Spaces:
Sleeping
Sleeping
File size: 11,674 Bytes
ce91ea1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import torchvision\n",
"import pretrainedmodels\n",
"import torch\n",
"import pretrainedmodels.utils as utils\n",
"import torchvision.transforms as transforms\n",
"import torchvision.models as models\n",
"import torch.nn as nn\n",
"import torch.nn.functional as F\n",
"from PIL import Image\n",
"from collections import OrderedDict"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'imagenet': {'url': 'http://data.lip6.fr/cadene/pretrainedmodels/nasnetalarge-a1897284.pth', 'input_space': 'RGB', 'input_size': [3, 331, 331], 'input_range': [0, 1], 'mean': [0.5, 0.5, 0.5], 'std': [0.5, 0.5, 0.5], 'num_classes': 1000}, 'imagenet+background': {'url': 'http://data.lip6.fr/cadene/pretrainedmodels/nasnetalarge-a1897284.pth', 'input_space': 'RGB', 'input_size': [3, 331, 331], 'input_range': [0, 1], 'mean': [0.5, 0.5, 0.5], 'std': [0.5, 0.5, 0.5], 'num_classes': 1001}}\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Downloading: \"http://data.lip6.fr/cadene/pretrainedmodels/nasnetalarge-a1897284.pth\" to /home/dattran/.torch/models/nasnetalarge-a1897284.pth\n",
"100%|██████████| 356056626/356056626 [07:27<00:00, 795221.08it/s] \n"
]
}
],
"source": [
"print(pretrainedmodels.pretrained_settings['nasnetalarge'])\n",
"model = pretrainedmodels.__dict__['nasnetalarge'](num_classes=1000, pretrained='imagenet')"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Variable containing:\n",
"( 0 , 0 ,.,.) = \n",
" 0.1121 0.0000 0.0000 ... 0.0000 0.0000 0.0000\n",
" 0.4418 0.0000 0.0000 ... 0.0000 0.0000 0.0000\n",
" 0.0000 0.0000 0.0000 ... 0.8554 0.0000 0.0000\n",
" ... ⋱ ... \n",
" 0.0000 0.5682 0.5166 ... 0.0301 0.0000 0.0000\n",
" 0.0000 0.0921 0.2531 ... 2.0754 0.4212 0.0000\n",
" 0.0000 0.0000 0.0000 ... 1.8003 0.5220 0.0000\n",
"\n",
"( 0 , 1 ,.,.) = \n",
" 0.1536 0.1211 0.0000 ... 1.3220 0.1388 0.0000\n",
" 0.4111 0.2736 0.1038 ... 0.7770 0.0000 0.0000\n",
" 0.0000 0.0000 0.0000 ... 1.5591 0.0000 0.0000\n",
" ... ⋱ ... \n",
" 0.0000 0.0000 0.3120 ... 0.0000 0.0000 0.0000\n",
" 1.2059 0.9648 0.7537 ... 0.0000 0.0000 0.0000\n",
" 1.8497 0.5725 0.0000 ... 0.0000 0.0000 0.0000\n",
"\n",
"( 0 , 2 ,.,.) = \n",
" 0.3311 0.0000 0.0000 ... 0.0000 0.0000 0.0000\n",
" 0.0000 0.0000 0.0000 ... 0.0000 0.0000 0.0000\n",
" 0.3876 0.2232 0.1740 ... 0.0000 0.0000 0.0000\n",
" ... ⋱ ... \n",
" 0.0000 0.0000 0.3968 ... 0.0000 0.2945 0.0000\n",
" 0.4885 0.8537 1.2278 ... 0.2380 0.6205 1.0980\n",
" 2.1136 1.3682 1.5039 ... 0.9723 0.9817 0.0760\n",
" ... \n",
"\n",
"( 0 ,1533,.,.) = \n",
" 0.8787 0.9274 0.5682 ... 0.4111 0.5084 0.5470\n",
" 0.5436 0.6317 0.5634 ... 0.5417 0.3694 0.4478\n",
" 0.0000 0.3396 0.5478 ... 0.8584 0.5552 0.5867\n",
" ... ⋱ ... \n",
" 0.0000 0.0000 0.0000 ... 0.0000 0.0000 0.0000\n",
" 0.4349 0.2017 0.0000 ... 0.0000 0.0000 0.0000\n",
" 0.3743 0.3398 0.0000 ... 0.0000 0.0000 0.0000\n",
"\n",
"( 0 ,1534,.,.) = \n",
" 0.1190 0.0000 0.0000 ... 0.0000 0.0000 0.0000\n",
" 0.0259 0.0000 0.0000 ... 0.3597 0.0000 0.0000\n",
" 0.0000 0.0000 0.0000 ... 1.4928 0.0000 0.0000\n",
" ... ⋱ ... \n",
" 0.0000 0.0000 0.0000 ... 1.4441 1.2858 0.6525\n",
" 0.0000 0.1889 0.5281 ... 0.7508 0.9813 0.5251\n",
" 0.0000 0.9832 1.3777 ... 0.0639 0.2403 0.0000\n",
"\n",
"( 0 ,1535,.,.) = \n",
" 0.0000 0.1068 0.3845 ... 0.0000 0.0000 0.0000\n",
" 0.0000 0.2751 0.7059 ... 0.0000 0.0000 0.0000\n",
" 0.0000 0.0711 0.4025 ... 1.2069 1.4548 1.1041\n",
" ... ⋱ ... \n",
" 0.0000 0.0000 0.0000 ... 0.7915 0.3439 0.1936\n",
" 0.0000 0.0000 0.0000 ... 0.0000 0.0000 0.0000\n",
" 0.0275 0.0000 0.0000 ... 0.0000 0.0000 0.0000\n",
"[torch.FloatTensor of size 1x1536x8x8]"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"load_img = utils.LoadImage()\n",
"# transformations depending on the model\n",
"# rescale, center crop, normalize, and others (ex: ToBGR, ToRange255)\n",
"tf_img = utils.TransformImage(model) \n",
"\n",
"path_img = '/home/dattran/data/xray/00000013_029.png'\n",
"\n",
"input_img = load_img(path_img)\n",
"input_tensor = tf_img(input_img) # 3x400x225 -> 3x299x299 size may differ\n",
"input_tensor = input_tensor.unsqueeze(0) # 3x299x299 -> 1x3x299x299\n",
"input = torch.autograd.Variable(input_tensor,\n",
" requires_grad=False)\n",
"model.features(input)"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\u001B[0;31mInit signature:\u001B[0m \u001B[0mtorch\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mnn\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mMaxPool2d\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mkernel_size\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mstride\u001B[0m\u001B[0;34m=\u001B[0m\u001B[0;32mNone\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mpadding\u001B[0m\u001B[0;34m=\u001B[0m\u001B[0;36m0\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mdilation\u001B[0m\u001B[0;34m=\u001B[0m\u001B[0;36m1\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mreturn_indices\u001B[0m\u001B[0;34m=\u001B[0m\u001B[0;32mFalse\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mceil_mode\u001B[0m\u001B[0;34m=\u001B[0m\u001B[0;32mFalse\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
"\u001B[0;31mDocstring:\u001B[0m \n",
"Applies a 2D max pooling over an input signal composed of several input\n",
"planes.\n",
"\n",
"In the simplest case, the output value of the layer with input size :math:`(N, C, H, W)`,\n",
"output :math:`(N, C, H_{out}, W_{out})` and :attr:`kernel_size` :math:`(kH, kW)`\n",
"can be precisely described as:\n",
"\n",
".. math::\n",
"\n",
" \\begin{array}{ll}\n",
" out(N_i, C_j, h, w) = \\max_{{m}=0}^{kH-1} \\max_{{n}=0}^{kW-1}\n",
" input(N_i, C_j, stride[0] * h + m, stride[1] * w + n)\n",
" \\end{array}\n",
"\n",
"| If :attr:`padding` is non-zero, then the input is implicitly zero-padded on both sides\n",
" for :attr:`padding` number of points\n",
"| :attr:`dilation` controls the spacing between the kernel points. It is harder to describe,\n",
" but this `link`_ has a nice visualization of what :attr:`dilation` does.\n",
"\n",
"The parameters :attr:`kernel_size`, :attr:`stride`, :attr:`padding`, :attr:`dilation` can either be:\n",
"\n",
" - a single ``int`` -- in which case the same value is used for the height and width dimension\n",
" - a ``tuple`` of two ints -- in which case, the first `int` is used for the height dimension,\n",
" and the second `int` for the width dimension\n",
"\n",
"Args:\n",
" kernel_size: the size of the window to take a max over\n",
" stride: the stride of the window. Default value is :attr:`kernel_size`\n",
" padding: implicit zero padding to be added on both sides\n",
" dilation: a parameter that controls the stride of elements in the window\n",
" return_indices: if ``True``, will return the max indices along with the outputs.\n",
" Useful when Unpooling later\n",
" ceil_mode: when True, will use `ceil` instead of `floor` to compute the output shape\n",
"\n",
"Shape:\n",
" - Input: :math:`(N, C, H_{in}, W_{in})`\n",
" - Output: :math:`(N, C, H_{out}, W_{out})` where\n",
" :math:`H_{out} = floor((H_{in} + 2 * padding[0] - dilation[0] * (kernel\\_size[0] - 1) - 1) / stride[0] + 1)`\n",
" :math:`W_{out} = floor((W_{in} + 2 * padding[1] - dilation[1] * (kernel\\_size[1] - 1) - 1) / stride[1] + 1)`\n",
"\n",
"Examples::\n",
"\n",
" >>> # pool of square window of size=3, stride=2\n",
" >>> m = nn.MaxPool2d(3, stride=2)\n",
" >>> # pool of non-square window\n",
" >>> m = nn.MaxPool2d((3, 2), stride=(2, 1))\n",
" >>> input = autograd.Variable(torch.randn(20, 16, 50, 32))\n",
" >>> output = m(input)\n",
"\n",
".. _link:\n",
" https://github.com/vdumoulin/conv_arithmetic/blob/master/README.md\n",
"\u001B[0;31mFile:\u001B[0m ~/miniconda2/envs/dat/lib/python3.6/site-packages/torch/nn/modules/pooling.py\n",
"\u001B[0;31mType:\u001B[0m type\n"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"torch.nn.MaxPool2d?"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"from pretrainedmodels.models.dpn import adaptive_avgmax_pool2d"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"1000"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"x = nn.Conv2d(1000, 14,kernel_size=1, bias=True)\n",
"x.in_channels"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"False"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model.eval()\n",
"model.training"
]
},
{
"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": "3.6.4"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|