└── PyTorch for Deep Learning and Computer Vision Course (All Codes)
    ├── CIFAR_10.ipynb
    ├── Convolutional Neural Networks.ipynb
    ├── Deep Neural Networks - MNIST.ipynb
    ├── Deep_Neural_Networks.ipynb
    ├── Linear_Regression.ipynb
    ├── Perceptron.ipynb
    ├── Style_Transfer.ipynb
    └── Transfer_Learning.ipynb


/PyTorch for Deep Learning and Computer Vision Course (All Codes)/Linear_Regression.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |   "nbformat": 4,
  3 |   "nbformat_minor": 0,
  4 |   "metadata": {
  5 |     "colab": {
  6 |       "name": "Linear Regression.ipynb",
  7 |       "version": "0.3.2",
  8 |       "provenance": []
  9 |     },
 10 |     "kernelspec": {
 11 |       "name": "python3",
 12 |       "display_name": "Python 3"
 13 |     }
 14 |   },
 15 |   "cells": [
 16 |     {
 17 |       "metadata": {
 18 |         "id": "oHxQbKZci27E",
 19 |         "colab_type": "code",
 20 |         "outputId": "703199c8-c579-4894-bd44-1bc1e8317fd1",
 21 |         "colab": {
 22 |           "base_uri": "https://localhost:8080/",
 23 |           "height": 1020
 24 |         }
 25 |       },
 26 |       "cell_type": "code",
 27 |       "source": [
 28 |         "!pip3 install torch"
 29 |       ],
 30 |       "execution_count": 1,
 31 |       "outputs": [
 32 |         {
 33 |           "output_type": "stream",
 34 |           "text": [
 35 |             "Collecting torch\n",
 36 |             "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/7e/60/66415660aa46b23b5e1b72bc762e816736ce8d7260213e22365af51e8f9c/torch-1.0.0-cp36-cp36m-manylinux1_x86_64.whl (591.8MB)\n",
 37 |             "\u001b[K    100% |████████████████████████████████| 591.8MB 23kB/s \n",
 38 |             "tcmalloc: large alloc 1073750016 bytes == 0x614fa000 @  0x7f296ec2c2a4 0x591a07 0x5b5d56 0x502e9a 0x506859 0x502209 0x502f3d 0x506859 0x504c28 0x502540 0x502f3d 0x506859 0x504c28 0x502540 0x502f3d 0x506859 0x504c28 0x502540 0x502f3d 0x507641 0x502209 0x502f3d 0x506859 0x504c28 0x502540 0x502f3d 0x507641 0x504c28 0x502540 0x502f3d 0x507641\n",
 39 |             "\u001b[?25hInstalling collected packages: torch\n",
 40 |             "Successfully installed torch-1.0.0\n"
 41 |           ],
 42 |           "name": "stdout"
 43 |         }
 44 |       ]
 45 |     },
 46 |     {
 47 |       "metadata": {
 48 |         "id": "g90d_JwFi8I7",
 49 |         "colab_type": "code",
 50 |         "colab": {}
 51 |       },
 52 |       "cell_type": "code",
 53 |       "source": [
 54 |         "import torch\n",
 55 |         "import torch.nn as nn\n",
 56 |         "import matplotlib.pyplot as plt\n",
 57 |         "import numpy as np"
 58 |       ],
 59 |       "execution_count": 0,
 60 |       "outputs": []
 61 |     },
 62 |     {
 63 |       "metadata": {
 64 |         "id": "BkdXhIlXvKzM",
 65 |         "colab_type": "code",
 66 |         "outputId": "9ea4075e-1585-4c9b-d057-4a948cb87611",
 67 |         "colab": {
 68 |           "base_uri": "https://localhost:8080/",
 69 |           "height": 378
 70 |         }
 71 |       },
 72 |       "cell_type": "code",
 73 |       "source": [
 74 |         "X = torch.randn(100, 1)*10\n",
 75 |         "y = X + 3*torch.randn(100, 1)\n",
 76 |         "plt.plot(X.numpy(), y.numpy(), 'o')\n",
 77 |         "plt.ylabel('y')\n",
 78 |         "plt.xlabel('x')"
 79 |       ],
 80 |       "execution_count": 3,
 81 |       "outputs": [
 82 |         {
 83 |           "output_type": "execute_result",
 84 |           "data": {
 85 |             "text/plain": [
 86 |               "Text(0.5, 0, 'x')"
 87 |             ]
 88 |           },
 89 |           "metadata": {
 90 |             "tags": []
 91 |           },
 92 |           "execution_count": 3
 93 |         },
 94 |         {
 95 |           "output_type": "display_data",
 96 |           "data": {
 97 |             "image/png": "iVBORw0KGgoAAAANSUhEUgAAAfIAAAFYCAYAAACoFn5YAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n5AAAGIwgBwDAYAQ5AAAGI8gBADDY/wEZYAq3NKw4GAAAAABJRU5ErkJggg==\n",
 98 |             "text/plain": [
 99 |               "<Figure size 576x396 with 1 Axes>"
100 |             ]
101 |           },
102 |           "metadata": {
103 |             "tags": []
104 |           }
105 |         }
106 |       ]
107 |     },
108 |     {
109 |       "metadata": {
110 |         "id": "Voo3RX1IYz21",
111 |         "colab_type": "code",
112 |         "colab": {}
113 |       },
114 |       "cell_type": "code",
115 |       "source": [
116 |         "class LR(nn.Module):\n",
117 |         "  def __init__(self, input_size, output_size):\n",
118 |         "    super().__init__()\n",
119 |         "    self.linear = nn.Linear(input_size, output_size)\n",
120 |         "  def forward(self, x):\n",
121 |         "    pred = self.linear(x)\n",
122 |         "    return pred"
123 |       ],
124 |       "execution_count": 0,
125 |       "outputs": []
126 |     },
127 |     {
128 |       "metadata": {
129 |         "id": "PeyVS6V_aBfy",
130 |         "colab_type": "code",
131 |         "outputId": "84dbdbae-8cd6-4d39-ac3b-862c9c0df5c9",
132 |         "colab": {
133 |           "base_uri": "https://localhost:8080/",
134 |           "height": 68
135 |         }
136 |       },
137 |       "cell_type": "code",
138 |       "source": [
139 |         "torch.manual_seed(1)\n",
140 |         "model = LR(1, 1)\n",
141 |         "print(model)"
142 |       ],
143 |       "execution_count": 5,
144 |       "outputs": [
145 |         {
146 |           "output_type": "stream",
147 |           "text": [
148 |             "LR(\n",
149 |             "  (linear): Linear(in_features=1, out_features=1, bias=True)\n",
150 |             ")\n"
151 |           ],
152 |           "name": "stdout"
153 |         }
154 |       ]
155 |     },
156 |     {
157 |       "metadata": {
158 |         "id": "e1HHLRTbaeZF",
159 |         "colab_type": "code",
160 |         "colab": {}
161 |       },
162 |       "cell_type": "code",
163 |       "source": [
164 |         "[w, b] = model.parameters()\n",
165 |         "def get_params():\n",
166 |         "  return (w[0][0].item(), b[0].item())"
167 |       ],
168 |       "execution_count": 0,
169 |       "outputs": []
170 |     },
171 |     {
172 |       "metadata": {
173 |         "id": "x1bjDI3vxEmd",
174 |         "colab_type": "code",
175 |         "colab": {}
176 |       },
177 |       "cell_type": "code",
178 |       "source": [
179 |         "def plot_fit(title):\n",
180 |         "  plt.title = title\n",
181 |         "  w1, b1 = get_params()\n",
182 |         "  x1 = np.array([-30, 30])\n",
183 |         "  y1 = w1*x1 + b1\n",
184 |         "  plt.plot(x1, y1, 'r')\n",
185 |         "  plt.scatter(X, y)\n",
186 |         "  plt.show()"
187 |       ],
188 |       "execution_count": 0,
189 |       "outputs": []
190 |     },
191 |     {
192 |       "metadata": {
193 |         "id": "wYEJKbTEy2Ci",
194 |         "colab_type": "code",
195 |         "outputId": "162542b8-3a08-4cdf-c8d3-74f6670f0eb7",
196 |         "colab": {
197 |           "base_uri": "https://localhost:8080/",
198 |           "height": 347
199 |         }
200 |       },
201 |       "cell_type": "code",
202 |       "source": [
203 |         "plot_fit('Initial Model')"
204 |       ],
205 |       "execution_count": 8,
206 |       "outputs": [
207 |         {
208 |           "output_type": "display_data",
209 |           "data": {
210 |             "image/png": "iVBORw0KGgoAAAANSUhEUgAAAeQAAAFKCAYAAADMuCxnAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
211 |             "text/plain": [
212 |               "<Figure size 576x396 with 1 Axes>"
213 |             ]
214 |           },
215 |           "metadata": {
216 |             "tags": []
217 |           }
218 |         }
219 |       ]
220 |     },
221 |     {
222 |       "metadata": {
223 |         "id": "4Z9-HIA0y5S7",
224 |         "colab_type": "code",
225 |         "colab": {}
226 |       },
227 |       "cell_type": "code",
228 |       "source": [
229 |         "criterion = nn.MSELoss()\n",
230 |         "optimizer = torch.optim.SGD(model.parameters(), lr = 0.01)"
231 |       ],
232 |       "execution_count": 0,
233 |       "outputs": []
234 |     },
235 |     {
236 |       "metadata": {
237 |         "id": "wu4Qzn3PCeJ9",
238 |         "colab_type": "code",
239 |         "outputId": "bcdc1419-824e-4bd5-d697-a66955589708",
240 |         "colab": {
241 |           "base_uri": "https://localhost:8080/",
242 |           "height": 1717
243 |         }
244 |       },
245 |       "cell_type": "code",
246 |       "source": [
247 |         "epochs = 100\n",
248 |         "losses = []\n",
249 |         "for i in range(epochs):\n",
250 |         "  y_pred = model.forward(X)\n",
251 |         "  loss = criterion(y_pred, y)\n",
252 |         "  print(\"epoch:\", i, \"loss:\", loss.item())\n",
253 |         "  \n",
254 |         "  losses.append(loss)\n",
255 |         "  optimizer.zero_grad()\n",
256 |         "  loss.backward()\n",
257 |         "  optimizer.step()"
258 |       ],
259 |       "execution_count": 10,
260 |       "outputs": [
261 |         {
262 |           "output_type": "stream",
263 |           "text": [
264 |             "epoch: 0 loss: 34.606773376464844\n",
265 |             "epoch: 1 loss: 32.641448974609375\n",
266 |             "epoch: 2 loss: 30.837696075439453\n",
267 |             "epoch: 3 loss: 29.182172775268555\n",
268 |             "epoch: 4 loss: 27.662689208984375\n",
269 |             "epoch: 5 loss: 26.2680606842041\n",
270 |             "epoch: 6 loss: 24.987957000732422\n",
271 |             "epoch: 7 loss: 23.813003540039062\n",
272 |             "epoch: 8 loss: 22.734525680541992\n",
273 |             "epoch: 9 loss: 21.744590759277344\n",
274 |             "epoch: 10 loss: 20.835914611816406\n",
275 |             "epoch: 11 loss: 20.001802444458008\n",
276 |             "epoch: 12 loss: 19.236114501953125\n",
277 |             "epoch: 13 loss: 18.533241271972656\n",
278 |             "epoch: 14 loss: 17.88799285888672\n",
279 |             "epoch: 15 loss: 17.295654296875\n",
280 |             "epoch: 16 loss: 16.751863479614258\n",
281 |             "epoch: 17 loss: 16.252628326416016\n",
282 |             "epoch: 18 loss: 15.794288635253906\n",
283 |             "epoch: 19 loss: 15.373481750488281\n",
284 |             "epoch: 20 loss: 14.987119674682617\n",
285 |             "epoch: 21 loss: 14.632369995117188\n",
286 |             "epoch: 22 loss: 14.306648254394531\n",
287 |             "epoch: 23 loss: 14.007560729980469\n",
288 |             "epoch: 24 loss: 13.73292064666748\n",
289 |             "epoch: 25 loss: 13.480721473693848\n",
290 |             "epoch: 26 loss: 13.249117851257324\n",
291 |             "epoch: 27 loss: 13.036426544189453\n",
292 |             "epoch: 28 loss: 12.841087341308594\n",
293 |             "epoch: 29 loss: 12.661684036254883\n",
294 |             "epoch: 30 loss: 12.496904373168945\n",
295 |             "epoch: 31 loss: 12.345552444458008\n",
296 |             "epoch: 32 loss: 12.206522941589355\n",
297 |             "epoch: 33 loss: 12.078808784484863\n",
298 |             "epoch: 34 loss: 11.9614839553833\n",
299 |             "epoch: 35 loss: 11.853694915771484\n",
300 |             "epoch: 36 loss: 11.754661560058594\n",
301 |             "epoch: 37 loss: 11.663664817810059\n",
302 |             "epoch: 38 loss: 11.58005142211914\n",
303 |             "epoch: 39 loss: 11.503213882446289\n",
304 |             "epoch: 40 loss: 11.432601928710938\n",
305 |             "epoch: 41 loss: 11.367704391479492\n",
306 |             "epoch: 42 loss: 11.308053016662598\n",
307 |             "epoch: 43 loss: 11.25322151184082\n",
308 |             "epoch: 44 loss: 11.202813148498535\n",
309 |             "epoch: 45 loss: 11.156472206115723\n",
310 |             "epoch: 46 loss: 11.113862991333008\n",
311 |             "epoch: 47 loss: 11.074682235717773\n",
312 |             "epoch: 48 loss: 11.038651466369629\n",
313 |             "epoch: 49 loss: 11.005512237548828\n",
314 |             "epoch: 50 loss: 10.975030899047852\n",
315 |             "epoch: 51 loss: 10.946990013122559\n",
316 |             "epoch: 52 loss: 10.92119312286377\n",
317 |             "epoch: 53 loss: 10.897455215454102\n",
318 |             "epoch: 54 loss: 10.875611305236816\n",
319 |             "epoch: 55 loss: 10.855506896972656\n",
320 |             "epoch: 56 loss: 10.83700180053711\n",
321 |             "epoch: 57 loss: 10.819965362548828\n",
322 |             "epoch: 58 loss: 10.804278373718262\n",
323 |             "epoch: 59 loss: 10.789833068847656\n",
324 |             "epoch: 60 loss: 10.776528358459473\n",
325 |             "epoch: 61 loss: 10.764272689819336\n",
326 |             "epoch: 62 loss: 10.75298023223877\n",
327 |             "epoch: 63 loss: 10.742575645446777\n",
328 |             "epoch: 64 loss: 10.732985496520996\n",
329 |             "epoch: 65 loss: 10.72414493560791\n",
330 |             "epoch: 66 loss: 10.715993881225586\n",
331 |             "epoch: 67 loss: 10.708476066589355\n",
332 |             "epoch: 68 loss: 10.701542854309082\n",
333 |             "epoch: 69 loss: 10.695145606994629\n",
334 |             "epoch: 70 loss: 10.689242362976074\n",
335 |             "epoch: 71 loss: 10.683794021606445\n",
336 |             "epoch: 72 loss: 10.678763389587402\n",
337 |             "epoch: 73 loss: 10.674118041992188\n",
338 |             "epoch: 74 loss: 10.66982650756836\n",
339 |             "epoch: 75 loss: 10.665861129760742\n",
340 |             "epoch: 76 loss: 10.66219711303711\n",
341 |             "epoch: 77 loss: 10.658808708190918\n",
342 |             "epoch: 78 loss: 10.65567684173584\n",
343 |             "epoch: 79 loss: 10.652778625488281\n",
344 |             "epoch: 80 loss: 10.650097846984863\n",
345 |             "epoch: 81 loss: 10.647615432739258\n",
346 |             "epoch: 82 loss: 10.645318031311035\n",
347 |             "epoch: 83 loss: 10.643189430236816\n",
348 |             "epoch: 84 loss: 10.641217231750488\n",
349 |             "epoch: 85 loss: 10.639389038085938\n",
350 |             "epoch: 86 loss: 10.637694358825684\n",
351 |             "epoch: 87 loss: 10.636122703552246\n",
352 |             "epoch: 88 loss: 10.634663581848145\n",
353 |             "epoch: 89 loss: 10.633308410644531\n",
354 |             "epoch: 90 loss: 10.632051467895508\n",
355 |             "epoch: 91 loss: 10.63088321685791\n",
356 |             "epoch: 92 loss: 10.629796981811523\n",
357 |             "epoch: 93 loss: 10.62878704071045\n",
358 |             "epoch: 94 loss: 10.627848625183105\n",
359 |             "epoch: 95 loss: 10.626974105834961\n",
360 |             "epoch: 96 loss: 10.626160621643066\n",
361 |             "epoch: 97 loss: 10.625402450561523\n",
362 |             "epoch: 98 loss: 10.624695777893066\n",
363 |             "epoch: 99 loss: 10.62403678894043\n"
364 |           ],
365 |           "name": "stdout"
366 |         }
367 |       ]
368 |     },
369 |     {
370 |       "metadata": {
371 |         "id": "j3D-8o6MDXO9",
372 |         "colab_type": "code",
373 |         "outputId": "dcbebc38-7284-43f1-d61b-afa252244857",
374 |         "colab": {
375 |           "base_uri": "https://localhost:8080/",
376 |           "height": 378
377 |         }
378 |       },
379 |       "cell_type": "code",
380 |       "source": [
381 |         "plt.plot(range(epochs), losses)\n",
382 |         "plt.ylabel('Loss')\n",
383 |         "plt.xlabel('epoch')"
384 |       ],
385 |       "execution_count": 11,
386 |       "outputs": [
387 |         {
388 |           "output_type": "execute_result",
389 |           "data": {
390 |             "text/plain": [
391 |               "Text(0.5, 0, 'epoch')"
392 |             ]
393 |           },
394 |           "metadata": {
395 |             "tags": []
396 |           },
397 |           "execution_count": 11
398 |         },
399 |         {
400 |           "output_type": "display_data",
401 |           "data": {
402 |             "image/png": "iVBORw0KGgoAAAANSUhEUgAAAe0AAAFYCAYAAAB+s6Q9AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAAAElFTkSuQmCC\n",
403 |             "text/plain": [
404 |               "<Figure size 576x396 with 1 Axes>"
405 |             ]
406 |           },
407 |           "metadata": {
408 |             "tags": []
409 |           }
410 |         }
411 |       ]
412 |     },
413 |     {
414 |       "metadata": {
415 |         "id": "VwsPWhWJFONF",
416 |         "colab_type": "code",
417 |         "outputId": "99806a4f-2eca-465e-d166-ae39ea701b32",
418 |         "colab": {
419 |           "base_uri": "https://localhost:8080/",
420 |           "height": 347
421 |         }
422 |       },
423 |       "cell_type": "code",
424 |       "source": [
425 |         "plot_fit(\"Trained Model\")"
426 |       ],
427 |       "execution_count": 12,
428 |       "outputs": [
429 |         {
430 |           "output_type": "display_data",
431 |           "data": {
432 |             "image/png": "iVBORw0KGgoAAAANSUhEUgAAAeQAAAFKCAYAAADMuCxnAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
433 |             "text/plain": [
434 |               "<Figure size 576x396 with 1 Axes>"
435 |             ]
436 |           },
437 |           "metadata": {
438 |             "tags": []
439 |           }
440 |         }
441 |       ]
442 |     },
443 |     {
444 |       "metadata": {
445 |         "id": "Eyc77EKUFYgZ",
446 |         "colab_type": "code",
447 |         "colab": {}
448 |       },
449 |       "cell_type": "code",
450 |       "source": [
451 |         ""
452 |       ],
453 |       "execution_count": 0,
454 |       "outputs": []
455 |     }
456 |   ]
457 | }


--------------------------------------------------------------------------------