  (normalization): LayerNorm((64,), eps=1e-05, elementwise_affine=True)\n",
+      ")\n"
      ]
     }
    ],
@@ -429,24 +491,35 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
-     "ename": "AttributeError",
-     "evalue": "Module LayerActivationNormalizationDropout(\n  (layer): Layer[Linear](in_features=784, out_features=64)\n  (activation): Layer[ReLU]()\n  (normalization): Layer[Identity](num_features=64)\n  (dropout): Layer[Dropout](p=0)\n) does not have a method activated. Use selection.hasattr('method_name') to filter modules that have the method.",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
-      "File \u001b[0;32m~/Documents/GitHub/deeplay/deeplay/module.py:1290\u001b[0m, in \u001b[0;36m_MethodForwarder._create_forwarder.<locals>.forwarder\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m   1289\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m-> 1290\u001b[0m     v \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mgetattr\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mmodule\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mname\u001b[49m\u001b[43m)\u001b[49m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m   1291\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmode \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfirst\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n",
-      "File \u001b[0;32m~/miniconda3/envs/py310/lib/python3.10/site-packages/torch/nn/modules/module.py:1695\u001b[0m, in \u001b[0;36mModule.__getattr__\u001b[0;34m(self, name)\u001b[0m\n\u001b[1;32m   1694\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m modules[name]\n\u001b[0;32m-> 1695\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mAttributeError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mtype\u001b[39m(\u001b[38;5;28mself\u001b[39m)\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m object has no attribute \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mname\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
-      "\u001b[0;31mAttributeError\u001b[0m: 'LayerActivationNormalizationDropout' object has no attribute 'activated'",
-      "\nThe above exception was the direct cause of the following exception:\n",
-      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[7], line 4\u001b[0m\n\u001b[1;32m      1\u001b[0m model \u001b[38;5;241m=\u001b[39m dl\u001b[38;5;241m.\u001b[39mMultiLayerPerceptron(\u001b[38;5;241m784\u001b[39m, [\u001b[38;5;241m64\u001b[39m, \u001b[38;5;241m64\u001b[39m], \u001b[38;5;241m10\u001b[39m)\n\u001b[1;32m      2\u001b[0m \u001b[43mmodel\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mblocks\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m:\u001b[49m\u001b[38;5;241;43m-\u001b[39;49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m \u001b[49m\u001b[43m\\\u001b[49m\n\u001b[1;32m      3\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mall\u001b[49m\u001b[43m \u001b[49m\u001b[43m\\\u001b[49m\n\u001b[0;32m----> 4\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mactivated\u001b[49m\u001b[43m(\u001b[49m\u001b[43mnn\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mReLU\u001b[49m\u001b[43m)\u001b[49m \\\n\u001b[1;32m      5\u001b[0m     \u001b[38;5;241m.\u001b[39mshortcut() \\\n\u001b[1;32m      6\u001b[0m     \u001b[38;5;241m.\u001b[39mnormalized(nn\u001b[38;5;241m.\u001b[39mLayerNorm)\n\u001b[1;32m      8\u001b[0m \u001b[38;5;28mprint\u001b[39m(model)\n",
-      "File \u001b[0;32m~/Documents/GitHub/deeplay/deeplay/module.py:1294\u001b[0m, in \u001b[0;36m_MethodForwarder._create_forwarder.<locals>.forwarder\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m   1292\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m v\n\u001b[1;32m   1293\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mAttributeError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[0;32m-> 1294\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mAttributeError\u001b[39;00m(\n\u001b[1;32m   1295\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mModule \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mmodule\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m does not have a method \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mname\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m   1296\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mUse selection.hasattr(\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mmethod_name\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m) to filter modules that have the method.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m   1297\u001b[0m     ) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n",
-      "\u001b[0;31mAttributeError\u001b[0m: Module LayerActivationNormalizationDropout(\n  (layer): Layer[Linear](in_features=784, out_features=64)\n  (activation): Layer[ReLU]()\n  (normalization): Layer[Identity](num_features=64)\n  (dropout): Layer[Dropout](p=0)\n) does not have a method activated. Use selection.hasattr('method_name') to filter modules that have the method."
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "MultiLayerPerceptron(\n",
+      "  (blocks): LayerList(\n",
+      "    (0): LinearBlock(\n",
+      "      (shortcut_start): Layer[Identity]()\n",
+      "      (layer): Layer[Linear](in_features=784, out_features=64, bias=True)\n",
+      "      (activation): Layer[ReLU]()\n",
+      "      (shortcut_end): Add()\n",
+      "      (normalization): Layer[LayerNorm](normalized_shape=64)\n",
+      "    )\n",
+      "    (1): LinearBlock(\n",
+      "      (shortcut_start): Layer[Identity]()\n",
+      "      (layer): Layer[Linear](in_features=64, out_features=64, bias=True)\n",
+      "      (activation): Layer[ReLU]()\n",
+      "      (shortcut_end): Add()\n",
+      "      (normalization): Layer[LayerNorm](normalized_shape=64)\n",
+      "    )\n",
+      "    (2): LinearBlock(\n",
+      "      (layer): Layer[Linear](in_features=64, out_features=10, bias=True)\n",
+      "      (activation): Layer[Identity]()\n",
+      "    )\n",
+      "  )\n",
+      ")\n"
      ]
     }
    ],
@@ -472,59 +545,37 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "Conv2dBlock(\n",
-       "  (blocks): Sequential(\n",
-       "    (0): Conv2dBlock(\n",
-       "      (shortcut_start): Conv2dBlock(\n",
-       "        (layer): Identity()\n",
-       "        (activation): Identity()\n",
-       "      )\n",
-       "      (blocks): Sequential(\n",
-       "        (0): Conv2dBlock(\n",
-       "          (layer): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1))\n",
-       "          (normalization): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
-       "          (activation): ReLU()\n",
-       "        )\n",
-       "        (1): Conv2dBlock(\n",
-       "          (layer): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1))\n",
-       "          (normalization): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
-       "        )\n",
-       "      )\n",
-       "      (shortcut_end): Add()\n",
-       "      (activation): ReLU()\n",
-       "    )\n",
-       "    (1): Conv2dBlock(\n",
-       "      (shortcut_start): Conv2dBlock(\n",
-       "        (layer): Identity()\n",
-       "        (activation): Identity()\n",
-       "      )\n",
-       "      (blocks): Sequential(\n",
-       "        (0): Conv2dBlock(\n",
-       "          (layer): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1))\n",
-       "          (normalization): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
-       "          (activation): ReLU()\n",
-       "        )\n",
-       "        (1): Conv2dBlock(\n",
-       "          (layer): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1))\n",
-       "          (normalization): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
-       "        )\n",
-       "      )\n",
-       "      (shortcut_end): Add()\n",
-       "      (activation): ReLU()\n",
-       "    )\n",
-       "  )\n",
-       ")"
-      ]
-     },
-     "execution_count": 28,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Conv2dBlock(\n",
+      "  (blocks): Sequential(\n",
+      "    (0-1): 2 x Conv2dBlock(\n",
+      "      (shortcut_start): Conv2dBlock(\n",
+      "        (layer): Identity()\n",
+      "        (activation): Identity()\n",
+      "      )\n",
+      "      (blocks): Sequential(\n",
+      "        (0): Conv2dBlock(\n",
+      "          (layer): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1))\n",
+      "          (normalization): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
+      "          (activation): ReLU()\n",
+      "        )\n",
+      "        (1): Conv2dBlock(\n",
+      "          (layer): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1))\n",
+      "          (normalization): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
+      "        )\n",
+      "      )\n",
+      "      (shortcut_end): Add()\n",
+      "      (activation): ReLU()\n",
+      "    )\n",
+      "  )\n",
+      ")\n"
+     ]
     }
    ],
    "source": [
@@ -564,7 +615,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.13"
+   "version": "3.12.2"
   }
  },
  "nbformat": 4,