File size: 16,393 Bytes
6f8f7d3 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"请点击[此处](https://ai.baidu.com/docs#/AIStudio_Project_Notebook/a38e5576)查看本环境基本用法. <br>\n",
"Please click [here ](https://ai.baidu.com/docs#/AIStudio_Project_Notebook/a38e5576) for more detailed instructions. "
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"execution": {
"iopub.execute_input": "2022-10-11T15:15:49.511879Z",
"iopub.status.busy": "2022-10-11T15:15:49.511286Z",
"iopub.status.idle": "2022-10-11T15:15:51.568549Z",
"shell.execute_reply": "2022-10-11T15:15:51.567597Z",
"shell.execute_reply.started": "2022-10-11T15:15:49.511839Z"
},
"jupyter": {
"outputs_hidden": false
},
"scrolled": true,
"tags": []
},
"outputs": [],
"source": [
"import os\n",
"import io\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"from PIL import Image\n",
"import paddle\n",
"from paddle.nn import functional as F\n",
"import random\n",
"from paddle.io import Dataset\n",
"from visualdl import LogWriter\n",
"from paddle.vision.transforms import transforms as T\n",
"import warnings\n",
"import cv2 as cv\n",
"from PIL import Image\n",
"import re\n",
"warnings.filterwarnings(\"ignore\")\n",
"os.environ[\"KMP_DUPLICATE_LIB_OK\"]=\"TRUE\""
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"execution": {
"iopub.execute_input": "2022-10-11T15:16:14.415916Z",
"iopub.status.busy": "2022-10-11T15:16:14.415245Z",
"iopub.status.idle": "2022-10-11T15:16:14.428584Z",
"shell.execute_reply": "2022-10-11T15:16:14.427470Z",
"shell.execute_reply.started": "2022-10-11T15:16:14.415874Z"
},
"jupyter": {
"outputs_hidden": false
},
"tags": []
},
"outputs": [],
"source": [
"class SeparableConv2D(paddle.nn.Layer):\n",
" def __init__(self,\n",
" in_channels,\n",
" out_channels,\n",
" kernel_size,\n",
" stride=1,\n",
" padding=0,\n",
" dilation=1,\n",
" groups=None,\n",
" weight_attr=None,\n",
" bias_attr=None,\n",
" data_format=\"NCHW\"):\n",
" super(SeparableConv2D, self).__init__()\n",
"\n",
" self._padding = padding\n",
" self._stride = stride\n",
" self._dilation = dilation\n",
" self._in_channels = in_channels\n",
" self._data_format = data_format\n",
"\n",
" # 第一次卷积参数，没有偏置参数\n",
" filter_shape = [in_channels, 1] + self.convert_to_list(kernel_size, 2, 'kernel_size')\n",
" self.weight_conv = self.create_parameter(shape=filter_shape, attr=weight_attr)\n",
"\n",
" # 第二次卷积参数\n",
" filter_shape = [out_channels, in_channels] + self.convert_to_list(1, 2, 'kernel_size')\n",
" self.weight_pointwise = self.create_parameter(shape=filter_shape, attr=weight_attr)\n",
" self.bias_pointwise = self.create_parameter(shape=[out_channels],\n",
" attr=bias_attr,\n",
" is_bias=True)\n",
"\n",
" def convert_to_list(self, value, n, name, dtype=np.int):\n",
" if isinstance(value, dtype):\n",
" return [value, ] * n\n",
" else:\n",
" try:\n",
" value_list = list(value)\n",
" except TypeError:\n",
" raise ValueError(\"The \" + name +\n",
" \"'s type must be list or tuple. Received: \" + str(\n",
" value))\n",
" if len(value_list) != n:\n",
" raise ValueError(\"The \" + name + \"'s length must be \" + str(n) +\n",
" \". Received: \" + str(value))\n",
" for single_value in value_list:\n",
" try:\n",
" dtype(single_value)\n",
" except (ValueError, TypeError):\n",
" raise ValueError(\n",
" \"The \" + name + \"'s type must be a list or tuple of \" + str(\n",
" n) + \" \" + str(dtype) + \" . Received: \" + str(\n",
" value) + \" \"\n",
" \"including element \" + str(single_value) + \" of type\" + \" \"\n",
" + str(type(single_value)))\n",
" return value_list\n",
"\n",
" def forward(self, inputs):\n",
" conv_out = F.conv2d(inputs,\n",
" self.weight_conv,\n",
" padding=self._padding,\n",
" stride=self._stride,\n",
" dilation=self._dilation,\n",
" groups=self._in_channels,\n",
" data_format=self._data_format)\n",
"\n",
" out = F.conv2d(conv_out,\n",
" self.weight_pointwise,\n",
" bias=self.bias_pointwise,\n",
" padding=0,\n",
" stride=1,\n",
" dilation=1,\n",
" groups=1,\n",
" data_format=self._data_format)\n",
"\n",
" return out\n",
"class Encoder(paddle.nn.Layer):\n",
" def __init__(self, in_channels, out_channels):\n",
" super(Encoder, self).__init__()\n",
"\n",
" self.relus = paddle.nn.LayerList(\n",
" [paddle.nn.ReLU() for i in range(2)])\n",
" self.separable_conv_01 = SeparableConv2D(in_channels,\n",
" out_channels,\n",
" kernel_size=3,\n",
" padding='same')\n",
" self.bns = paddle.nn.LayerList(\n",
" [paddle.nn.BatchNorm2D(out_channels) for i in range(2)])\n",
"\n",
" self.separable_conv_02 = SeparableConv2D(out_channels,\n",
" out_channels,\n",
" kernel_size=3,\n",
" padding='same')\n",
" self.pool = paddle.nn.MaxPool2D(kernel_size=3, stride=2, padding=1)\n",
" self.residual_conv = paddle.nn.Conv2D(in_channels,\n",
" out_channels,\n",
" kernel_size=1,\n",
" stride=2,\n",
" padding='same')\n",
"\n",
" def forward(self, inputs):\n",
" previous_block_activation = inputs\n",
"\n",
" y = self.relus[0](inputs)\n",
" y = self.separable_conv_01(y)\n",
" y = self.bns[0](y)\n",
" y = self.relus[1](y)\n",
" y = self.separable_conv_02(y)\n",
" y = self.bns[1](y)\n",
" y = self.pool(y)\n",
"\n",
" residual = self.residual_conv(previous_block_activation)\n",
" y = paddle.add(y, residual)\n",
"\n",
" return y\n",
"class Decoder(paddle.nn.Layer):\n",
" def __init__(self, in_channels, out_channels):\n",
" super(Decoder, self).__init__()\n",
"\n",
" self.relus = paddle.nn.LayerList(\n",
" [paddle.nn.ReLU() for i in range(2)])\n",
" self.conv_transpose_01 = paddle.nn.Conv2DTranspose(in_channels,\n",
" out_channels,\n",
" kernel_size=3,\n",
" padding=1)\n",
" self.conv_transpose_02 = paddle.nn.Conv2DTranspose(out_channels,\n",
" out_channels,\n",
" kernel_size=3,\n",
" padding=1)\n",
" self.bns = paddle.nn.LayerList(\n",
" [paddle.nn.BatchNorm2D(out_channels) for i in range(2)]\n",
" )\n",
" self.upsamples = paddle.nn.LayerList(\n",
" [paddle.nn.Upsample(scale_factor=2.0) for i in range(2)]\n",
" )\n",
" self.residual_conv = paddle.nn.Conv2D(in_channels,\n",
" out_channels,\n",
" kernel_size=1,\n",
" padding='same')\n",
"\n",
" def forward(self, inputs):\n",
" previous_block_activation = inputs\n",
"\n",
" y = self.relus[0](inputs)\n",
" y = self.conv_transpose_01(y)\n",
" y = self.bns[0](y)\n",
" y = self.relus[1](y)\n",
" y = self.conv_transpose_02(y)\n",
" y = self.bns[1](y)\n",
" y = self.upsamples[0](y)\n",
"\n",
" residual = self.upsamples[1](previous_block_activation)\n",
" residual = self.residual_conv(residual)\n",
"\n",
" y = paddle.add(y, residual)\n",
"\n",
" return y\n",
"class PetNet(paddle.nn.Layer):\n",
" def __init__(self, num_classes):\n",
" super(PetNet, self).__init__()\n",
"\n",
" self.conv_1 = paddle.nn.Conv2D(3, 32,\n",
" kernel_size=3,\n",
" stride=2,\n",
" padding='same')\n",
" self.bn = paddle.nn.BatchNorm2D(32)\n",
" self.relu = paddle.nn.ReLU()\n",
"\n",
" in_channels = 32\n",
" self.encoders = []\n",
" self.encoder_list = [64, 128, 256]\n",
" self.decoder_list = [256, 128, 64, 32]\n",
"\n",
" for out_channels in self.encoder_list:\n",
" block = self.add_sublayer('encoder_{}'.format(out_channels),\n",
" Encoder(in_channels, out_channels))\n",
" self.encoders.append(block)\n",
" in_channels = out_channels\n",
"\n",
" self.decoders = []\n",
"\n",
" for out_channels in self.decoder_list:\n",
" block = self.add_sublayer('decoder_{}'.format(out_channels),\n",
" Decoder(in_channels, out_channels))\n",
" self.decoders.append(block)\n",
" in_channels = out_channels\n",
"\n",
" self.output_conv = paddle.nn.Conv2D(in_channels,\n",
" num_classes,\n",
" kernel_size=3,\n",
" padding='same')\n",
"\n",
" def forward(self, inputs):\n",
" y = self.conv_1(inputs)\n",
" y = self.bn(y)\n",
" y = self.relu(y)\n",
"\n",
" for encoder in self.encoders:\n",
" y = encoder(y)\n",
"\n",
" for decoder in self.decoders:\n",
" y = decoder(y)\n",
"\n",
" y = self.output_conv(y)\n",
" return y\n",
"IMAGE_SIZE = (512, 512)\n",
"num_classes = 2\n",
"network = PetNet(num_classes)\n",
"model = paddle.Model(network)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"execution": {
"iopub.execute_input": "2022-10-11T15:16:14.415916Z",
"iopub.status.busy": "2022-10-11T15:16:14.415245Z",
"iopub.status.idle": "2022-10-11T15:16:14.428584Z",
"shell.execute_reply": "2022-10-11T15:16:14.427470Z",
"shell.execute_reply.started": "2022-10-11T15:16:14.415874Z"
},
"jupyter": {
"outputs_hidden": false
},
"scrolled": true,
"tags": []
},
"outputs": [],
"source": [
"#加载训练好的权重\n",
"optimizer = paddle.optimizer.RMSProp(learning_rate=0.001, parameters=network.parameters())\n",
"layer_state_dict = paddle.load(\"mymodel.pdparams\")\n",
"opt_state_dict = paddle.load(\"optimizer.pdopt\")\n",
"\n",
"network.set_state_dict(layer_state_dict)\n",
"optimizer.set_state_dict(opt_state_dict)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"execution": {
"iopub.execute_input": "2022-10-11T16:07:50.639995Z",
"iopub.status.busy": "2022-10-11T16:07:50.639338Z",
"iopub.status.idle": "2022-10-11T16:07:50.941928Z",
"shell.execute_reply": "2022-10-11T16:07:50.940805Z",
"shell.execute_reply.started": "2022-10-11T16:07:50.639949Z"
},
"jupyter": {
"outputs_hidden": false
},
"tags": []
},
"outputs": [],
"source": [
"def FinalImage(mask,image):\n",
" # 这个函数的作用是把mask高斯模糊之后的遮罩和原始的image叠加起来\n",
" #输入 mask [0,255]的这招图\n",
" #image 必须无条件转化为512*512 三通道彩图\n",
" \n",
" th = cv.threshold(mask,140,255,cv.THRESH_BINARY)[1]\n",
" blur = cv.GaussianBlur(th,(33,33), 15)\n",
" heatmap_img = cv.applyColorMap(blur, cv.COLORMAP_OCEAN)\n",
" Blendermap = cv.addWeighted(heatmap_img, 0.5, image, 1, 0)\n",
" return Blendermap"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"IMPORTANT: You are using gradio version 3.12.0, however version 3.14.0 is available, please upgrade.\n",
"--------\n",
"Running on local URL: http://127.0.0.1:7864\n",
"Running on public URL: https://317fc297694e39a2.gradio.app\n",
"\n",
"This share link expires in 72 hours. For free permanent hosting and GPU upgrades (NEW!), check out Spaces: https://huggingface.co/spaces\n"
]
},
{
"data": {
"text/html": [
"<div><iframe src=\"https://317fc297694e39a2.gradio.app\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": []
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import gradio as gr\n",
"def Showsegmentation(image):\n",
" mask = paddle.argmax(network(paddle.to_tensor([((image - 127.5) / 127.5).transpose(2, 0, 1)]))[0], axis=0).numpy()\n",
" mask=mask.astype('uint8')*255\n",
" immask=cv.resize(mask, (512, 512))\n",
" image=cv.resize(image,(512,512))\n",
" blendmask=FinalImage(immask,image)\n",
" return blendmask\n",
"\n",
"gr.Interface(fn=Showsegmentation, inputs=\"image\", outputs=\"image\").launch(share=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.8.5"
},
"toc-autonumbering": true,
"toc-showcode": true,
"toc-showmarkdowntxt": true
},
"nbformat": 4,
"nbformat_minor": 4
}
|