158 lines
97 KiB
Text
158 lines
97 KiB
Text
|
{
|
||
|
|
"cells": [
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 11,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"import random"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 4,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"import matplotlib.pyplot as plt"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 1,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"N90_100(\n",
|
||
|
|
" (conv1): Conv2d(1, 9, kernel_size=(3, 3), stride=(1, 1))\n",
|
||
|
|
" (conv2): Conv2d(9, 1, kernel_size=(3, 3), stride=(1, 1))\n",
|
||
|
|
")\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"from models import *"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 2,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"4\n",
|
||
|
|
"torch.Size([9, 1, 3, 3])\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"params = list(net.parameters())\n",
|
||
|
|
"print(len(params))\n",
|
||
|
|
"print(params[0].size()) # conv1's .weight\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 1,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"from dataset import *"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 2,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"a=IMPAXDataset()\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 27,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAAC7CAYAAACend6FAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjEsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy8QZhcZAAAgAElEQVR4nOy9SZBc13X3+X85D5VZVVkjABKkSGtA2LIoYaJAgANIWCJpm4rwEFZHeOuFd164wyuHo8Md/nbujTdedMS36w7bITsscACJgUABIAgCICVZ/tySRYoggBpzrpwzXy8Kv5MnkwBlWaQAO+pGIFCVlfnyvnvPPed//md4QRiG2h7bY3tsj+3x32tE7vUEtsf22B7bY3t8+mNbuW+P7bE9tsd/w7Gt3LfH9tge2+O/4dhW7ttje2yP7fHfcGwr9+2xPbbH9vhvOLaV+/bYHttje/w3HJ+Zcg+C4JtBEPxbEAQ/DoLgzz6r79ke2+OXObblenv8VxnBZ5HnHgRBVNL/J+mYpI8kXZb07TAMf/ipf9n22B6/pLEt19vjv9L4rJD7AUk/DsPwJ2EYdiT9P5Je+oy+a3tsj1/W2Jbr7fFfZnxWyn2XpOvu949uv7Y9tsd/5bEt19vjv8yI3asvDoLgjyT90e1f90YiEf833Yku+rQoJK4fBMEnXn/873caXOdO17vTtf17xu/TX+tOc+Wz/hq9Xk+RSORj3++vc6d5+dcGg4H97q8z/jmu+bPWzt/Hnd57t3W60/rf6R7G1+dur/H6YDBQGIY/ezM/pTEu2/8Rubj9uV9YxsdlcVymftbP4+t5p7nf6X3++8evNxgMJEmRSMR+vtP7eQ9yw7XH5/IflW3/eT+fMAwViURsbuiecXnlf+Z8N510t/29m8z+Z993p/fe/nfHCXxWyv2GpAfd7w/cfs1P7G8l/a0kRSKRMJPJ8PrIxo59ZuT3OwnYJyknrySDIFAikZAkdTod22A2nA3lvWEYqt/vKwgCRSIReWM0LrD+c/1+34Sa13q9nsIwVCqVUrvd1u01MKHr9XqKRqOKRCKKRqNKJpNqt9tKJpPqdDpKJpOq1Wr2XfF4XLFYDCWmSCSiTCYzIpT8GwwGikajikaj6vV6NpeJiQn1+33VajWlUilJUjKZHLnPaDSqMAxtftFoVPV6XZLU7/eVTqfV7XY1GAzU7/cVi8VsfYIgUCwWUxiG6nQ6I3MKw1DJZFL9ft/m6I1Zr9dTEAT2nfx9XDH51zm8kUhkZK1+wfEz5fr2eptsB0EQxuNxkwH2BKXCXJEt9ou5c1/+PtkLZMsrsWg0arLNWrPuyKNfp3g8rk6nY9+NHCF7nU7Hvg8g4ZU0MtHtdhWPx9XtdiXJfg7DUIlEwubq/zEvf/1EIqFut6tOp2N7zb0ju6lUymQQWfP3I8lkqdvtamJiQoPBQLVaTclkUpKEvuFemAvzD4LAzmYYhiOyzL36s8Dv7XZbQRDYvSP3zK/b7Soajdp383nkG1n3xog9Yw58NggCNZvNuwrrZ6XcL0v6fBAEn9OW8P+BpP/tkz7g0eN/dNxJqY4L+7hCZyGlUbTgF3TcWPifvdLxn2U+Xhj5O9+JouR9XuB5fXy+ktRsNtXtdnX27FkdOXJErVZLS0tLCsNQR44cUTKZtGt6xTiOoCWZ0fD/JJmil4YHIxaLmUJFyTBvjAzXC4LADiTX8/fs19BfD6OJkeH1cYPIZ/v9/sjejl/b/7vTfv6C4+eWa0kfU+zjaM/LsZ+3v9dxuRtHpf7vHpWyB+ypNOqBYVx4b6/XMwUvDeWF/eTz/szwvlgsNvI9XomhoPzcWZNer6d4PK5EIqF2uz2C9CV9bE58z/j6cPYTiYRdGyMzDrJ6vZ6SyaQpX4wghiIIAsXjcZs3ShnFnUwmbe3i8fjHzj3z5XXWz+s51nDcsPv18WeZ88lnOUd3G59Jtsztm3xB0v8lKSrp/w7D8P+823sjkUjIYrnPS/rF3Bn/dxbIW0n/tzspOSwpm8gY/ywbiCeAAmROCDfX8B4A34Uy9YfGu40I2MmTJ/XSSy+pUqmo3W4rl8uZUPZ6PZsLyGQwGKjT6ZigxOPxEe+D10Fv/X7fUGEymVQqlRLIs9ls2to1m80RQ4HQc00UPesei8XU7XbtO/ye8DlvJHn/uHIGrfm9REGwL/5QMO9+v/+p0DI/j1zffn/InL0M3U2u7wZwxsGPPx/eAxhHd3xPLBZTr9f7GBL37xsMBmawPd3X7/dNblh7FPK4V3EnQ4W8I9/j8+e6nU5H2Wx2RHb4PhC1JKVSKZPDWq1m946H4HUJc0U+WZ94PG4eL+en2+0qlUqpWq2acgaVI/uRSMQ8T7zN8X3g7HOuuD4yjSd+J2XvAd64EfPGdQzV31FoPrM89zAMXw7D8AthGD76sw4AC7O0tKSrV68qEomo1Wrp2rVrI3TI0tKSbdyZM2fMoicSCS0tLUnaUs6nT5/W0tKS+v2+rl69qqWlJTWbzZGN4R8LF4/HTVlJMus+jhoREiw6ByabzerkyZNqt9sKw1BLS0tKp9NKpVJqtVojqLjZbOrChQsmoN6FgxJB2XGouMder6fNzU1zP0+dOqWTJ0/a/Fi7EydOaHNz09aI64VhqGazqUajMXIv9Xpd6XTarpPJZBSGoTY3N7W2tqaNjQ27336/r9dee83caIQskUioWq3amqbTaQVBoHQ6rXa7rU6no06nY653u91WIpEw7yCZTKrRaIy4phgW3F5c4sFgoEwmY9dELlCifl8/TQDz88i1+4yhLI8yx726O6FzDxDGr+kVCq+12+0RRCjJFLZH+aBar1yj0aja7bba7bYpO5QS3hoDdCzJ9gBwMe4Bgqb5DPcOWkehJRKJEZqBfca4cK+dTkftdluNRmPE6ID6vSfY6/XsfHlvtdfrqdlsqlwuq9ls2me73a4ZCc4isibJrsvAWPjv9CAFQyTJQAz3g77x+xzeppZYf+b9SbJxt/GZIfefZ0QikfD2/4Yc33rrLX39619Xv9/X1NSUGo2G3nzzTT399NNmESWZQHzve9/Tr//6ryuTyajRaEiSKc9er6d3331Xhw4dssX0KM/zeJ1OZ8SF88FK5gaqkYYHNx6P6/XXX1en09GLL76oEydOGGUSBIE2NzeVTCZVr9fNcqP4UZDwgSAFL/wnT57U1772NVMIKHHmk06njWtvtVrqdrvqdrsmlLwP5Yqhm5iYMKUAssnlciqXy2q1Wpqenra/TU5OStoS6M3NTTUaDeXzeU1OTqper9thCIJAtVptBFHiHvd6PVUqFc3MzKhUKikejyubzWowGKharSqfzxsKr1QqikajmpiYUKVSUTabtcM9OTmpSqVi1BH8KGsmyZTUbYXzSwuo+hEEQXin4B3rJI2iVwywH+NKnDEeCPTI1VMC6XTalB977JUDsoESl0bjJNLQ2wQo8HeU/riS4nzxGmAEDwKjBpplXpzrdDptxh6FTQwAo+/XjTkPBgPb/zutJXKIdzoYDJTNZtVoNEa8UOaM15VKpez9rVbLvCR0BUaJ1/yahmGoVqtlRjwej9vvfo7Mzb/mZQID7WMetw3KLzWg+nOPq1evmoJ46qmnlEqldPr0aR07dkxvvvmmDhw4oCAIlMlkdOLECXU6Hf3Gb/yG2u22JicnTRkuLS2ZMBw8eFBvvfWWJOmxxx5TLBYbcTsRDv+/F0S/iF7ofTCo1+sZWpe2hPr48eN22KLRqIrFot577z0dOnRIsVhM7XZbFy5c0De+8Q1DOpcuXdJgMNDBgwclSfl8Xp1OR5VKRVeuXNFzzz1nQt1qtbRjxw6trq6OoL5EIqG1tTW9++676vV6OnDggI4fP65sNqt+v68jR44oDEPV63XFYjFdvHhRx44dU6vVUqvV0ve+9z099dRT6vf7KhQKWllZUbPZVCqVUqPRUKlUUhAEevvttxUEgfbt26dUKqVisagzZ87o4MGDyufz2tjY0NWrVw2Z7927Vw888IBWV1dtPVOplBm1YrGobDarq1ev6vDhw7YXFy9eVDqdVjwe16/
|
||
|
|
"text/plain": [
|
||
|
|
"<Figure size 432x288 with 2 Axes>"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"metadata": {
|
||
|
|
"needs_background": "light"
|
||
|
|
},
|
||
|
|
"output_type": "display_data"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"idx = random.randrange(len(a))\n",
|
||
|
|
"i1, i2 = a[idx]\n",
|
||
|
|
"\n",
|
||
|
|
"plt.subplot(1,2,1)\n",
|
||
|
|
"plt.imshow(i1, cmap='gray')\n",
|
||
|
|
"plt.subplot(1,2,2)\n",
|
||
|
|
"plt.imshow(i2, cmap='gray')\n",
|
||
|
|
"plt.show()"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 7,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"text/plain": [
|
||
|
|
"(256, 256)"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"execution_count": 7,
|
||
|
|
"metadata": {},
|
||
|
|
"output_type": "execute_result"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"plt.imshow(i2, cmap='gray')"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"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": "3.7.4"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"nbformat": 4,
|
||
|
|
"nbformat_minor": 2
|
||
|
|
}
|