diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index 143514b36ba31cb2b292f3a1961187709798efbf..f8f12a0269fb124bed7efa93b1826a66cfca5982 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -32,7 +32,7 @@ default_language_version:
     python: python3
 
 repos:
-- repo: git://github.com/pre-commit/pre-commit-hooks
+- repo: https://github.com/pre-commit/pre-commit-hooks
   rev: v3.2.0
   hooks:
   - id: trailing-whitespace
@@ -50,12 +50,12 @@ repos:
   - id: mixed-line-ending
     args: ['--fix=no']
 
-- repo: git://github.com/PyCQA/isort
+- repo: https://github.com/PyCQA/isort
   rev: 5.5.3
   hooks:
   - id: isort
 
-- repo: git://github.com/psf/black
+- repo: https://github.com/psf/black
   rev: stable
   hooks:
   - id: black
diff --git a/notebooks/end2end_example/cybersecurity/1-train-mlp-with-brevitas.ipynb b/notebooks/end2end_example/cybersecurity/1-train-mlp-with-brevitas.ipynb
index 2c9f4a99ed3edd05a8e8d32db2fe6bcdad204716..69ac1f7717f281a43b7d6215eee91e8d3e1d9478 100644
--- a/notebooks/end2end_example/cybersecurity/1-train-mlp-with-brevitas.ipynb
+++ b/notebooks/end2end_example/cybersecurity/1-train-mlp-with-brevitas.ipynb
@@ -103,27 +103,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "--2021-10-12 15:49:17--  https://zenodo.org/record/4519767/files/unsw_nb15_binarized.npz?download=1\n",
-      "Resolving zenodo.org (zenodo.org)... 137.138.76.77\n",
-      "Connecting to zenodo.org (zenodo.org)|137.138.76.77|:443... connected.\n",
-      "HTTP request sent, awaiting response... 200 OK\n",
-      "Length: 13391907 (13M) [application/octet-stream]\n",
-      "Saving to: ‘unsw_nb15_binarized.npz’\n",
-      "\n",
-      "unsw_nb15_binarized 100%[===================>]  12.77M  3.56MB/s    in 3.7s    \n",
-      "\n",
-      "2021-10-12 15:49:22 (3.44 MB/s) - ‘unsw_nb15_binarized.npz’ saved [13391907/13391907]\n",
-      "\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "! wget -O unsw_nb15_binarized.npz https://zenodo.org/record/4519767/files/unsw_nb15_binarized.npz?download=1"
    ]
@@ -137,18 +119,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Samples in each set: train = 175341, test = 82332\n",
-      "Shape of one input sample: torch.Size([593])\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "import numpy as np\n",
     "from torch.utils.data import TensorDataset\n",
@@ -220,6 +193,33 @@
     "        break"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Define a PyTorch Device <a id='define_pytorch_device'></a> \n",
+    "\n",
+    "GPUs can significantly speed-up training of deep neural networks. We check for availability of a GPU and if so define it as target device."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Target device: cuda\n"
+     ]
+    }
+   ],
+   "source": [
+    "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
+    "print(\"Target device: \" + str(device))"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -236,7 +236,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -258,7 +258,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -282,7 +282,9 @@
     "      nn.Dropout(0.5),\n",
     "      QuantReLU(bit_width=act_bit_width),\n",
     "      QuantLinear(hidden3, num_classes, bias=True, weight_bit_width=weight_bit_width)\n",
-    ")\n"
+    ")\n",
+    "\n",
+    "model.to(device)"
    ]
   },
   {
@@ -302,7 +304,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -313,6 +315,7 @@
     "    \n",
     "    for i, data in enumerate(train_loader, 0):        \n",
     "        inputs, target = data\n",
+    "        inputs, target = inputs.to(device), target.to(device)\n",
     "        optimizer.zero_grad()   \n",
     "                \n",
     "        # forward pass\n",
@@ -324,14 +327,14 @@
     "        optimizer.step()\n",
     "        \n",
     "        # keep track of loss value\n",
-    "        losses.append(loss.data.numpy()) \n",
+    "        losses.append(loss.data.cpu().numpy()) \n",
     "           \n",
     "    return losses"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -347,12 +350,13 @@
     "    with torch.no_grad():\n",
     "        for data in test_loader:\n",
     "            inputs, target = data\n",
+    "            inputs, target = inputs.to(device), target.to(device)\n",
     "            output_orig = model(inputs.float())\n",
     "            # run the output through sigmoid\n",
     "            output = torch.sigmoid(output_orig)  \n",
     "            # compare against a threshold of 0.5 to generate 0/1\n",
-    "            pred = (output.detach().numpy() > 0.5) * 1\n",
-    "            target = target.float()\n",
+    "            pred = (output.detach().cpu().numpy() > 0.5) * 1\n",
+    "            target = target.cpu().float()\n",
     "            y_true.extend(target.tolist()) \n",
     "            y_pred.extend(pred.reshape(-1).tolist())\n",
     "        \n",
@@ -384,7 +388,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -402,18 +406,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [],
    "source": [
     "# loss criterion and optimizer\n",
-    "criterion = nn.BCEWithLogitsLoss()\n",
+    "criterion = nn.BCEWithLogitsLoss().to(device)\n",
     "optimizer = torch.optim.Adam(model.parameters(), lr=lr, betas=(0.9, 0.999))"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 13,
    "metadata": {
     "scrolled": true
    },
@@ -422,7 +426,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Training loss = 0.132918 test accuracy = 0.798341: 100%|██████████| 10/10 [00:44<00:00,  4.45s/it]\n"
+      "Training loss = 0.131165 test accuracy = 0.809102: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 10/10 [02:24<00:00, 14.43s/it]\n"
      ]
     }
    ],
@@ -450,14 +454,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 14,
    "metadata": {
     "scrolled": true
    },
    "outputs": [
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "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\n",
       "text/plain": [
        "<Figure size 432x288 with 1 Axes>"
       ]
@@ -478,12 +482,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYgAAAEWCAYAAAB8LwAVAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/d3fzzAAAACXBIWXMAAAsTAAALEwEAmpwYAAAot0lEQVR4nO3deXxcZ33v8c9Xuyx5X+LEexI7djYSUMOSsrQ0kFJIKFDqpBRyWxrgEkqhhZv09lIaXuXSjcItebUNNMAtS6CBUtObktKyFgq1Q0xCrHHiOIttNIls2dZYsvbf/eMcyWN5JI1tjWak+b5fr3nNOc9Z5qeJc37znOc5z6OIwMzMbLyacgdgZmaVyQnCzMwKcoIwM7OCnCDMzKwgJwgzMyvICcLMzApygjAzs4KcIGzWk3Qs7zUi6Xje+q+dwfm+JenNpYjVbDapK3cAZmcrIlpHlyU9Abw5Iv6tfBGVlqS6iBgqdxw297kGYXOWpBpJt0p6TNIhSV+UtCTd1iTpM2n5EUnbJZ0j6Y+BFwIfS2sgH5vg3P8gKSvpqKTvSLokb1uzpL+Q9GS6/T8kNafbflbS99PP3CfpprT8pFqLpJsk/Ufeekh6u6RHgUfTso+m5+iWdL+kF+btXyvp99O/PZduXyPpDkl/Me5v2SbpXWf/jdtc4wRhc9k7gFcDLwbOAw4Dd6Tb3gQsBNYAS4G3Ascj4n8C3wVuiYjWiLhlgnP/C7ARWAH8CPhs3rY/B54DvABYArwXGJG0Lj3ur4DlwBXAztP4e14NPBe4OF3fnp5jCfA54B8kNaXb3g3cALwCWAD8BtALfBq4QVINgKRlwC+kx5udxLeYbC57K8mFfj+ApPcDT0n6dWCQJDFcGBEPAvefzokj4q7R5fS8hyUtBHIkF+PnRcSBdJfvp/vdCPxbRHw+LT+Uvor1vyOiKy+Gz+Rt+wtJfwBcBPwYeDPw3ojYnW7/8ehnSjoKvBT4OrAV+FZEPH0acViVcA3C5rJ1wD+mt3OOAO3AMHAO8PfAfcDdkn4q6U8l1Rdz0vT2zYfS2zfdwBPppmXpqwl4rMChayYoL9a+cXH8nqT29DbWEZIa0bIiPuvTwBvS5TeQfBdmp3CCsLlsH/CLEbEo79UUEQciYjAi/igiLia5FfRK4I3pcVMNcXwjcD3JrZmFwPq0XMBBoA+4YIJ4CpUD9ADz8tZXFthnLK60veG9wOuBxRGxCDiaxjDVZ30GuF7Ss4AtwFcm2M+qnBOEzWV/A/xxeu8fScslXZ8u/5ykyyTVAt0kt5xG0uOeBs6f5LzzgX6S20PzgA+OboiIEeAu4MOSzktrG8+X1EjSTvELkl4vqU7SUklXpIfuBF4jaZ6kC4HfnOJvmw8MAZ1AnaT3kbQ1jPoE8AFJG5W4XNLSNMb9JO0Xfw98KSKOT/FZVqWcIGwu+yiwDfhXSTngBySNvJD8Qr+HJDm0A9/mxK2WjwKvk3RY0v8pcN7/CzwJHAB2pefN93vAQyQX4S7gT4CaiHiKpNH4d9PyncCz0mP+EhggSU6f5uRG70LuA74GPJLG0sfJt6A+DHwR+Nf0b/w7oDlv+6eBy/DtJZuEPGGQWfWR9CKSW03rwhcBm4BrEGZVJm2MfyfwCScHm4wThFkVkbQFOAKcC3ykrMFYxfMtJjMzK8g1CDMzK2jOPEm9bNmyWL9+fbnDMDObVe6///6DEbG80LY5kyDWr1/Pjh07yh2GmdmsIunJibb5FpOZmRXkBGFmZgU5QZiZWUFOEGZmVpAThJmZFeQEYWZmBZU0QUi6VtJuSXsk3Vpg+1pJ35T0gKQHJb0ib9tt6XG7Jb28lHGamdmpSvYcRDrO/h3ANcB+YLukbRGxK2+3PwC+GBF/Leli4F5gfbq8FbiEZC7hf5O0KSKGSxWvmRUWETzd3c+D+4/w6DPHaKyrYdG8BhbPqx97XzyvgYXN9dTUaOoT2qxRygflrgL2RMReAEl3k8zClZ8gghOTnCwEfpouXw/cHRH9wOOS9qTn+88SxmtmwDPdfTy4/ygPHTjx6sz1T3mcBAubk2SxaN7J7yeSSd5yS7Ktqb52Bv4qOxOlTBCrOHkCk/2cmKxl1PtJJnN5B9BCMoXj6LH5k7DsT8tOIulm4GaAtWvXTkvQZtWkM9fPTw4cTRPCER46cJSnu5NkUCO4YHkrL9y4jMtXLeSy1QvZvHIBQ8PB4d4BjhwfTN57BzjcM5i8946WDfJ0dx+7szkO9w7QOzBx5b+pviZNJg0saq5nccvJNZNCtZUFzfXUVkFtpW9wmEM9A3QdG+BQTz+Hjg3Q1TPAwZ5+usaWB1i/dB4f3XrltH9+uYfauAH4VET8haTnA38v6dJiD46IO4E7Adra2jwsrdkkDh3rT2oEebWDjqN9QPLr//xlLbzggmVcliaDi89dQEtj4UvEwnn1p/XZ/UPDHEmTx6nJJFk+kiaW3dkcR3oHOXJ8kOGRwv9bS9DaUMf8pjrmN9WzoDl5T9ZPLC8Y9z5W3lxPS0Mt0swmmb7BYbp6BjiUXvBPLA/QlSaAQz3ptmMD9EyQWOtrxdKWRpa0NLC0tYFzFzYX3O9slTJBHADW5K2vTsvy/SZwLUBE/KekJmBZkcea2QQO9wycuEWUJoQDR05MPX3+shau2rAkSQarFnLJqoW0TpAMpkNjXS3nLKjlnAVNRR8zMhLk+odOTSY9SfLI9Q3SfXyIXN8gub4hnsn18VjnELm+IbqPDzI0QXIZVSNobTw5mUyVaOY31bMgr7y2RnT1JL/kD/UMcOhY/ynLB9Nf+l09AxzrHyoYS32tkot9SyNLWxtYt3Te2PLSloaxRLC0pZElrQ3Mb6ybkeRWygSxHdgoaQPJxX0rcOO4fZ4CXgp8Kp3IpIlkEvZtwOckfZikkXoj8F8ljNVszOGeAXbuP8IDTx1h574j9PYPsaA5uTAk78mFJHk/dX1+Ux31tTPXg/xo7yA/+enJt4n2dZ1IBuuXzuPZ6xbzphes47JVi7hk1QIWNJ1eDaAcamrEwuZ6FjbXs27p6R0bEfQNjiRJpO9EEulO33Nj70nZaKL56ZE+cv25sW0T1WCmUlcjlrY2sKSlkaUtyQV/SUsDy1qTX/3JcrJ9SUsDC5pm5oJ/ukqWICJiSNItJJOr1wJ3RcTDkm4HdkTENpLJ2z8u6V0kDdY3pVMgPizpiyQN2kPA292DyUphcHiE3dkcDzx1mAeeOsID+47w+MEeIPmFuemc+SxpaeCZXB97nhm9mAwy1XVjXkNtgURy9gmmu2+Qn4y7TfTkod6x7WuXzOPyVYv4teeu4/K0ZrCwufKTwXSTRHNDLc0NtaxYMPX+hUQEvQPDYwmlUKIZHgkWz2sY+6W/tLWyL/ina87MKNfW1hYe7tumkj3alySDfUd44KnDPHTgKH2DIwAsa23kyrWLkteaxVy+emHBe/CjF47RX56jSWNsPX+5b7DAflP/Mh2fYFoa63iqq3cseQGsXtw81l5w+apFXLpqAYvmNUzvF2ZznqT7I6Kt0LZyN1KblUzf4DAPHTjKA08dZue+5JbRaKNsQ20Nl6xawI1XrRtLCqsWNRf1q08SLY11tDTWce7C04/rTBLM4d4BNp3Tyuues5pL03aDJS1OBlZaThB2kogg291Ha2MdrTPUEDYdIoInDvWyc196q+ipI7R3dI81VK5Z0szPrF+SJoPFbDl3Po115el/f7YJxmymOEHYSe7evo/bvvwQkPzKXtxSnzakpe/z0vfWBpbMaxhrcFvSkvRRr5uhxtnuvkF+nNYKRmsIh3sHAWhpqOVZaxbxlhefz5VrFnPF2kUsa22ckbjM5hInCDvJ/U8eZvG8et72kgvo6hmkK+2r3dUzwEOHj9DVM0B3X+GuepA8STvaLW9xS9JwN/q+ZNzykpYG5jVM/U9weCR45OncWDJ4YN8RHus8RkTSH37jilZedvFKrkhvFW1cMb8qHqIyKzUnCDtJJtvNpasWcvOLLphwn8HhEQ73DNDVmzzh2dU7MPbAz+HepA/44Z4B9nX1Jr/sewYm7JPeVF+T1ERGu/zNO1Fj6RkYZudTR/jx/iNjT+IuaWngyjWLuP5Z53Hl2sVcvmbhrOiyaTYbOUHYmKHhER55+hg3vWD9pPvV19awYkETK4p86Cki6O4bGquJdKUJZPTp0bGaSu8gjx88NvYEaV2NuOS8BfzKc1Zz5drFXLl2EWuXzJs17SJms50ThI154lAPA0MjbF45f1rPK5144GnDspaijukbHEaibA3JZuYEYXnaO3IAbF55hk8WTSOP8GlWfp5RzsZkst3U1YgLVhT3K9/M5jYnCBuT6chxwfJW39YxM8AJwvJksjk2nzu97Q9mNns5QRgAR48PcuDI8YpofzCzyuAEYQDszqYN1K5BmFnKCcIA2J3tBmCLaxBmlnKCMADaszkWzavnnAUes8jMEk4QBkCmo5vNK+f7KWUzG+MEYYyMBLuzOTdQm9lJnCCM/YeP0zMwPO1DbJjZ7OYEYbSnDdSbz3UNwsxOKGmCkHStpN2S9ki6tcD2v5S0M309IulI3rbhvG3bShlntct05JBg0zmt5Q7FzCpIyQbrk1QL3AFcA+wHtkvaFhG7RveJiHfl7f8O4Mq8UxyPiCtKFZ+dkMl2s35pS1GT95hZ9ShlDeIqYE9E7I2IAeBu4PpJ9r8B+HwJ47EJZLI5tz+Y2SlKmSBWAfvy1venZaeQtA7YAHwjr7hJ0g5JP5D06gmOuzndZ0dnZ+c0hV1degeGeOJQj3swmdkpKqWReitwT0QM55Wti4g24EbgI5JOmQMzIu6MiLaIaFu+fPlMxTqnPPJ0Mrezh9gws/FKmSAOAGvy1lenZYVsZdztpYg4kL7vBb7Fye0TNk0yHR5iw8wKK2WC2A5slLRBUgNJEjilN5KkzcBi4D/zyhZLakyXlwFXA7vGH2tnL5PN0dJQy+rFzeUOxcwqTMm6rUTEkKRbgPuAWuCuiHhY0u3AjogYTRZbgbsjIvIO3wL8raQRkiT2ofzeTzZ92ju6uWjlfGpqPMSGmZ2spP0aI+Je4N5xZe8bt/7+Asd9H7islLEZRASZbI5fuvzccodiZhWoUhqprQyy3X0cPT7IFndxNbMCnCCqWKZjdJIgN1Cb2amcIKrY6BhMF7kGYWYFOEFUsUxHjlWLmlnQVF/uUMysAjlBVLFMtpstfkDOzCbgBFGl+oeGeazTQ2yY2cScIKrUnmeOMTwSHmLDzCbkBFGlxnowuQZhZhNwgqhSmWw3jXU1rF86r9yhmFmFcoKoUplsjk3nzKeu1v8EzKwwXx2qVHuHJwkys8k5QVShzlw/B4/1+wlqM5uUE0QV2p1NGqg9BpOZTcYJogplPMSGmRXBCaIKtXfkWDG/kaWtjeUOxcwqmBNEFcpku93+YGZTcoKoMkPDIzz69DG3P5jZlJwgqszjB3sYGB7xEBtmNiUniCrTnvUQG2ZWnJImCEnXStotaY+kWwts/0tJO9PXI5KO5G17k6RH09ebShlnNcl0dFNXIy5Y3lruUMyswtWV6sSSaoE7gGuA/cB2SdsiYtfoPhHxrrz93wFcmS4vAf4QaAMCuD899nCp4q0WmWyOC1e00lDnyqOZTa6UV4mrgD0RsTciBoC7gesn2f8G4PPp8suBr0dEV5oUvg5cW8JYq0amo9tDbJhZUUqZIFYB+/LW96dlp5C0DtgAfON0jpV0s6QdknZ0dnZOS9Bz2dHeQX56tM9dXM2sKJVyn2ErcE9EDJ/OQRFxZ0S0RUTb8uXLSxTa3DH6BLVrEGZWjFImiAPAmrz11WlZIVs5cXvpdI+1ImVGx2ByDcLMilDKBLEd2Chpg6QGkiSwbfxOkjYDi4H/zCu+D3iZpMWSFgMvS8vsLGSy3SyeV8+K+R5iw8ymVrJeTBExJOkWkgt7LXBXRDws6XZgR0SMJoutwN0REXnHdkn6AEmSAbg9IrpKFWu1yGRzbF65AEnlDsXMZoGSJQiAiLgXuHdc2fvGrb9/gmPvAu4qWXBVZmQk2J3N8as/s2bqnc3MqJxGaiuxfYd76R0YdgO1mRXNCaJKtHd4iA0zOz1OEFUik+1Ggk3nuAZhZsVxgqgSmY4cG5a20NxQW+5QzGyWcIKoEskkQa49mFnxJuzFJOk1RRzfl/ZUsgrW0z/Ek129vObZq8sdipnNIpN1c/048E/AZJ3mX8S4bqxWeR55OkeEh9gws9MzWYL4l4j4jckOlvSZaY7HSsBDbJjZmZiwDSIi3jDVwcXsY+WX6eimtbGOVYuayx2Kmc0iRTdSS7pQ0mckfUnS80sZlE2v9myOi1bOp6bGQ2yYWfEma6Ruioi+vKIPAO9Nl78KXFHCuGyaRASZjm5e9azzyh2Kmc0yk9UgvirpjXnrg8B6YB1wWvM2WPl0HO2ju2/IkwSZ2WmbLEFcCyyQ9DVJLwJ+j2Qq0F8Gfm0mgrOzNzpJ0Bb3YDKz0zThLaZ0drePSfp74H8BbwP+ICIem6ng7OyNjsG0yQnCzE7TZG0QzwXeAwwAHwSOA38s6QDwgYg4MiMR2lnJZHOsXtzMgqb6codiZrPMZM9B/C3wCqAV+GREXA1slfRi4Askt5uswmU6uj2Cq5mdkcnaIIY40Sg9MFoYEd+OCCeHWaBvcJi9B3vY4jGYzOwMTFaDuBF4C0lyeOMk+1mF2vPMMYZHwjUIMzsjkzVSPwL87gzGYtNsdIgNj+JqZmdiwltMkv55qoOn2kfStZJ2S9oj6dYJ9nm9pF2SHpb0ubzyYUk709e2qWKxU2U6ummsq2H90pZyh2Jms9Bkt5h+dooLs4CLJ9wo1QJ3ANcA+4HtkrZFxK68fTYCtwFXR8RhSSvyTnE8Iq4o4m+wCWTSITZqPcSGmZ2ByRLE9UUcPzDJtquAPRGxF0DS3ek5d+Xt81vAHRFxGCAininiM61ImWw3P795xdQ7mpkVMFkbxLfP8tyrgH156/uB547bZxOApO8BtcD7I+Jr6bYmSTtIelN9KCK+Mv4DJN0M3Aywdu3aswx3bunM9XPw2IAbqM3sjE1Wg5ipz98IvARYDXxH0mXpQ3jrIuKApPOBb0h6aPxT3BFxJ3AnQFtbW8xo5BVudIgNN1Cb2Zkq5ZzUB4A1eeur07J8+4FtETEYEY8Dj5AkDCLiQPq+F/gWcGUJY51zMukQG65BmNmZmjJBSHqVpDNJJNuBjZI2SGoAtgLjG72/QlJ7QNIykltOeyUtltSYV341J7dd2BTas92cs6CRJS0N5Q7FzGapYi78vwo8KulPJW0u9sQRMQTcAtwHtANfjIiHJd0u6bp0t/uAQ5J2Ad8E3hMRh4AtwA5JP07LP5Tf+8mmlunIufZgZmdlyjaIiHiDpAXADcCnJAXwSeDzEZGb4th7gXvHlb0vbzmAd6ev/H2+D1xW7B9hJxscHmHPM8d44aZl5Q7FzGaxom4dRUQ3cA9wN3AuyZwQP5L0jhLGZmfo8YM9DAyPsMU1CDM7C8W0QVwn6R9JGorrgasi4heBZ+GhOCpSe4d7MJnZ2Summ+trgb+MiO/kF0ZEr6TfLE1YdjYy2Rz1teL8Za3lDsXMZrFiEsT7gY7RFUnNwDkR8URE/HupArMzl+no5oLlrTTUlbIXs5nNdcVcQf4BGMlbH07LrEJlsjm2nOv2BzM7O8UkiLqIyJ8waABw5/oKdaR3gI6jfWz2HNRmdpaKSRCdec8tIOl64GDpQrKzcWIOCNcgzOzsFNMG8Vbgs5I+RjLE9z48w1zFyqQ9mLa4BmFmZ6mYB+UeA54nqTVdP1byqOyMZbI5lrQ0sHx+Y7lDMbNZrqjRXCX9EnAJyRDcAETE7SWMy85QezbH5pXzGf3vZGZ2pop5UO5vSMZjegfJLaZfAdaVOC47AyMjwSNZj8FkZtOjmEbqF0TEG4HDEfFHwPNJJ/qxyvJUVy/HB4f9BLWZTYtiEkRf+t4r6TxgkGQ8JqswY5MEuYHazKZBMW0QX5W0CPgz4EdAAB8vZVB2Zto7ctQINq5wgjCzszdpgkgnCvr3dArQL0n6Z6ApIo7ORHB2ejLZbtYva6G5obbcoZjZHDDpLaaIGAHuyFvvd3KoXJlszkN8m9m0KaYN4t8lvVbuN1nRevqHePJQr9sfzGzaFJMg3kIyOF+/pG5JOUndJY7LTtPupz3EhplNr2KepPZP0lkg05EmCNcgzGyaFPOg3IsKvYo5uaRrJe2WtEfSrRPs83pJuyQ9LOlzeeVvkvRo+npT8X9Sdcpku2ltrGP14uZyh2Jmc0Qx3Vzfk7fcBFwF3A/8/GQHSaolaeC+BtgPbJe0LSJ25e2zEbgNuDoiDktakZYvAf4QaCPpVnt/euzhov+yKpPp8BAbZja9pqxBRMSr8l7XAJcCxVyorwL2RMTedA6Ju4Hrx+3zW8Adoxf+iHgmLX858PWI6Eq3fR24trg/qfpEBO3Zbj9BbWbT6kzmpNwPbCliv1UkQ4PnH7dq3D6bgE2SvifpB5KuPY1jkXSzpB2SdnR2dhb9B8w1Pz3aR65vyGMwmdm0mvIWk6S/IrnNA0lCuYLkierp+vyNwEuA1cB3JF1W7MERcSdwJ0BbW1tMsfucNTYHhGsQZjaNimmD2JG3PAR8PiK+V8RxB4A1eeur07J8+4EfRsQg8LikR0gSxgGSpJF/7LeK+MyqNDqL3KZznCDMbPoUkyDuAfoiYhiSxmdJ8yKid4rjtgMbJW0gueBvBW4ct89XgBuAT0paRnLLaS/wGPBBSYvT/V5G0phtBbR3dLNmSTPzm+rLHYqZzSFFPUkN5PedbAb+baqDImIIuAW4D2gHvhgRD0u6PW+O6/uAQ5J2Ad8E3hMRhyKiC/gASZLZDtyellkBGc8BYWYlUEwNoil/mtGIOCZpXjEnj4h7gXvHlb0vbzmAd6ev8cfeBdxVzOdUs77BYfZ2HuMVl64sdyhmNscUU4PokfTs0RVJzwGOly4kOx17njnGSHiIDTObfsXUIH4H+AdJPyWZcnQlyRSkVgHaOzxJkJmVRjFjMW2XtBm4KC3anfY6sgqQyeZoqq9h3dKWcodiZnNMMWMxvR1oiYifRMRPgFZJ/730oVkxMtluLjpnPrU1HmLDzKZXMW0Qv5XOKAdAOvTFb5UsIitaRNDe4R5MZlYaxSSI2vzJgtJB+BpKF5IVq/NYP109Ax6DycxKophG6q8BX5D0t+n6W9IyK7MTc0C4BmFm06+YBPE/gJuBt6XrXwc+XrKIrGiZrHswmVnpFDPc90hE/E1EvC4iXgfsAv6q9KHZVDIdOVYuaGJxi+/4mdn0K6YGgaQrScZMej3wOPDlUgZlxWnP5tz+YGYlM2GCkLSJJCncABwEvgAoIn5uhmKzSQwOj7DnmRwv3rS83KGY2Rw1WQ0iA3wXeGVE7AGQ9K4ZicqmtLezh8Hh8BwQZlYyk7VBvAboAL4p6eOSXkoy1IZVgBMN1O7BZGalMWGCiIivRMRWYDPJUNy/A6yQ9NeSXjZD8dkE2jty1NeK85d7iA0zK41iejH1RMTnIuJVJDO7PUDS9dXKKJPt5sIV86mvPZNpxc3MpnZaV5eIOBwRd0bES0sVkBUn05Fji59/MLMS8s/PWehwzwDZ7j53cTWzknKCmIUyWQ+xYWal5wQxC431YHINwsxKqKQJQtK1knZL2iPp1gLbb5LUKWln+npz3rbhvPJtpYxztsl05Fja0sDy1sZyh2Jmc1hRQ22ciXRY8DuAa4D9wHZJ2yJi17hdvxARtxQ4xfGIuKJU8c1mmWw3m8+dT94o7GZm066UNYirgD0RsTciBoC7getL+HlVYXgk2P20Jwkys9IrZYJYBezLW9+flo33WkkPSrpH0pq88iZJOyT9QNKrC32ApJvTfXZ0dnZOX+QV7MlDPfQNjniIbzMruXI3Un8VWB8Rl5PMM/HpvG3rIqINuBH4iKQLxh+cPpPRFhFty5dXx6B1u9MeTFvOdQ3CzEqrlAniAJBfI1idlo2JiEMR0Z+ufgJ4Tt62A+n7XuBbwJUljHXWaM/mqBFcuKK13KGY2RxXygSxHdgoaYOkBmArcFJvJEnn5q1eB7Sn5YslNabLy4CrSSYqqnqZjm42LGuhqb623KGY2RxXsl5METEk6RbgPqAWuCsiHpZ0O7AjIrYBvy3pOmAI6AJuSg/fAvytpBGSJPahAr2fqlImm+Oy1QvLHYaZVYGSJQiAiLgXuHdc2fvylm8Dbitw3PeBy0oZ22x0rH+Ip7p6eX3b6nKHYmZVoNyN1HYadnuIDTObQU4Qs4iH2DCzmeQEMYtkOnLMb6xj1aLmcodiZlXACWIW8RAbZjaTnCBmiYgg0+EhNsxs5jhBzBIHjhwn1z/k9gczmzFOELNEpsM9mMxsZjlBzBKjPZgu8iB9ZjZDnCBmifZsjrVL5tHaWNJnG83MxjhBzBKZjm4P8W1mM8oJYhboGxzm8YM9bPYQ32Y2g5wgZoFHnz7GSMAW1yDMbAY5QcwC7WNDbLgGYWYzxwliFsh05Giur2XtknnlDsXMqogTxCyQyXazaeV8ams8xIaZzRwniAoXEbR3dLv9wcxmnBNEhevM9XO4d9BdXM1sxjlBVLj20UmC3EBtZjPMCaLCZTrSHkyuQZjZDCtpgpB0raTdkvZIurXA9pskdUramb7enLftTZIeTV9vKmWclSyTzXHuwiYWzWsodyhmVmVKNrCPpFrgDuAaYD+wXdK2iNg1btcvRMQt445dAvwh0AYEcH967OFSxVup2j3EhpmVSSlrEFcBeyJib0QMAHcD1xd57MuBr0dEV5oUvg5cW6I4K9bA0AiPdR5z+4OZlUUpE8QqYF/e+v60bLzXSnpQ0j2S1pzOsZJulrRD0o7Ozs7pirti7D14jMHhcA3CzMqi3I3UXwXWR8TlJLWET5/OwRFxZ0S0RUTb8uXLSxJgOY1OErTFNQgzK4NSJogDwJq89dVp2ZiIOBQR/enqJ4DnFHtsNWjPdtNQW8OGZS3lDsXMqlApE8R2YKOkDZIagK3AtvwdJJ2bt3od0J4u3we8TNJiSYuBl6VlVSXTkePCFa3U15a7omdm1ahkvZgiYkjSLSQX9lrgroh4WNLtwI6I2Ab8tqTrgCGgC7gpPbZL0gdIkgzA7RHRVapYK1Um283VFy4rdxhmVqVKOn9lRNwL3Duu7H15y7cBt01w7F3AXaWMr5J19QzwdHc/W1a6/cHMysP3LipUZmwOCPdgMrPycIKoUKM9mDa7BmFmZeIEUaEy2W6WtTawfH5juUMxsyrlBFGhMtmcaw9mVlZOEBVoeCTYnc35CWozKysniAr0xKEe+odGPAaTmZWVE0QFOtFA7RqEmZWPE0QFymS7qa0RF65oLXcoZlbFnCAqUCab4/xlLTTV15Y7FDOrYk4QFSiT7eYi314yszJzgqgwub5B9nUd9xDfZlZ2ThAV5pGn3UBtZpXBCaLCtI/2YHINwszKzAmiwmSy3cxvquO8hU3lDsXMqpwTRIXJdOTYsnIBksodiplVOSeIChIRyRhMHuLbzCqAE0QF2X/4OMf6hzxIn5lVBCeICpLJjjZQuwZhZuXnBFFBMh3JLHIXneMEYWblV9IEIelaSbsl7ZF06yT7vVZSSGpL19dLOi5pZ/r6m1LGWSky2Rzrls6jpbGkU4WbmRWlZFciSbXAHcA1wH5gu6RtEbFr3H7zgXcCPxx3isci4opSxVeJ2rPdfkDOzCpGKX+qXgXsiYi9AJLuBq4Hdo3b7wPAnwDvKWEsExoeCQ4e60eCGil9gdL30bIT2xlbn86uqMcHhnniYA+vuvy8aTunmdnZKGWCWAXsy1vfDzw3fwdJzwbWRMT/kzQ+QWyQ9ADQDfxBRHy3FEEe6R3guR/89zM6Nj9pTJ1Q8ren+9ec2H9oZISRgC1uoDazClG2m92SaoAPAzcV2NwBrI2IQ5KeA3xF0iUR0T3uHDcDNwOsXbv2jOJoaazjg798GSMRRAQjASPpe7J+oiwCRkby14vYP68sIhgZOXX/4XS/521YytUXLjujv8PMbLqVMkEcANbkra9Oy0bNBy4FvpXeqlkJbJN0XUTsAPoBIuJ+SY8Bm4Ad+R8QEXcCdwK0tbXFmQTZVF/Ljc89s+RiZjaXlbIX03Zgo6QNkhqArcC20Y0RcTQilkXE+ohYD/wAuC4idkhanjZyI+l8YCOwt4SxmpnZOCWrQUTEkKRbgPuAWuCuiHhY0u3AjojYNsnhLwJulzQIjABvjYiuUsVqZmanUsQZ3ZmpOG1tbbFjx46pdzQzszGS7o+ItkLb/CS1mZkV5ARhZmYFOUGYmVlBThBmZlaQE4SZmRU0Z3oxSeoEnjyLUywDDk5TOLOdv4uT+fs4mb+PE+bCd7EuIpYX2jBnEsTZkrRjoq5e1cbfxcn8fZzM38cJc/278C0mMzMryAnCzMwKcoI44c5yB1BB/F2czN/Hyfx9nDCnvwu3QZiZWUGuQZiZWUFOEGZmVlDVJwhJ10raLWmPpFvLHU85SVoj6ZuSdkl6WNI7yx1TuUmqlfSApH8udyzlJmmRpHskZSS1S3p+uWMqJ0nvSv8/+Ymkz0tqKndM062qE0Q6KdEdwC8CFwM3SLq4vFGV1RDwuxFxMfA84O1V/n0AvBNoL3cQFeKjwNciYjPwLKr4e5G0CvhtoC0iLiWZ82ZreaOaflWdIICrgD0RsTciBoC7gevLHFPZRERHRPwoXc6RXABWlTeq8pG0Gvgl4BPljqXcJC0kmcjr7wAiYiAijpQ1qPKrA5ol1QHzgJ+WOZ5pV+0JYhWwL299P1V8QcwnaT1wJfDDModSTh8B3ksyq2G12wB0Ap9Mb7l9QlJLuYMql4g4APw58BTQARyNiH8tb1TTr9oThBUgqRX4EvA7EdFd7njKQdIrgWci4v5yx1Ih6oBnA38dEVcCPUDVttlJWkxyt2EDcB7QIukN5Y1q+lV7gjgArMlbX52WVS1J9STJ4bMR8eVyx1NGVwPXSXqC5Nbjz0v6THlDKqv9wP6IGK1R3kOSMKrVLwCPR0RnRAwCXwZeUOaYpl21J4jtwEZJGyQ1kDQybStzTGUjSST3mNsj4sPljqecIuK2iFgdEetJ/l18IyLm3C/EYkVEFtgn6aK06KXArjKGVG5PAc+TNC/9/+alzMFG+7pyB1BOETEk6RbgPpJeCHdFxMNlDqucrgZ+HXhI0s607Pcj4t7yhWQV5B3AZ9MfU3uB/1bmeMomIn4o6R7gRyS9/x5gDg674aE2zMysoGq/xWRmZhNwgjAzs4KcIMzMrCAnCDMzK8gJwszMCnKCMEtJOpa+r5d04zSf+/fHrX9/Os9vVgpOEGanWg+cVoJIB2ybzEkJIiLm3FO3Nvc4QZid6kPACyXtTMf8r5X0Z5K2S3pQ0lsAJL1E0nclbSN9qljSVyTdn84TcHNa9iGSUT93SvpsWjZaW1F67p9IekjSr+ad+1t58y98Nn1iF0kfSufseFDSn8/4t2NVo6qfpDabwK3A70XEKwHSC/3RiPgZSY3A9ySNjtz5bODSiHg8Xf+NiOiS1Axsl/SliLhV0i0RcUWBz3oNcAXJ/ArL0mO+k267EriEZBjp7wFXS2oHfhnYHBEhadH0/ulmJ7gGYTa1lwFvTIcf+SGwFNiYbvuvvOQA8NuSfgz8gGQgyI1M7meBz0fEcEQ8DXwb+Jm8c++PiBFgJ8mtr6NAH/B3kl4D9J7l32Y2IScIs6kJeEdEXJG+NuSN/d8ztpP0EpJRPp8fEc8iGZ/nbKah7M9bHgbqImKIZKKre4BXAl87i/ObTcoJwuxUOWB+3vp9wNvSodCRtGmCyXIWAocjolfSZpJpW0cNjh4/zneBX03bOZaTzNr2XxMFls7VsTAdQPFdJLemzErCbRBmp3oQGE5vFX2KZC7m9cCP0obiTuDVBY77GvDWtJ1gN8ltplF3Ag9K+lFE/Fpe+T8Czwd+DATw3ojIpgmmkPnAP0lqIqnZvPuM/kKzIng0VzMzK8i3mMzMrCAnCDMzK8gJwszMCnKCMDOzgpwgzMysICcIMzMryAnCzMwK+v9dS7Ovcb84WwAAAABJRU5ErkJggg==\n",
+      "image/png": "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\n",
       "text/plain": [
        "<Figure size 432x288 with 1 Axes>"
       ]
@@ -501,16 +505,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "0.798340863819657"
+       "0.8091021716950881"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 16,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -521,7 +525,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -540,7 +544,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [
     {
@@ -549,7 +553,7 @@
        "<All keys matched successfully>"
       ]
      },
-     "execution_count": 17,
+     "execution_count": 18,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -557,6 +561,10 @@
    "source": [
     "import torch\n",
     "\n",
+    "# Make sure the model is on CPU before loading a pretrained state_dict\n",
+    "model = model.cpu()\n",
+    "\n",
+    "# Load pretrained weights\n",
     "trained_state_dict = torch.load(\"state_dict.pth\")[\"models_state_dict\"][0]\n",
     "\n",
     "model.load_state_dict(trained_state_dict, strict=False)"
@@ -564,7 +572,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 19,
    "metadata": {
     "scrolled": true
    },
@@ -575,12 +583,16 @@
        "0.9188772287810328"
       ]
      },
-     "execution_count": 18,
+     "execution_count": 19,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "# Move the model back to it's target device\n",
+    "model.to(device)\n",
+    "\n",
+    "# Test for accuracy\n",
     "test(model, test_quantized_loader)"
    ]
   },
@@ -600,6 +612,16 @@
     "Sometimes, it's desirable to make some changes to our trained network prior to export (this is known in general as \"network surgery\"). This depends on the model and is not generally necessary, but in this case we want to make a couple of changes to get better results with FINN."
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Move the model to CPU before surgery\n",
+    "model = model.cpu()"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -609,7 +631,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [
     {
@@ -618,7 +640,7 @@
        "(64, 593)"
       ]
      },
-     "execution_count": 19,
+     "execution_count": 21,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -634,7 +656,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [
     {
@@ -643,7 +665,7 @@
        "(64, 600)"
       ]
      },
-     "execution_count": 20,
+     "execution_count": 22,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -658,7 +680,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [
     {
@@ -667,7 +689,7 @@
        "torch.Size([64, 600])"
       ]
      },
-     "execution_count": 21,
+     "execution_count": 23,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -690,11 +712,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "from brevitas.core.quant import QuantType\n",
     "from brevitas.nn import QuantIdentity\n",
     "\n",
     "\n",
@@ -702,23 +723,27 @@
     "    def __init__(self, my_pretrained_model):\n",
     "        super(CybSecMLPForExport, self).__init__()\n",
     "        self.pretrained = my_pretrained_model\n",
-    "        self.qnt_output = QuantIdentity(quant_type=QuantType.BINARY, bit_width=1, min_val=-1.0, max_val=1.0)\n",
+    "        self.qnt_output = QuantIdentity(\n",
+    "            quant_type='binary', \n",
+    "            scaling_impl_type='const',\n",
+    "            bit_width=1, min_val=-1.0, max_val=1.0)\n",
     "    \n",
     "    def forward(self, x):\n",
     "        # assume x contains bipolar {-1,1} elems\n",
     "        # shift from {-1,1} -> {0,1} since that is the\n",
     "        # input range for the trained network\n",
-    "        x = (x + torch.tensor([1.0])) / 2.0  \n",
+    "        x = (x + torch.tensor([1.0]).to(x.device)) / 2.0  \n",
     "        out_original = self.pretrained(x)\n",
     "        out_final = self.qnt_output(out_original)   # output as {-1,1}     \n",
     "        return out_final\n",
     "\n",
-    "model_for_export = CybSecMLPForExport(modified_model)"
+    "model_for_export = CybSecMLPForExport(modified_model)\n",
+    "model_for_export.to(device)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -731,16 +756,17 @@
     "    with torch.no_grad():\n",
     "        for data in test_loader:\n",
     "            inputs, target = data\n",
+    "            inputs, target = inputs.to(device), target.to(device)\n",
     "            # pad inputs to 600 elements\n",
-    "            input_padded = np.pad(inputs, [(0,0), (0,7)])\n",
+    "            input_padded = torch.nn.functional.pad(inputs, (0,7,0,0))\n",
     "            # convert inputs to {-1,+1}\n",
-    "            input_scaled = 2*input_padded - 1\n",
+    "            input_scaled = 2 * input_padded - 1\n",
     "            # run the model\n",
-    "            output = model(torch.from_numpy(input_scaled).float())\n",
-    "            y_pred.extend(list(output.flatten()))\n",
+    "            output = model(input_scaled.float())\n",
+    "            y_pred.extend(list(output.flatten().cpu().numpy()))\n",
     "            # make targets bipolar {-1,+1}\n",
-    "            expected = 2*target.float() - 1\n",
-    "            expected = expected.detach().numpy()\n",
+    "            expected = 2 * target.float() - 1\n",
+    "            expected = expected.cpu().numpy()\n",
     "            y_true.extend(list(expected.flatten()))\n",
     "        \n",
     "    return accuracy_score(y_true, y_pred)"
@@ -748,7 +774,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 26,
    "metadata": {},
    "outputs": [
     {
@@ -757,7 +783,7 @@
        "0.9188772287810328"
       ]
      },
-     "execution_count": 24,
+     "execution_count": 26,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -780,7 +806,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 27,
    "metadata": {
     "scrolled": true
    },
@@ -791,16 +817,6 @@
      "text": [
       "Model saved to cybsec-mlp-ready.onnx\n"
      ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "<ipython-input-22-78c27bb59095>:15: TracerWarning: torch.tensor results are registered as constants in the trace. You can safely ignore this warning if you use this function to create tensors out of constant variables that would be the same every time you call this function. In any other case, this might cause the trace to be incorrect.\n",
-      "  x = (x + torch.tensor([1.0])) / 2.0\n",
-      "/workspace/brevitas/src/brevitas/quant_tensor/__init__.py:74: TracerWarning: torch.tensor results are registered as constants in the trace. You can safely ignore this warning if you use this function to create tensors out of constant variables that would be the same every time you call this function. In any other case, this might cause the trace to be incorrect.\n",
-      "  training = torch.tensor(training, dtype=torch.bool)\n"
-     ]
     }
    ],
    "source": [
@@ -809,6 +825,7 @@
     "\n",
     "ready_model_filename = \"cybsec-mlp-ready.onnx\"\n",
     "input_shape = (1, 600)\n",
+    "\n",
     "# create a QuantTensor instance to mark input as bipolar during export\n",
     "input_a = np.random.randint(0, 1, size=input_shape).astype(np.float32)\n",
     "input_a = 2 * input_a - 1\n",
@@ -818,6 +835,10 @@
     "    input_t, scale=torch.tensor(scale), bit_width=torch.tensor(1.0), signed=True\n",
     ")\n",
     "\n",
+    "#Move to CPU before export\n",
+    "model_for_export.cpu()\n",
+    "\n",
+    "# Export to ONNX\n",
     "bo.export_finn_onnx(\n",
     "    model_for_export, export_path=ready_model_filename, input_t=input_qt\n",
     ")\n",
@@ -843,38 +864,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Serving 'cybsec-mlp-ready.onnx' at http://0.0.0.0:8081\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "\n",
-       "        <iframe\n",
-       "            width=\"100%\"\n",
-       "            height=\"400\"\n",
-       "            src=\"http://localhost:8081/\"\n",
-       "            frameborder=\"0\"\n",
-       "            allowfullscreen\n",
-       "        ></iframe>\n",
-       "        "
-      ],
-      "text/plain": [
-       "<IPython.lib.display.IFrame at 0x7fb36398c3a0>"
-      ]
-     },
-     "execution_count": 26,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "from finn.util.visualization import showInNetron\n",
     "\n",
@@ -888,18 +880,11 @@
     "## That's it! <a id=\"thats_it\" ></a>\n",
     "You created, trained and tested a quantized MLP that is ready to be loaded into FINN, congratulations! You can now proceed to the next notebook."
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -913,7 +898,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.5"
+   "version": "3.7.0"
   }
  },
  "nbformat": 4,
diff --git a/requirements.txt b/requirements.txt
index da0ec0b63092f0618bb7c9982b95fa90e8f91118..87386cfbbd03393c8b5936f5510b86c8cf25557f 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -8,7 +8,7 @@ numpy==1.18.0
 onnx==1.7.0
 onnxoptimizer
 onnxruntime==1.4.0
-pre-commit==2.6.0
+pre-commit==2.9.2
 pyscaffold==3.2.1
 scipy==1.5.2
 setupext-janitor>=1.1.2
diff --git a/src/finn/builder/build_dataflow_config.py b/src/finn/builder/build_dataflow_config.py
index 698f050cc25937684f935d78fb8eb05da4662049..6abac895a9ba647d3fd3733fda4b337f3b05dca6 100644
--- a/src/finn/builder/build_dataflow_config.py
+++ b/src/finn/builder/build_dataflow_config.py
@@ -342,7 +342,7 @@ class DataflowBuildConfig:
         if self.target_fps is None:
             return None
         else:
-            n_clock_cycles_per_sec = 10 ** 9 / self.synth_clk_period_ns
+            n_clock_cycles_per_sec = 10**9 / self.synth_clk_period_ns
             n_cycles_per_frame = n_clock_cycles_per_sec / self.target_fps
             return int(n_cycles_per_frame)
 
diff --git a/src/finn/builder/build_dataflow_steps.py b/src/finn/builder/build_dataflow_steps.py
index e81f99413179cbf57e52b1cc05cacbf36f508657..85f150dcf83972a0d14cef959235965b5cf30fe6 100644
--- a/src/finn/builder/build_dataflow_steps.py
+++ b/src/finn/builder/build_dataflow_steps.py
@@ -405,7 +405,7 @@ def step_generate_estimate_reports(model: ModelWrapper, cfg: DataflowBuildConfig
         model = model.transform(AnnotateCycles())
         estimate_network_performance = model.analysis(dataflow_performance)
         # add some more metrics to estimated performance
-        n_clock_cycles_per_sec = (10 ** 9) / cfg.synth_clk_period_ns
+        n_clock_cycles_per_sec = (10**9) / cfg.synth_clk_period_ns
         est_fps = n_clock_cycles_per_sec / estimate_network_performance["max_cycles"]
         estimate_network_performance["estimated_throughput_fps"] = est_fps
         est_latency_ns = (
@@ -607,7 +607,7 @@ def step_out_of_context_synthesis(model: ModelWrapper, cfg: DataflowBuildConfig)
 
         estimate_network_performance = model.analysis(dataflow_performance)
         # add some more metrics to estimated performance
-        n_clock_cycles_per_sec = float(ooc_res_dict["fmax_mhz"]) * (10 ** 6)
+        n_clock_cycles_per_sec = float(ooc_res_dict["fmax_mhz"]) * (10**6)
         est_fps = n_clock_cycles_per_sec / estimate_network_performance["max_cycles"]
         ooc_res_dict["estimated_throughput_fps"] = est_fps
         with open(report_dir + "/ooc_synth_and_timing.json", "w") as f:
diff --git a/src/finn/custom_op/fpgadataflow/streamingfclayer_batch.py b/src/finn/custom_op/fpgadataflow/streamingfclayer_batch.py
index 8ca3787232fc22ae6cf798edc8552fd257fdcc2f..3f4103b4380f8d1838910b37e966e8363891d39f 100644
--- a/src/finn/custom_op/fpgadataflow/streamingfclayer_batch.py
+++ b/src/finn/custom_op/fpgadataflow/streamingfclayer_batch.py
@@ -358,8 +358,8 @@ class StreamingFCLayer_Batch(HLSCustomOp):
         if noact == 0:
             odt = self.get_output_datatype()
             B = odt.bitwidth()
-            thr_luts = (2 ** B - 1) * acc_bits * math.ceil(self.calc_tmem() / 64)
-            comp_luts = (2 ** B - 1) * acc_bits
+            thr_luts = (2**B - 1) * acc_bits * math.ceil(self.calc_tmem() / 64)
+            comp_luts = (2**B - 1) * acc_bits
 
         return int(
             c0
diff --git a/src/finn/custom_op/fpgadataflow/vector_vector_activate_batch.py b/src/finn/custom_op/fpgadataflow/vector_vector_activate_batch.py
index e9a212a588d90bfd72ef0487c4137eda912ca701..3d8dcaf2fca52b6c23b10322e0061b580807e0bc 100644
--- a/src/finn/custom_op/fpgadataflow/vector_vector_activate_batch.py
+++ b/src/finn/custom_op/fpgadataflow/vector_vector_activate_batch.py
@@ -698,8 +698,8 @@ class Vector_Vector_Activate_Batch(HLSCustomOp):
         if noact == 0:
             odt = self.get_output_datatype()
             B = odt.bitwidth()
-            thr_luts = (2 ** B - 1) * acc_bits * math.ceil(self.calc_tmem() / 64)
-            comp_luts = (2 ** B - 1) * acc_bits
+            thr_luts = (2**B - 1) * acc_bits * math.ceil(self.calc_tmem() / 64)
+            comp_luts = (2**B - 1) * acc_bits
 
         return int(c0 + c1 * (P * (mult_luts + acc_luts + thr_luts + comp_luts)) + c2)
 
diff --git a/src/finn/transformation/fpgadataflow/set_fifo_depths.py b/src/finn/transformation/fpgadataflow/set_fifo_depths.py
index 39eb049565475b462ea0df9d88b46e3598e6cdd9..ce7cf7bc589fae7fb6c8785b51cf45514f49c5a0 100644
--- a/src/finn/transformation/fpgadataflow/set_fifo_depths.py
+++ b/src/finn/transformation/fpgadataflow/set_fifo_depths.py
@@ -222,7 +222,7 @@ class InsertAndSetFIFODepths(Transformation):
         fpgapart,
         clk_ns=10.0,
         max_qsrl_depth=256,
-        max_depth=2 ** 14,
+        max_depth=2**14,
         swg_exception=True,
         vivado_ram_style="auto",
     ):
diff --git a/src/finn/transformation/qonnx/infer_quant_avg_pool_2d.py b/src/finn/transformation/qonnx/infer_quant_avg_pool_2d.py
index faad31fa06e76b245f25b6f0aa583fec5c0da29a..c234bd38d9679f72b6df73e81df57fba3e8d4554 100644
--- a/src/finn/transformation/qonnx/infer_quant_avg_pool_2d.py
+++ b/src/finn/transformation/qonnx/infer_quant_avg_pool_2d.py
@@ -230,7 +230,7 @@ class AvgPoolAndTruncToQuantAvgPool(Transformation):
                         # 7c2603a95e90e4de2575020e575c24eab6a15889/src/finn/custom_op/
                         # general/quantavgpool2d.py#L94
                         ibits = math.floor(
-                            math.log(2 ** trunc_in_bits / (k_s * k_s), 2)
+                            math.log(2**trunc_in_bits / (k_s * k_s), 2)
                         )
                         # Get sign
                         signed = _get_signed_from_upstream(model, t_node)
diff --git a/src/finn/transformation/qonnx/qonnx_activation_handlers.py b/src/finn/transformation/qonnx/qonnx_activation_handlers.py
index 3336b1eee7fa9d54092cd56b9ba0edaf9d0884b1..c8bde7fea8ae8195001a7eccfd48baa4c48997ae 100644
--- a/src/finn/transformation/qonnx/qonnx_activation_handlers.py
+++ b/src/finn/transformation/qonnx/qonnx_activation_handlers.py
@@ -333,7 +333,7 @@ class QuantReluHandler(QuantActBaseHandler):
         # Calculate thersholds, see: https://github.com/Xilinx/brevitas/blob/
         # a5bfd6dc5e030f0047ac1ee47932b60e8e873e17/src/brevitas/export/
         # onnx/finn/handler/act.py#L21
-        num_distinct_values = 2 ** bit_width
+        num_distinct_values = 2**bit_width
         num_thresholds = int(num_distinct_values - 1)
         flat_scale = quant_scale.flatten().astype(np.float32)
         num_scale_channels = flat_scale.shape[0]
@@ -468,9 +468,9 @@ class QuantIdentityHandler(QuantActBaseHandler):
             return thresholds
         else:
             if narrow:
-                num_distinct_values = 2 ** bit_width - 1
+                num_distinct_values = 2**bit_width - 1
             else:
-                num_distinct_values = 2 ** bit_width
+                num_distinct_values = 2**bit_width
 
             num_thresholds = int(num_distinct_values - 1)
             flat_scale = quant_scale.flatten()
diff --git a/tests/end2end/test_end2end_bnn_pynq.py b/tests/end2end/test_end2end_bnn_pynq.py
index bc14b9dee5de0b1c0a5d05292935ab91c1dd1553..b74875e10fc8c539b7a5f3eced5f1f11df3b5f94 100644
--- a/tests/end2end/test_end2end_bnn_pynq.py
+++ b/tests/end2end/test_end2end_bnn_pynq.py
@@ -765,7 +765,7 @@ class TestEnd2End:
         ret = dict()
         # try a range of batch sizes, some may fail due to insufficient DMA
         # buffers
-        bsize_range_in = [8 ** i for i in range(5)]
+        bsize_range_in = [8**i for i in range(5)]
         bsize_range = []
         for bsize in bsize_range_in:
             res = throughput_test_remote(model, bsize)
diff --git a/tests/fpgadataflow/test_fpgadataflow_vvau.py b/tests/fpgadataflow/test_fpgadataflow_vvau.py
index 6f39994bf27594a063a1e66c5bba7867eaabef6e..9eb3a7f4514e610d79bb83cc62a7561a33ced543 100644
--- a/tests/fpgadataflow/test_fpgadataflow_vvau.py
+++ b/tests/fpgadataflow/test_fpgadataflow_vvau.py
@@ -62,8 +62,8 @@ def _infer_sparse_weight_tensor(W_conv, k_h, k_w, channels):
 def _calculate_dot_prod_range(dt_a, dt_b, len):
     """Returns the (min,max) values a dot product between two (un)signed vectors of
     types dt_a and dt_b of len elements can take."""
-    min_prod = 2 ** 30
-    max_prod = -(2 ** 30)
+    min_prod = 2**30
+    max_prod = -(2**30)
     for a_val in [dt_a.min(), dt_a.max()]:
         for b_val in [dt_b.min(), dt_b.max()]:
             prod = a_val * b_val * len
diff --git a/tests/fpgadataflow/test_set_folding.py b/tests/fpgadataflow/test_set_folding.py
index 66fd5b43a1b8b8c8986bf9c9b9d0e9efd7a744a6..492f208671f4622d189c48ece874740a68b69072 100644
--- a/tests/fpgadataflow/test_set_folding.py
+++ b/tests/fpgadataflow/test_set_folding.py
@@ -109,7 +109,7 @@ def make_multi_fclayer_model(ch, wdt, adt, tdt, nnodes):
 
 
 # desired frames per second
-@pytest.mark.parametrize("target_fps", [30, 10 ** 5, 10 ** 7])
+@pytest.mark.parametrize("target_fps", [30, 10**5, 10**7])
 # target chip or board
 @pytest.mark.parametrize("platform", ["Pynq-Z1", "Ultra96", "U200"])
 def test_set_folding(target_fps, platform):
@@ -126,7 +126,7 @@ def test_set_folding(target_fps, platform):
     dataflow_model = load_test_checkpoint_or_skip(dataflow_model_filename)
 
     clk_ns = 5
-    target_cycles_per_frame = int((10 ** 9 / clk_ns) / target_fps)
+    target_cycles_per_frame = int((10**9 / clk_ns) / target_fps)
     dataflow_model = dataflow_model.transform(SetFolding(target_cycles_per_frame))
 
     exp_cycles_dict = dataflow_model.analysis(exp_cycles_per_layer)