Add new notebooks

4 files changed, 984 insertions, 0 deletions

diff --git a/notebooks/04-efficientnet-transformer.ipynb b/notebooks/04-efficientnet-transformer.ipynb
new file mode 100644
index 0000000..427c98c
--- /dev/null
+++ b/notebooks/04-efficientnet-transformer.ipynb
@@ -0,0 +1,219 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "7c02ae76-b540-4b16-9492-e9210b3b9249",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "os.environ['CUDA_VISIBLE_DEVICE'] = ''\n",
+    "import random\n",
+    "\n",
+    "%matplotlib inline\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "import numpy as np\n",
+    "from omegaconf import OmegaConf\n",
+    "\n",
+    "%load_ext autoreload\n",
+    "%autoreload 2\n",
+    "\n",
+    "from importlib.util import find_spec\n",
+    "if find_spec(\"text_recognizer\") is None:\n",
+    "    import sys\n",
+    "    sys.path.append('..')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "ccdb6dde-47e5-429a-88f2-0764fb7e259a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from hydra import compose, initialize\n",
+    "from omegaconf import OmegaConf\n",
+    "from hydra.utils import instantiate"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "3cf50475-39f2-4642-a7d1-5bcbc0a036f7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "path = \"../training/conf/experiment/cnn_htr_char_lines.yaml\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "e52ecb01-c975-4e55-925d-1182c7aea473",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(path, \"rb\") as f:\n",
+    "    cfg = OmegaConf.load(f)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "f939aa37-7b1d-45cc-885c-323c4540bda1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'defaults': [{'override /mapping': None}, {'override /criterion': None}, {'override /datamodule': None}, {'override /network': None}, {'override /model': None}, {'override /lr_schedulers': None}, {'override /optimizers': None}], 'criterion': {'_target_': 'torch.nn.CrossEntropyLoss', 'ignore_index': 3}, 'mapping': {'_target_': 'text_recognizer.data.emnist_mapping.EmnistMapping'}, 'optimizers': {'madgrad': {'_target_': 'madgrad.MADGRAD', 'lr': 0.0001, 'momentum': 0.9, 'weight_decay': 0, 'eps': 1e-06, 'parameters': 'network'}}, 'lr_schedulers': {'network': {'_target_': 'torch.optim.lr_scheduler.CosineAnnealingLR', 'T_max': 1024, 'eta_min': 4.5e-06, 'last_epoch': -1, 'interval': 'epoch', 'monitor': 'val/loss'}}, 'datamodule': {'_target_': 'text_recognizer.data.iam_lines.IAMLines', 'batch_size': 8, 'num_workers': 12, 'train_fraction': 0.8, 'augment': False, 'pin_memory': False}, 'network': {'_target_': 'text_recognizer.networks.conv_transformer.ConvTransformer', 'input_dims': [1, 56, 1024], 'hidden_dim': 128, 'encoder_dim': 1280, 'dropout_rate': 0.2, 'num_classes': 58, 'pad_index': 3, 'encoder': {'_target_': 'text_recognizer.networks.encoders.efficientnet.EfficientNet', 'arch': 'b0', 'out_channels': 1280, 'stochastic_dropout_rate': 0.2, 'bn_momentum': 0.99, 'bn_eps': 0.001}, 'decoder': {'_target_': 'text_recognizer.networks.transformer.Decoder', 'dim': 128, 'depth': 2, 'num_heads': 4, 'attn_fn': 'text_recognizer.networks.transformer.attention.Attention', 'attn_kwargs': {'dim_head': 32, 'dropout_rate': 0.2}, 'norm_fn': 'torch.nn.LayerNorm', 'ff_fn': 'text_recognizer.networks.transformer.mlp.FeedForward', 'ff_kwargs': {'dim_out': None, 'expansion_factor': 4, 'glu': True, 'dropout_rate': 0.2}, 'cross_attend': True, 'pre_norm': True, 'rotary_emb': None}}, 'model': {'_target_': 'text_recognizer.models.transformer.TransformerLitModel', 'max_output_len': 89, 'start_token': '<s>', 'end_token': '<e>', 'pad_token': '<p>'}, 'trainer': {'_target_': 'pytorch_lightning.Trainer', 'stochastic_weight_avg': False, 'auto_scale_batch_size': 'binsearch', 'auto_lr_find': False, 'gradient_clip_val': 0, 'fast_dev_run': False, 'gpus': 1, 'precision': 16, 'max_epochs': 1024, 'terminate_on_nan': True, 'weights_summary': 'top', 'limit_train_batches': 1.0, 'limit_val_batches': 1.0, 'limit_test_batches': 1.0, 'resume_from_checkpoint': None, 'accumulate_grad_batches': 4}}"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "cfg"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "aaeab329-aeb0-4a1b-aa35-5a2aab81b1d0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "net = instantiate(cfg.network)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "618b997c-e6a6-4487-b70c-9d260cb556d3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from torchinfo import summary"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "25759b7b-8deb-4163-b75d-a1357c9fe88f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "torch.Size([4, 4, 89, 1024])\n",
+      "torch.Size([4, 4, 89, 1024])\n",
+      "torch.Size([4, 4, 89, 1024])\n",
+      "torch.Size([4, 4, 32, 1024])\n",
+      "torch.Size([4, 4, 89, 1024])\n",
+      "torch.Size([4, 4, 89, 1024])\n",
+      "torch.Size([4, 4, 89, 1024])\n",
+      "torch.Size([4, 4, 32, 1024])\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "====================================================================================================\n",
+       "Layer (type:depth-idx)                             Output Shape              Param #\n",
+       "====================================================================================================\n",
+       "ConvTransformer                                    --                        --\n",
+       "├─EfficientNet: 1                                  --                        --\n",
+       "│    └─ModuleList: 2-1                             --                        --\n",
+       "├─Decoder: 1                                       --                        --\n",
+       "│    └─ModuleList: 2-2                             --                        --\n",
+       "│    │    └─ModuleList: 3-1                        --                        2,097,536\n",
+       "│    │    └─ModuleList: 3-2                        --                        2,097,536\n",
+       "│    │    └─ModuleList: 3-3                        --                        198,016\n",
+       "│    │    └─ModuleList: 3-4                        --                        2,097,536\n",
+       "│    │    └─ModuleList: 3-5                        --                        2,097,536\n",
+       "│    │    └─ModuleList: 3-6                        --                        198,016\n",
+       "├─EfficientNet: 1-1                                [4, 1280, 1, 32]          --\n",
+       "│    └─Sequential: 2-3                             [4, 32, 28, 512]          --\n",
+       "│    │    └─ZeroPad2d: 3-7                         [4, 1, 57, 1025]          --\n",
+       "│    │    └─Conv2d: 3-8                            [4, 32, 28, 512]          288\n",
+       "│    │    └─BatchNorm2d: 3-9                       [4, 32, 28, 512]          64\n",
+       "│    │    └─Mish: 3-10                             [4, 32, 28, 512]          --\n",
+       "│    └─ModuleList: 2-1                             --                        --\n",
+       "│    │    └─MBConvBlock: 3-11                      [4, 16, 28, 512]          1,448\n",
+       "│    │    └─MBConvBlock: 3-12                      [4, 24, 14, 256]          9,864\n",
+       "│    │    └─MBConvBlock: 3-13                      [4, 24, 14, 256]          19,380\n",
+       "│    │    └─MBConvBlock: 3-14                      [4, 40, 7, 128]           24,020\n",
+       "│    │    └─MBConvBlock: 3-15                      [4, 40, 7, 128]           55,340\n",
+       "│    │    └─MBConvBlock: 3-16                      [4, 80, 3, 64]            61,180\n",
+       "│    │    └─MBConvBlock: 3-17                      [4, 80, 3, 64]            199,000\n",
+       "│    │    └─MBConvBlock: 3-18                      [4, 80, 3, 64]            199,000\n",
+       "│    │    └─MBConvBlock: 3-19                      [4, 112, 3, 64]           222,104\n",
+       "│    │    └─MBConvBlock: 3-20                      [4, 112, 3, 64]           396,872\n",
+       "│    │    └─MBConvBlock: 3-21                      [4, 112, 3, 64]           396,872\n",
+       "│    │    └─MBConvBlock: 3-22                      [4, 192, 1, 32]           450,792\n",
+       "│    │    └─MBConvBlock: 3-23                      [4, 192, 1, 32]           1,141,152\n",
+       "│    │    └─MBConvBlock: 3-24                      [4, 192, 1, 32]           1,141,152\n",
+       "│    │    └─MBConvBlock: 3-25                      [4, 192, 1, 32]           1,141,152\n",
+       "│    │    └─MBConvBlock: 3-26                      [4, 320, 1, 32]           1,270,432\n",
+       "│    └─Sequential: 2-4                             [4, 1280, 1, 32]          --\n",
+       "│    │    └─Conv2d: 3-27                           [4, 1280, 1, 32]          409,600\n",
+       "│    │    └─BatchNorm2d: 3-28                      [4, 1280, 1, 32]          2,560\n",
+       "├─Sequential: 1-2                                  [4, 128, 32]              --\n",
+       "│    └─Conv2d: 2-5                                 [4, 128, 1, 32]           163,968\n",
+       "│    └─PositionalEncoding2D: 2-6                   [4, 128, 1, 32]           --\n",
+       "│    └─Flatten: 2-7                                [4, 128, 32]              --\n",
+       "├─Embedding: 1-3                                   [4, 89, 128]              7,424\n",
+       "├─PositionalEncoding: 1-4                          [4, 89, 128]              --\n",
+       "│    └─Dropout: 2-8                                [4, 89, 128]              --\n",
+       "├─Decoder: 1-5                                     [4, 89, 128]              --\n",
+       "├─Linear: 1-6                                      [4, 89, 58]               7,482\n",
+       "====================================================================================================\n",
+       "Total params: 16,107,322\n",
+       "Trainable params: 16,107,322\n",
+       "Non-trainable params: 0\n",
+       "Total mult-adds (G): 2.84\n",
+       "====================================================================================================\n",
+       "Input size (MB): 0.92\n",
+       "Forward/backward pass size (MB): 677.01\n",
+       "Params size (MB): 64.43\n",
+       "Estimated Total Size (MB): 742.36\n",
+       "===================================================================================================="
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "summary(net, ((4, 1, 56, 1024), (4, 89)), device=\"cpu\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/notebooks/04-efficientnet.ipynb b/notebooks/04-efficientnet.ipynb
new file mode 100644
index 0000000..4148e7d
--- /dev/null
+++ b/notebooks/04-efficientnet.ipynb
@@ -0,0 +1,279 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "7c02ae76-b540-4b16-9492-e9210b3b9249",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "os.environ['CUDA_VISIBLE_DEVICE'] = ''\n",
+    "import random\n",
+    "\n",
+    "%matplotlib inline\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "import numpy as np\n",
+    "from omegaconf import OmegaConf\n",
+    "\n",
+    "%load_ext autoreload\n",
+    "%autoreload 2\n",
+    "\n",
+    "from importlib.util import find_spec\n",
+    "if find_spec(\"text_recognizer\") is None:\n",
+    "    import sys\n",
+    "    sys.path.append('..')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "ccdb6dde-47e5-429a-88f2-0764fb7e259a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from hydra import compose, initialize\n",
+    "from omegaconf import OmegaConf\n",
+    "from hydra.utils import instantiate"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "3cf50475-39f2-4642-a7d1-5bcbc0a036f7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "path = \"../training/conf/network/encoder/efficientnet.yaml\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "e52ecb01-c975-4e55-925d-1182c7aea473",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(path, \"rb\") as f:\n",
+    "    cfg = OmegaConf.load(f)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "f939aa37-7b1d-45cc-885c-323c4540bda1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'_target_': 'text_recognizer.networks.encoders.efficientnet.EfficientNet', 'arch': 'b0', 'out_channels': 1280, 'stochastic_dropout_rate': 0.2, 'bn_momentum': 0.99, 'bn_eps': 0.001}"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "cfg"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "aaeab329-aeb0-4a1b-aa35-5a2aab81b1d0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "net = instantiate(cfg)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "618b997c-e6a6-4487-b70c-9d260cb556d3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from torchinfo import summary"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "25759b7b-8deb-4163-b75d-a1357c9fe88f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "==========================================================================================\n",
+       "Layer (type:depth-idx)                   Output Shape              Param #\n",
+       "==========================================================================================\n",
+       "EfficientNet                             --                        --\n",
+       "├─ModuleList: 1-1                        --                        --\n",
+       "├─Sequential: 1-2                        [2, 32, 288, 320]         --\n",
+       "│    └─ZeroPad2d: 2-1                    [2, 1, 577, 641]          --\n",
+       "│    └─Conv2d: 2-2                       [2, 32, 288, 320]         288\n",
+       "│    └─BatchNorm2d: 2-3                  [2, 32, 288, 320]         64\n",
+       "│    └─Mish: 2-4                         [2, 32, 288, 320]         --\n",
+       "├─ModuleList: 1-1                        --                        --\n",
+       "│    └─MBConvBlock: 2-5                  [2, 16, 288, 320]         --\n",
+       "│    │    └─Sequential: 3-1              [2, 32, 288, 320]         352\n",
+       "│    │    └─Sequential: 3-2              [2, 32, 288, 320]         552\n",
+       "│    │    └─Sequential: 3-3              [2, 16, 288, 320]         544\n",
+       "│    └─MBConvBlock: 2-6                  [2, 24, 144, 160]         --\n",
+       "│    │    └─Sequential: 3-4              [2, 96, 288, 320]         1,728\n",
+       "│    │    └─Sequential: 3-5              [2, 96, 144, 160]         1,056\n",
+       "│    │    └─Sequential: 3-6              [2, 96, 144, 160]         4,728\n",
+       "│    │    └─Sequential: 3-7              [2, 24, 144, 160]         2,352\n",
+       "│    └─MBConvBlock: 2-7                  [2, 24, 144, 160]         --\n",
+       "│    │    └─Sequential: 3-8              [2, 144, 144, 160]        3,744\n",
+       "│    │    └─Sequential: 3-9              [2, 144, 144, 160]        1,584\n",
+       "│    │    └─Sequential: 3-10             [2, 144, 144, 160]        10,548\n",
+       "│    │    └─Sequential: 3-11             [2, 24, 144, 160]         3,504\n",
+       "│    └─MBConvBlock: 2-8                  [2, 40, 72, 80]           --\n",
+       "│    │    └─Sequential: 3-12             [2, 144, 144, 160]        3,744\n",
+       "│    │    └─Sequential: 3-13             [2, 144, 72, 80]          3,888\n",
+       "│    │    └─Sequential: 3-14             [2, 144, 72, 80]          10,548\n",
+       "│    │    └─Sequential: 3-15             [2, 40, 72, 80]           5,840\n",
+       "│    └─MBConvBlock: 2-9                  [2, 40, 72, 80]           --\n",
+       "│    │    └─Sequential: 3-16             [2, 240, 72, 80]          10,080\n",
+       "│    │    └─Sequential: 3-17             [2, 240, 72, 80]          6,480\n",
+       "│    │    └─Sequential: 3-18             [2, 240, 72, 80]          29,100\n",
+       "│    │    └─Sequential: 3-19             [2, 40, 72, 80]           9,680\n",
+       "│    └─MBConvBlock: 2-10                 [2, 80, 36, 40]           --\n",
+       "│    │    └─Sequential: 3-20             [2, 240, 72, 80]          10,080\n",
+       "│    │    └─Sequential: 3-21             [2, 240, 36, 40]          2,640\n",
+       "│    │    └─Sequential: 3-22             [2, 240, 36, 40]          29,100\n",
+       "│    │    └─Sequential: 3-23             [2, 80, 36, 40]           19,360\n",
+       "│    └─MBConvBlock: 2-11                 [2, 80, 36, 40]           --\n",
+       "│    │    └─Sequential: 3-24             [2, 480, 36, 40]          39,360\n",
+       "│    │    └─Sequential: 3-25             [2, 480, 36, 40]          5,280\n",
+       "│    │    └─Sequential: 3-26             [2, 480, 36, 40]          115,800\n",
+       "│    │    └─Sequential: 3-27             [2, 80, 36, 40]           38,560\n",
+       "│    └─MBConvBlock: 2-12                 [2, 80, 36, 40]           --\n",
+       "│    │    └─Sequential: 3-28             [2, 480, 36, 40]          39,360\n",
+       "│    │    └─Sequential: 3-29             [2, 480, 36, 40]          5,280\n",
+       "│    │    └─Sequential: 3-30             [2, 480, 36, 40]          115,800\n",
+       "│    │    └─Sequential: 3-31             [2, 80, 36, 40]           38,560\n",
+       "│    └─MBConvBlock: 2-13                 [2, 112, 36, 40]          --\n",
+       "│    │    └─Sequential: 3-32             [2, 480, 36, 40]          39,360\n",
+       "│    │    └─Sequential: 3-33             [2, 480, 36, 40]          12,960\n",
+       "│    │    └─Sequential: 3-34             [2, 480, 36, 40]          115,800\n",
+       "│    │    └─Sequential: 3-35             [2, 112, 36, 40]          53,984\n",
+       "│    └─MBConvBlock: 2-14                 [2, 112, 36, 40]          --\n",
+       "│    │    └─Sequential: 3-36             [2, 672, 36, 40]          76,608\n",
+       "│    │    └─Sequential: 3-37             [2, 672, 36, 40]          18,144\n",
+       "│    │    └─Sequential: 3-38             [2, 672, 36, 40]          226,632\n",
+       "│    │    └─Sequential: 3-39             [2, 112, 36, 40]          75,488\n",
+       "│    └─MBConvBlock: 2-15                 [2, 112, 36, 40]          --\n",
+       "│    │    └─Sequential: 3-40             [2, 672, 36, 40]          76,608\n",
+       "│    │    └─Sequential: 3-41             [2, 672, 36, 40]          18,144\n",
+       "│    │    └─Sequential: 3-42             [2, 672, 36, 40]          226,632\n",
+       "│    │    └─Sequential: 3-43             [2, 112, 36, 40]          75,488\n",
+       "│    └─MBConvBlock: 2-16                 [2, 192, 18, 20]          --\n",
+       "│    │    └─Sequential: 3-44             [2, 672, 36, 40]          76,608\n",
+       "│    │    └─Sequential: 3-45             [2, 672, 18, 20]          18,144\n",
+       "│    │    └─Sequential: 3-46             [2, 672, 18, 20]          226,632\n",
+       "│    │    └─Sequential: 3-47             [2, 192, 18, 20]          129,408\n",
+       "│    └─MBConvBlock: 2-17                 [2, 192, 18, 20]          --\n",
+       "│    │    └─Sequential: 3-48             [2, 1152, 18, 20]         223,488\n",
+       "│    │    └─Sequential: 3-49             [2, 1152, 18, 20]         31,104\n",
+       "│    │    └─Sequential: 3-50             [2, 1152, 18, 20]         664,992\n",
+       "│    │    └─Sequential: 3-51             [2, 192, 18, 20]          221,568\n",
+       "│    └─MBConvBlock: 2-18                 [2, 192, 18, 20]          --\n",
+       "│    │    └─Sequential: 3-52             [2, 1152, 18, 20]         223,488\n",
+       "│    │    └─Sequential: 3-53             [2, 1152, 18, 20]         31,104\n",
+       "│    │    └─Sequential: 3-54             [2, 1152, 18, 20]         664,992\n",
+       "│    │    └─Sequential: 3-55             [2, 192, 18, 20]          221,568\n",
+       "│    └─MBConvBlock: 2-19                 [2, 192, 18, 20]          --\n",
+       "│    │    └─Sequential: 3-56             [2, 1152, 18, 20]         223,488\n",
+       "│    │    └─Sequential: 3-57             [2, 1152, 18, 20]         31,104\n",
+       "│    │    └─Sequential: 3-58             [2, 1152, 18, 20]         664,992\n",
+       "│    │    └─Sequential: 3-59             [2, 192, 18, 20]          221,568\n",
+       "│    └─MBConvBlock: 2-20                 [2, 320, 18, 20]          --\n",
+       "│    │    └─Sequential: 3-60             [2, 1152, 18, 20]         223,488\n",
+       "│    │    └─Sequential: 3-61             [2, 1152, 18, 20]         12,672\n",
+       "│    │    └─Sequential: 3-62             [2, 1152, 18, 20]         664,992\n",
+       "│    │    └─Sequential: 3-63             [2, 320, 18, 20]          369,280\n",
+       "├─Sequential: 1-3                        [2, 1280, 18, 20]         --\n",
+       "│    └─Conv2d: 2-21                      [2, 1280, 18, 20]         409,600\n",
+       "│    └─BatchNorm2d: 2-22                 [2, 1280, 18, 20]         2,560\n",
+       "==========================================================================================\n",
+       "Total params: 7,142,272\n",
+       "Trainable params: 7,142,272\n",
+       "Non-trainable params: 0\n",
+       "Total mult-adds (G): 11.27\n",
+       "==========================================================================================\n",
+       "Input size (MB): 2.95\n",
+       "Forward/backward pass size (MB): 1922.96\n",
+       "Params size (MB): 28.57\n",
+       "Estimated Total Size (MB): 1954.48\n",
+       "=========================================================================================="
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "summary(net, (2, 1, 576, 640), device=\"cpu\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "3ef95a63-7044-45bf-a085-faf5ea0c03ec",
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "TypeError",
+     "evalue": "'EfficientNet' object is not subscriptable",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[0;32m/tmp/ipykernel_2800/4064962505.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mnet\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0;36m2\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[0;31mTypeError\u001b[0m: 'EfficientNet' object is not subscriptable"
+     ]
+    }
+   ],
+   "source": [
+    "net[:-2]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "62ca0d97-625c-474b-8d6c-d0caba79e198",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/notebooks/04-vq-transformer.ipynb b/notebooks/04-vq-transformer.ipynb
new file mode 100644
index 0000000..69d2688
--- /dev/null
+++ b/notebooks/04-vq-transformer.ipynb
@@ -0,0 +1,253 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7c02ae76-b540-4b16-9492-e9210b3b9249",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "os.environ['CUDA_VISIBLE_DEVICE'] = ''\n",
+    "import random\n",
+    "\n",
+    "%matplotlib inline\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "import numpy as np\n",
+    "from omegaconf import OmegaConf\n",
+    "\n",
+    "%load_ext autoreload\n",
+    "%autoreload 2\n",
+    "\n",
+    "from importlib.util import find_spec\n",
+    "if find_spec(\"text_recognizer\") is None:\n",
+    "    import sys\n",
+    "    sys.path.append('..')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ccdb6dde-47e5-429a-88f2-0764fb7e259a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from hydra import compose, initialize\n",
+    "from omegaconf import OmegaConf\n",
+    "from hydra.utils import instantiate"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3cf50475-39f2-4642-a7d1-5bcbc0a036f7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "path = \"../training/conf/experiment/vqgan_htr_char_iam_lines.yaml\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e52ecb01-c975-4e55-925d-1182c7aea473",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(path, \"rb\") as f:\n",
+    "    cfg = OmegaConf.load(f)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f939aa37-7b1d-45cc-885c-323c4540bda1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cfg"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "aaeab329-aeb0-4a1b-aa35-5a2aab81b1d0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "net = instantiate(cfg.network)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a564ac7a-b67f-4bc1-af36-0fe0a58c1bc9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import torch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "aeddcc5c-e48d-4d90-8efa-963011ef40bc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x = torch.randn((16, 1, 16, 64))\n",
+    "y = torch.randint(0, 56, (16, 89))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0f0d78bc-7e0a-4d06-8e38-49b29ad25933",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e9f4ee2a-c93f-4461-8d75-40c8c12d9d48",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "yy = net(x, y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7a7493a9-0e1d-46ef-8180-27605e18d082",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "yy[0].shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "75bc9695-2afd-455c-a4fb-2e182456ccbd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "z = torch.randn((16, 8, 32))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3df6f9a0-6e66-4f46-a5b7-c0bb71b16b9b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "z, _ = net.encode(x)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6d6e9dd1-c56e-4169-8216-bcc84ea980e3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "z.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8f1539cb-b9b2-40b7-a843-d7479ddbddd7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "yy = net.decode(z, y[:, :2])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5cdba0a9-da7d-4e33-b209-7f360d1a38e5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "yy.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6da8065f-f93f-4aec-a60e-408712a28c3b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "torch.argmax(yy,dim=-2).shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "beabbda7-6a1f-4294-8f01-f9d866ffe088",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "yy[0].shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "618b997c-e6a6-4487-b70c-9d260cb556d3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from torchinfo import summary"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "25759b7b-8deb-4163-b75d-a1357c9fe88f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "summary(net, (1, 1, 576, 640), device=\"cpu\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "62ca0d97-625c-474b-8d6c-d0caba79e198",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/notebooks/04-vqvae.ipynb b/notebooks/04-vqvae.ipynb
new file mode 100644
index 0000000..1b31671
--- /dev/null
+++ b/notebooks/04-vqvae.ipynb
@@ -0,0 +1,233 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "136a80f5-10e1-40c4-973a-a7eb7939bb1f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The autoreload extension is already loaded. To reload it, use:\n",
+      "  %reload_ext autoreload\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "os.environ['CUDA_VISIBLE_DEVICE'] = ''\n",
+    "import random\n",
+    "\n",
+    "%matplotlib inline\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "import numpy as np\n",
+    "from omegaconf import OmegaConf\n",
+    "from hydra import compose, initialize\n",
+    "from omegaconf import OmegaConf\n",
+    "from hydra.utils import instantiate\n",
+    "from torchinfo import summary\n",
+    "%load_ext autoreload\n",
+    "%autoreload 2\n",
+    "\n",
+    "from importlib.util import find_spec\n",
+    "if find_spec(\"text_recognizer\") is None:\n",
+    "    import sys\n",
+    "    sys.path.append('..')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "1a0fb9ca-1886-4fd4-839f-dc111a450cfd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "path = \"../training/conf/network/vqvae.yaml\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "0182a614-5781-44a6-b659-008e7c584fa7",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "encoder:\n",
+      "  _target_: text_recognizer.networks.vqvae.encoder.Encoder\n",
+      "  in_channels: 1\n",
+      "  hidden_dim: 32\n",
+      "  channels_multipliers:\n",
+      "  - 1\n",
+      "  - 2\n",
+      "  - 4\n",
+      "  dropout_rate: 0.0\n",
+      "  activation: mish\n",
+      "  use_norm: true\n",
+      "  num_residuals: 4\n",
+      "  residual_channels: 32\n",
+      "decoder:\n",
+      "  _target_: text_recognizer.networks.vqvae.decoder.Decoder\n",
+      "  out_channels: 1\n",
+      "  hidden_dim: 32\n",
+      "  channels_multipliers:\n",
+      "  - 4\n",
+      "  - 2\n",
+      "  - 1\n",
+      "  dropout_rate: 0.0\n",
+      "  activation: mish\n",
+      "  use_norm: true\n",
+      "  num_residuals: 4\n",
+      "  residual_channels: 32\n",
+      "_target_: text_recognizer.networks.vqvae.vqvae.VQVAE\n",
+      "hidden_dim: 128\n",
+      "embedding_dim: 32\n",
+      "num_embeddings: 8192\n",
+      "decay: 0.99\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/aktersnurra/.cache/pypoetry/virtualenvs/text-recognizer-ejNaVa9M-py3.9/lib/python3.9/site-packages/hydra/_internal/defaults_list.py:251: UserWarning: In 'vqvae': Defaults list is missing `_self_`. See https://hydra.cc/docs/upgrades/1.0_to_1.1/default_composition_order for more information\n",
+      "  warnings.warn(msg, UserWarning)\n"
+     ]
+    }
+   ],
+   "source": [
+    "with initialize(config_path=\"../training/conf/network/\", job_name=\"test_app\"):\n",
+    "    cfg = compose(config_name=\"vqvae\")\n",
+    "    print(OmegaConf.to_yaml(cfg))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "a500f94c-7dae-477e-a3fb-2a2d62ee7b72",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "net = instantiate(cfg)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "7f3b3559-5e23-485e-bf57-9405568a1fbf",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "====================================================================================================\n",
+       "Layer (type:depth-idx)                             Output Shape              Param #\n",
+       "====================================================================================================\n",
+       "VQVAE                                              --                        --\n",
+       "├─Encoder: 1-1                                     [1, 128, 72, 80]          --\n",
+       "│    └─Sequential: 2-1                             [1, 128, 72, 80]          --\n",
+       "│    │    └─Conv2d: 3-1                            [1, 32, 576, 640]         320\n",
+       "│    │    └─Normalize: 3-2                         [1, 32, 576, 640]         64\n",
+       "│    │    └─Mish: 3-3                              [1, 32, 576, 640]         --\n",
+       "│    │    └─Mish: 3-4                              [1, 32, 576, 640]         --\n",
+       "│    │    └─Mish: 3-5                              [1, 32, 576, 640]         --\n",
+       "│    │    └─Conv2d: 3-6                            [1, 32, 288, 320]         16,416\n",
+       "│    │    └─Normalize: 3-7                         [1, 32, 288, 320]         64\n",
+       "│    │    └─Mish: 3-8                              [1, 32, 288, 320]         --\n",
+       "│    │    └─Mish: 3-9                              [1, 32, 288, 320]         --\n",
+       "│    │    └─Mish: 3-10                             [1, 32, 288, 320]         --\n",
+       "│    │    └─Conv2d: 3-11                           [1, 64, 144, 160]         32,832\n",
+       "│    │    └─Normalize: 3-12                        [1, 64, 144, 160]         128\n",
+       "│    │    └─Mish: 3-13                             [1, 64, 144, 160]         --\n",
+       "│    │    └─Mish: 3-14                             [1, 64, 144, 160]         --\n",
+       "│    │    └─Mish: 3-15                             [1, 64, 144, 160]         --\n",
+       "│    │    └─Conv2d: 3-16                           [1, 128, 72, 80]          131,200\n",
+       "│    │    └─Residual: 3-17                         [1, 128, 72, 80]          41,280\n",
+       "│    │    └─Residual: 3-18                         [1, 128, 72, 80]          41,280\n",
+       "│    │    └─Residual: 3-19                         [1, 128, 72, 80]          41,280\n",
+       "│    │    └─Residual: 3-20                         [1, 128, 72, 80]          41,280\n",
+       "├─Conv2d: 1-2                                      [1, 32, 72, 80]           4,128\n",
+       "├─VectorQuantizer: 1-3                             [1, 32, 72, 80]           --\n",
+       "├─Conv2d: 1-4                                      [1, 128, 72, 80]          4,224\n",
+       "├─Decoder: 1-5                                     [1, 1, 576, 640]          --\n",
+       "│    └─Sequential: 2-2                             [1, 1, 576, 640]          --\n",
+       "│    │    └─Residual: 3-21                         [1, 128, 72, 80]          41,280\n",
+       "│    │    └─Residual: 3-22                         [1, 128, 72, 80]          41,280\n",
+       "│    │    └─Residual: 3-23                         [1, 128, 72, 80]          41,280\n",
+       "│    │    └─Residual: 3-24                         [1, 128, 72, 80]          41,280\n",
+       "│    │    └─Normalize: 3-25                        [1, 128, 72, 80]          256\n",
+       "│    │    └─Mish: 3-26                             [1, 128, 72, 80]          --\n",
+       "│    │    └─Mish: 3-27                             [1, 128, 72, 80]          --\n",
+       "│    │    └─Mish: 3-28                             [1, 128, 72, 80]          --\n",
+       "│    │    └─ConvTranspose2d: 3-29                  [1, 64, 144, 160]         131,136\n",
+       "│    │    └─Normalize: 3-30                        [1, 64, 144, 160]         128\n",
+       "│    │    └─Mish: 3-31                             [1, 64, 144, 160]         --\n",
+       "│    │    └─Mish: 3-32                             [1, 64, 144, 160]         --\n",
+       "│    │    └─Mish: 3-33                             [1, 64, 144, 160]         --\n",
+       "│    │    └─ConvTranspose2d: 3-34                  [1, 32, 288, 320]         32,800\n",
+       "│    │    └─Normalize: 3-35                        [1, 32, 288, 320]         64\n",
+       "│    │    └─Mish: 3-36                             [1, 32, 288, 320]         --\n",
+       "│    │    └─Mish: 3-37                             [1, 32, 288, 320]         --\n",
+       "│    │    └─Mish: 3-38                             [1, 32, 288, 320]         --\n",
+       "│    │    └─ConvTranspose2d: 3-39                  [1, 32, 576, 640]         16,416\n",
+       "│    │    └─Normalize: 3-40                        [1, 32, 576, 640]         64\n",
+       "│    │    └─Conv2d: 3-41                           [1, 1, 576, 640]          289\n",
+       "====================================================================================================\n",
+       "Total params: 700,769\n",
+       "Trainable params: 700,769\n",
+       "Non-trainable params: 0\n",
+       "Total mult-adds (G): 17.28\n",
+       "====================================================================================================\n",
+       "Input size (MB): 1.47\n",
+       "Forward/backward pass size (MB): 659.13\n",
+       "Params size (MB): 2.80\n",
+       "Estimated Total Size (MB): 663.41\n",
+       "===================================================================================================="
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "summary(net, (1, 1, 576, 640), device=\"cpu\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9f880b03-d641-4640-acd3-aa5666ca5184",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}