{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "hidden_dim = 1024\n",
    "\n",
    "class Discriminator(torch.nn.Module):\n",
    "    def __init__(self):\n",
    "        super().__init__()\n",
    "        self.discriminator = torch.nn.Sequential(\n",
    "            torch.nn.Conv1d(hidden_dim, 128, kernel_size=4, stride=2),\n",
    "            torch.nn.SiLU(),\n",
    "            torch.nn.GroupNorm(32, 128),\n",
    "            torch.nn.Conv1d(128, 128, kernel_size=4, stride=2),\n",
    "            torch.nn.SiLU(),\n",
    "            torch.nn.GroupNorm(32, 128),\n",
    "            torch.nn.Conv1d(128, 128, kernel_size=4, stride=2),\n",
    "            torch.nn.SiLU(),\n",
    "            torch.nn.GroupNorm(32, 128),\n",
    "            torch.nn.Conv1d(128, 128, kernel_size=4, stride=2),\n",
    "            torch.nn.SiLU(),\n",
    "        )\n",
    "\n",
    "    def forward(self, x):\n",
    "        return self.discriminator(x)\n",
    "\n",
    "# count the number of parameters in the discriminator\n",
    "print(sum(p.numel() for p in discriminator.parameters()))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# create dummy innput \n",
    "bs = 4\n",
    "seq_len = 750\n",
    "\n",
    "x = torch.randn(bs, hidden_dim, seq_len)\n",
    "\n",
    "out = discriminator(x)\n",
    "\n",
    "print(out.shape)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "suno_env",
   "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": "3.10.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}