{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Discriminator(\n",
      "  (conv_pipe): Sequential(\n",
      "    (0): Conv2d(3, 200, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n",
      "    (1): ReLU()\n",
      "    (2): Conv2d(200, 400, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n",
      "    (3): BatchNorm2d(400, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
      "    (4): ReLU()\n",
      "    (5): Conv2d(400, 800, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n",
      "    (6): BatchNorm2d(800, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
      "    (7): ReLU()\n",
      "    (8): Conv2d(800, 1600, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n",
      "    (9): BatchNorm2d(1600, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
      "    (10): ReLU()\n",
      "    (11): Conv2d(1600, 3200, kernel_size=(8, 8), stride=(2, 2), padding=(1, 1))\n",
      "    (12): BatchNorm2d(3200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
      "    (13): ReLU()\n",
      "    (14): Conv2d(3200, 1, kernel_size=(4, 4), stride=(1, 1))\n",
      "    (15): Sigmoid()\n",
      "  )\n",
      ")\n",
      "Generator(\n",
      "  (pipe): Sequential(\n",
      "    (0): ConvTranspose2d(400, 1000, kernel_size=(6, 6), stride=(1, 1))\n",
      "    (1): BatchNorm2d(1000, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
      "    (2): ReLU()\n",
      "    (3): ConvTranspose2d(1000, 800, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n",
      "    (4): BatchNorm2d(800, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
      "    (5): ReLU()\n",
      "    (6): ConvTranspose2d(800, 600, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n",
      "    (7): BatchNorm2d(600, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
      "    (8): ReLU()\n",
      "    (9): ConvTranspose2d(600, 400, kernel_size=(6, 6), stride=(2, 2), padding=(1, 1))\n",
      "    (10): BatchNorm2d(400, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
      "    (11): ReLU()\n",
      "    (12): ConvTranspose2d(400, 200, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n",
      "    (13): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
      "    (14): ReLU()\n",
      "    (15): ConvTranspose2d(200, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n",
      "    (16): Tanh()\n",
      "  )\n",
      ")\n",
      "Iteration :  20\n",
      "INFO: Iter 20: gen_loss=9.649e+00, dis_loss=5.266e-01\n",
      "Iteration :  21\n",
      "Iteration :  22\n",
      "Iteration :  23\n",
      "Iteration :  24\n",
      "Iteration :  25\n",
      "Iteration :  26\n",
      "Iteration :  27\n",
      "Iteration :  28\n",
      "Iteration :  29\n",
      "Iteration :  30\n",
      "INFO: Iter 30: gen_loss=6.851e+00, dis_loss=1.911e-01\n",
      "Iteration :  31\n",
      "Iteration :  32\n",
      "Iteration :  33\n",
      "Iteration :  34\n",
      "Iteration :  35\n",
      "Iteration :  36\n",
      "Iteration :  37\n",
      "Iteration :  38\n",
      "Iteration :  39\n",
      "Iteration :  40\n",
      "INFO: Iter 40: gen_loss=6.467e+00, dis_loss=3.223e-01\n"
     ]
    }
   ],
   "source": [
    "!python ganSynthesisImage_200.py --load test_model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.6.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}