diff --git a/vrc_pondernet.ipynb b/vrc_pondernet.ipynb
index 64304c6..105ffaa 100644
--- a/vrc_pondernet.ipynb
+++ b/vrc_pondernet.ipynb
@@ -21,41 +21,74 @@
   },
   {
    "cell_type": "markdown",
-   "source": [],
+   "source": [
+    "## Problem setting\n",
+    "\n",
+    "### Model\n",
+    "Given input and output data, we want to learn a supervised model of the function $X \\to y$ as follows:\n",
+    "\n",
+    "$\n",
+    "f: X,h_n \\mapsto \\tilde{y},h_{n+1}, \\lambda_n\n",
+    "$\n",
+    "\n",
+    "where $X$ and $y$ denote stimulus and response symbols, $\\lambda_n$ denotes halting probability at time $n$, and $h_{n}$ is the latent state of the model. The learninig continious up to the time point $N$.\n",
+    "\n",
+    "For the brevity and compatibility, both data are one-hot encoded.\n",
+    "\n",
+    "\n",
+    "### Input\n",
+    "\n",
+    "One-hot encoded symbols.\n",
+    "\n",
+    "### Output\n",
+    "\n",
+    "One-hot encoded symbols.\n",
+    "\n",
+    "### Criterion\n",
+    "\n",
+    "L = L_cross_entropy + L_halting"
+   ],
    "metadata": {}
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 161,
    "source": [
     "# Setup and imports\n",
     "import torch\n",
     "from torch import nn\n",
+    "from torch.utils.tensorboard import SummaryWriter\n",
+    "\n",
+    "from sklearn.metrics import accuracy_score\n",
     "\n",
     "import numpy as np\n",
     "from scipy import stats\n",
     "import pandas as pd\n",
     "\n",
     "import matplotlib.pyplot as plt\n",
-    "import seaborn as sns; sns.set()"
+    "import seaborn as sns; sns.set()\n",
+    "\n",
+    "import tensorflow as tf\n",
+    "import tensorboard as tb\n",
+    "tf.io.gfile = tb.compat.tensorflow_stub.io.gfile"
    ],
    "outputs": [],
    "metadata": {}
   },
   {
    "cell_type": "code",
-   "execution_count": 170,
+   "execution_count": 2,
    "source": [
     "# produce a tarin of spikes and store timestamps of each spike in `spike_timestamps`.\n",
     "\n",
     "signal_rate = 2\n",
     "noise_rate = 1\n",
     "rate = signal_rate + noise_rate\n",
-    "duration_in_sec = 10.\n",
+    "max_duration_in_sec = 10.\n",
     "resolution_in_sec = .1\n",
     "\n",
-    "n_total_timesteps = int(duration_in_sec / resolution_in_sec)\n",
-    "n_spikes = np.random.poisson(rate * duration_in_sec)\n",
+    "n_total_timesteps = int(max_duration_in_sec / resolution_in_sec)\n",
+    "n_spikes = np.random.poisson(rate * max_duration_in_sec)\n",
     "\n",
     "# method 1: shuffle timesteps\n",
     "spike_timesteps = np.sort(np.random.choice(n_total_timesteps, size=n_spikes, replace=False))\n",
@@ -65,7 +98,7 @@
     "# spike_timestamps = np.cumsum(isi)\n",
     "\n",
     "# method 3: homogenous spikes -> timestamps\n",
-    "# spike_timestamps = stats.uniform.rvs(loc=0, scale=duration_in_sec, size=n_spikes)\n"
+    "# spike_timestamps = stats.uniform.rvs(loc=0, scale=max_duration_in_sec, size=n_spikes)"
    ],
    "outputs": [],
    "metadata": {}
@@ -73,32 +106,11 @@
   {
    "cell_type": "markdown",
    "source": [
-    "## RNN"
+    "## PonderRNN"
    ],
    "metadata": {}
   },
   {
-   "cell_type": "code",
-   "execution_count": 174,
-   "source": [
-    "class PonderVRC(nn.Module):\n",
-    "  def __init__(self, n_inputs, n_channels):\n",
-    "    super(PonderVRC, self).__init__()\n",
-    "    self.rnn = nn.RNN(n_inputs, n_channels)\n",
-    "    self.fc1 = nn.Linear(n_channels, n_inputs, bias=False)\n",
-    "    self.fc2 = nn.Linear(n_channels,1, bias=False)\n",
-    "\n",
-    "  def forward(self, x):\n",
-    "    h = self.rnn(x)\n",
-    "    y = self.fc1(h)\n",
-    "    y = self.fc1(h)\n",
-    "\n",
-    "    return y"
-   ],
-   "outputs": [],
-   "metadata": {}
-  },
-  {
    "cell_type": "markdown",
    "source": [
     "## Mock data"
@@ -107,86 +119,157 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 330,
+   "execution_count": 3,
    "source": [
-    "n_trials = 30\n",
-    "n_stimuli = 6\n",
+    "\n",
+    "\n",
+    "def generate_mock_data(n_subjects, n_trials, n_stimuli):\n",
+    "  \"\"\"[summary]\n",
+    "\n",
+    "  # TODO required data columns: subject_index, trial_index, stimulus_index, accuracy, response_time\n",
+    "\n",
+    "  Args:\n",
+    "      n_subjects (int): [description]\n",
+    "      n_trials (int): [description]\n",
+    "      n_stimuli (int): [description]\n",
+    "\n",
+    "  Returns:\n",
+    "      (X, accuracies, response_times): A tuple containing generated mock X, accuracies, and response_times (in sec).\n",
+    "  \"\"\"\n",
+    "  # stimuli\n",
+    "  X = np.random.randint(low=1, high=n_stimuli+1, size=(n_subjects, n_trials))\n",
+    "\n",
+    "  # response accuracy\n",
+    "  subject_accuracies = np.random.uniform(low=0.2, high=1.0, size=n_subjects)\n",
+    "  subject_accuracies = np.round(subject_accuracies * n_trials) / n_trials\n",
+    "  accuracies = np.empty(shape=(n_subjects, n_trials))\n",
+    "  for subj in range(n_subjects):\n",
+    "    accuracies[subj,:] = np.random.choice(\n",
+    "      [0,1],\n",
+    "      p=[1-subject_accuracies[subj],subject_accuracies[subj]],\n",
+    "      size=n_trials)\n",
+    "\n",
+    "  # generate output w.r.t the accuracy (and fill incorrect trials with invalid response)\n",
+    "  y = np.where(accuracies == 1., X, X+1 % (n_stimuli+1))\n",
+    "\n",
+    "  # response time\n",
+    "  response_times = np.random.exponential(.5, size=accuracies.shape)\n",
+    "\n",
+    "  return X, y, accuracies, response_times"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 105,
+   "source": [
+    "# mock data parameters\n",
     "n_subjects = 1\n",
+    "n_trials = 20\n",
+    "n_stimuli = 6\n",
     "\n",
-    "# required data columns: subject_index, trial_index, stimulus_index, accuracy, response_time\n",
-    "# TODO: generate random data and reshape into the following\n",
+    "X, y, accuracies, response_times = generate_mock_data(n_subjects, n_trials, n_stimuli)"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 172,
+   "source": [
+    "logs = SummaryWriter()\n",
     "\n",
-    "# stimuli\n",
-    "X = np.random.randint(low=1, high=n_stimuli+1, size=(n_subjects, n_trials))\n",
+    "class PonderRNN(nn.Module):\n",
+    "  def __init__(self, n_inputs, n_channels, n_outputs):\n",
+    "    super(PonderRNN, self).__init__()\n",
+    "    self.fc1 = nn.Linear(n_inputs, n_channels, bias=False)\n",
+    "    self.rnn = nn.RNN(n_channels, n_channels)\n",
+    "    self.fc2 = nn.Linear(n_channels,n_outputs, bias=False)\n",
+    "    self.softmax = nn.Softmax(dim=2)\n",
     "\n",
-    "# accuracy (index=0)\n",
-    "accuracies = np.random.randint(low=0, high=2, size=(n_subjects, n_trials))\n",
-    "response_times = np.random.exponential(.5, size=(n_subjects, n_trials))\n",
+    "  def forward(self, x):\n",
+    "    sent_msg = self.fc1(x)\n",
+    "    rcvd_msg, embedding = self.rnn(sent_msg)\n",
+    "    logits = self.fc2(rcvd_msg)\n",
     "\n",
-    "response_times\n",
-    "# responses = np.empty((n_subjects, n_trials, 2))\n",
-    "# responses[:,:,0] = np.where(accuracies==1., X, )\n",
-    "# response_time (index=1)\n",
-    "# responses[:,:,1].exponential_(.5)\n",
-    "\n"
+    "    out = self.softmax(logits).squeeze()\n",
+    "\n",
+    "    halting_prob = 0. # TODO\n",
+    "\n",
+    "    return out, embedding, halting_prob\n",
+    "\n",
+    "def criterion(self, input: torch.Tensor, target: torch.Tensor) -> torch.Tensor:\n",
+    "  return torch.functional.binary_cross_entropy_with_logits()\n",
+    "\n",
+    "n_epoches = 1500\n",
+    "\n",
+    "model = PonderRNN(n_stimuli+1, n_stimuli, n_stimuli+1)\n",
+    "optimizer = torch.optim.Adam(model.parameters(), lr=0.001)\n",
+    "criterion = torch.nn.CrossEntropyLoss()\n",
+    "\n",
+    "X_train = nn.functional.one_hot(torch.tensor(X)).type(torch.float)\n",
+    "y_train = torch.tensor(y) - 1\n",
+    "\n",
+    "for epoch in range(n_epoches):\n",
+    "  model.train()\n",
+    "  optimizer.zero_grad()\n",
+    "  y_pred, h, _ = model(X_train)\n",
+    "\n",
+    "  # logs.add_embedding(h.reshape(n_trials,n_stimuli), global_step=epoch, tag='embedding')\n",
+    "\n",
+    "  model_accuracy = accuracy_score(y_train.squeeze(), torch.argmax(y_pred.detach(),dim=1))\n",
+    "  logs.add_scalar('accurracy/train', model_accuracy, epoch)  \n",
+    "\n",
+    "  loss = criterion(y_pred, y_train.squeeze())\n",
+    "  logs.add_scalar('loss/train', loss, epoch)\n",
+    "  loss.backward()\n",
+    "  optimizer.step()\n",
+    "\n",
+    "# tensorboard --logdir==runs/"
    ],
    "outputs": [
     {
-     "output_type": "execute_result",
-     "data": {
-      "text/plain": [
-       "array([[0.89434811, 0.64370202, 0.19886853, 1.39208346, 0.41082363,\n",
-       "        0.08900332, 1.11360565, 0.46728826, 0.36291653, 0.67963475,\n",
-       "        0.45148227, 0.38839379, 0.64743332, 0.41294597, 0.45289691,\n",
-       "        0.13357337, 0.85012272, 0.7988117 , 1.23502906, 0.53615726,\n",
-       "        0.07061297, 0.80473662, 0.38354505, 0.58555392, 0.38719181,\n",
-       "        0.42993123, 0.23014178, 0.13333575, 0.26819837, 0.28917237]])"
-      ]
-     },
-     "metadata": {},
-     "execution_count": 330
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "torch.Size([1, 20, 6])\n"
+     ]
+    },
+    {
+     "output_type": "error",
+     "ename": "NameError",
+     "evalue": "name 'xx' is not defined",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-172-3dd48c33ed48>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     39\u001b[0m   \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mh\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msize\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     40\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 41\u001b[0;31m   \u001b[0mxx\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     42\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     43\u001b[0m   \u001b[0mlogs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0madd_embedding\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mh\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreshape\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mn_trials\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mn_stimuli\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mglobal_step\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mepoch\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtag\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'embedding'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;31mNameError\u001b[0m: name 'xx' is not defined"
+     ]
     }
    ],
    "metadata": {}
   },
   {
    "cell_type": "code",
-   "execution_count": 176,
+   "execution_count": 137,
    "source": [
-    "\n",
-    "n_epoches = 10\n",
-    "\n",
-    "model = PonderVRC(10,10)\n",
-    "optimizer = torch.optim.Adam(model.parameters(), lr=0.001)\n",
-    "criterion = torch.nn.BCELoss()\n",
-    "\n",
-    "for epoch in range(n_epoches):\n",
-    "  model.train()\n",
-    "  optimizer.zero_grad()\n",
-    "  x = ...\n",
-    "  y_true = ...\n",
-    "  y_pred = model(x)\n",
-    "\n",
-    "  loss = criterion(y_pred, y_pred)\n",
-    "\n",
-    "  loss.backward()\n",
-    "  optimizer.step()"
+    "model.eval()\n",
+    "y_pred, _ = model(X_train)\n",
+    "y_pred = np.argmax(y_pred.detach().numpy(), axis=1) + 1\n",
+    "y_pred, y"
    ],
    "outputs": [
     {
-     "output_type": "error",
-     "ename": "AssertionError",
-     "evalue": "",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mAssertionError\u001b[0m                            Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-176-fe19421f351b>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     10\u001b[0m   \u001b[0mx\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m...\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     11\u001b[0m   \u001b[0my_true\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m...\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 12\u001b[0;31m   \u001b[0my_pred\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     13\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     14\u001b[0m   \u001b[0mloss\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcriterion\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my_pred\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_pred\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;32m~/miniconda3/envs/py3/lib/python3.9/site-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_call_impl\u001b[0;34m(self, *input, **kwargs)\u001b[0m\n\u001b[1;32m    887\u001b[0m             \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_slow_forward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0minput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    888\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 889\u001b[0;31m             \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mforward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0minput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    890\u001b[0m         for hook in itertools.chain(\n\u001b[1;32m    891\u001b[0m                 \u001b[0m_global_forward_hooks\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;32m<ipython-input-174-11ee17fdc0d0>\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, x)\u001b[0m\n\u001b[1;32m      7\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      8\u001b[0m   \u001b[0;32mdef\u001b[0m \u001b[0mforward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 9\u001b[0;31m     \u001b[0mh\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrnn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     10\u001b[0m     \u001b[0my\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfc1\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mh\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     11\u001b[0m     \u001b[0my\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfc1\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mh\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;32m~/miniconda3/envs/py3/lib/python3.9/site-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_call_impl\u001b[0;34m(self, *input, **kwargs)\u001b[0m\n\u001b[1;32m    887\u001b[0m             \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_slow_forward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0minput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    888\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 889\u001b[0;31m             \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mforward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0minput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    890\u001b[0m         for hook in itertools.chain(\n\u001b[1;32m    891\u001b[0m                 \u001b[0m_global_forward_hooks\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;32m~/miniconda3/envs/py3/lib/python3.9/site-packages/torch/nn/modules/rnn.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, input, hx)\u001b[0m\n\u001b[1;32m    242\u001b[0m             \u001b[0mmax_batch_size\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbatch_sizes\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    243\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 244\u001b[0;31m             \u001b[0;32massert\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mTensor\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    245\u001b[0m             \u001b[0mbatch_sizes\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    246\u001b[0m             \u001b[0mmax_batch_size\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0minput\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msize\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbatch_first\u001b[0m \u001b[0;32melse\u001b[0m \u001b[0minput\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msize\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;31mAssertionError\u001b[0m: "
-     ]
+     "output_type": "execute_result",
+     "data": {
+      "text/plain": [
+       "(array([2, 6, 5, 2, 6, 4, 4, 7, 3, 7, 5, 3, 4, 3, 3, 6, 3, 5, 7, 2]),\n",
+       " array([[2, 6, 5, 1, 6, 4, 4, 6, 3, 7, 5, 3, 4, 3, 3, 6, 3, 5, 7, 2]]))"
+      ]
+     },
+     "metadata": {},
+     "execution_count": 137
     }
    ],
    "metadata": {}