File size: 31,329 Bytes
cf8627d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e623e7e
cf8627d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e623e7e
cf8627d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e623e7e
cf8627d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e623e7e
cf8627d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e623e7e
cf8627d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e623e7e
cf8627d
 
 
 
 
 
 
 
 
 
 
e623e7e
 
 
 
 
 
cf8627d
 
 
e623e7e
 
 
cf8627d
 
e623e7e
 
 
cf8627d
 
e623e7e
 
 
 
 
 
 
 
 
 
 
 
cf8627d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e623e7e
cf8627d
 
 
 
 
 
e623e7e
 
 
 
cf8627d
 
 
 
 
 
e623e7e
cf8627d
e623e7e
cf8627d
 
 
 
 
 
 
e623e7e
cf8627d
 
 
e623e7e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cf8627d
 
 
 
 
 
 
 
 
 
e623e7e
 
 
cf8627d
 
 
 
 
 
 
 
e623e7e
 
 
 
 
 
 
cf8627d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "os.chdir('../')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'c:\\\\mlops project\\\\image-colorization-mlops'"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "%pwd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Assuming all necessary imports are here\n",
    "from dataclasses import dataclass\n",
    "from pathlib import Path\n",
    "\n",
    "@dataclass(frozen=True)\n",
    "class ModelTrainerConfig:\n",
    "    root_dir: Path\n",
    "    test_data_path: Path\n",
    "    train_data_path: Path\n",
    "    LEARNING_RATE: float\n",
    "    LAMBDA_RECON: int\n",
    "    DISPLAY_STEP: int\n",
    "    IMAGE_SIZE: list\n",
    "    INPUT_CHANNELS: int\n",
    "    OUTPUT_CHANNELS: int\n",
    "    EPOCH: int\n",
    "    BATCH_SIZE : int"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "from src.imagecolorization.constants import *\n",
    "from src.imagecolorization.utils.common import read_yaml, create_directories\n",
    "\n",
    "class ConfigurationManager:\n",
    "    def __init__(self, config_filepath=CONFIG_FILE_PATH, params_filepath=PARAMS_FILE_PATH):\n",
    "        self.config = read_yaml(config_filepath)\n",
    "        self.params = read_yaml(params_filepath)\n",
    "        create_directories([self.config.artifacts_root])\n",
    "\n",
    "    def get_model_trainer_config(self) -> ModelTrainerConfig:\n",
    "        config = self.config.model_trainer\n",
    "        params = self.params\n",
    "        \n",
    "        create_directories([config.root_dir])\n",
    "        \n",
    "        # Convert LEARNING_RATE to float explicitly\n",
    "        learning_rate = float(params.LEARNING_RATE)\n",
    "        \n",
    "        model_trainer_config = ModelTrainerConfig(\n",
    "            root_dir=config.root_dir,\n",
    "            test_data_path=config.test_data_path,\n",
    "            train_data_path=config.train_data_path,\n",
    "            LEARNING_RATE=learning_rate,  # Use the converted float value\n",
    "            LAMBDA_RECON=params.LAMBDA_RECON,\n",
    "            DISPLAY_STEP=params.DISPLAY_STEP,\n",
    "            IMAGE_SIZE=params.IMAGE_SIZE,\n",
    "            INPUT_CHANNELS=params.INPUT_CHANNELS,\n",
    "            OUTPUT_CHANNELS=params.OUTPUT_CHANNELS,\n",
    "            EPOCH=params.EPOCH,\n",
    "            BATCH_SIZE= params.BATCH_SIZE\n",
    "        )\n",
    "        return model_trainer_config\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch\n",
    "import numpy as np\n",
    "from skimage.color import rgb2lab, lab2rgb\n",
    "def lab_to_rgb(L, ab):\n",
    "    L = L * 100\n",
    "    ab = (ab - 0.5) * 128 * 2\n",
    "    Lab = torch.cat([L, ab], dim = 2).numpy()\n",
    "    rgb_img = []\n",
    "    for img in Lab:\n",
    "        img_rgb = lab2rgb(img)\n",
    "        rgb_img.append(img_rgb)\n",
    "        \n",
    "    return np.stack(rgb_img, axis = 0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "def display_progress(cond, real, fake, current_epoch = 0, figsize=(20,15)):\n",
    "    \"\"\"\n",
    "    Save cond, real (original) and generated (fake)\n",
    "    images in one panel \n",
    "    \"\"\"\n",
    "    cond = cond.detach().cpu().permute(1, 2, 0)   \n",
    "    real = real.detach().cpu().permute(1, 2, 0)\n",
    "    fake = fake.detach().cpu().permute(1, 2, 0)\n",
    "    \n",
    "    images = [cond, real, fake]\n",
    "    titles = ['input','real','generated']\n",
    "    print(f'Epoch: {current_epoch}')\n",
    "    fig, ax = plt.subplots(1, 3, figsize=figsize)\n",
    "    for idx,img in enumerate(images):\n",
    "        if idx == 0:\n",
    "            ab = torch.zeros((224,224,2))\n",
    "            img = torch.cat([images[0]* 100, ab], dim=2).numpy()\n",
    "            imgan = lab2rgb(img)\n",
    "        else:\n",
    "            imgan = lab_to_rgb(images[0],img)\n",
    "        ax[idx].imshow(imgan)\n",
    "        ax[idx].axis(\"off\")\n",
    "    for idx, title in enumerate(titles):    \n",
    "        ax[idx].set_title('{}'.format(title))\n",
    "    plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch\n",
    "from torch import nn, optim\n",
    "from torchvision import transforms\n",
    "from torch.utils.data import Dataset, DataLoader\n",
    "from torch.autograd import Variable\n",
    "from torchvision import models\n",
    "from torch.nn import functional as F\n",
    "import torch.utils.data\n",
    "from torchvision.models.inception import inception_v3\n",
    "from scipy.stats import entropy\n",
    "import pytorch_lightning as pl\n",
    "from torchsummary import summary\n",
    "from src.imagecolorization.conponents.model_building import Generator, Critic\n",
    "from src.imagecolorization.conponents.data_tranformation import ImageColorizationDataset\n",
    "from src.imagecolorization.logging import logger\n",
    "import gc\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "class CWGAN(pl.LightningModule):\n",
    "    def __init__(self, in_channels, out_channels, learning_rate=0.0002, lambda_recon=100, display_step=10, lambda_gp=10, lambda_r1=10):\n",
    "        super().__init__()\n",
    "        self.save_hyperparameters()\n",
    "        self.display_step = display_step\n",
    "        self.generator = Generator(in_channels, out_channels)\n",
    "        self.critic = Critic(in_channels + out_channels)\n",
    "        self.lambda_recon = lambda_recon\n",
    "        self.lambda_gp = lambda_gp\n",
    "        self.lambda_r1 = lambda_r1\n",
    "        self.recon_criterion = nn.L1Loss()\n",
    "        self.generator_losses, self.critic_losses = [], []\n",
    "        self.automatic_optimization = False  # Disable automatic optimization\n",
    "\n",
    "    def configure_optimizers(self):\n",
    "        optimizer_G = optim.Adam(self.generator.parameters(), lr=self.hparams.learning_rate, betas=(0.5, 0.9))\n",
    "        optimizer_C = optim.Adam(self.critic.parameters(), lr=self.hparams.learning_rate, betas=(0.5, 0.9))\n",
    "        return [optimizer_C, optimizer_G]\n",
    "\n",
    "    def generator_step(self, real_images, conditioned_images, optimizer_G):\n",
    "        optimizer_G.zero_grad()\n",
    "        fake_images = self.generator(conditioned_images)\n",
    "        recon_loss = self.recon_criterion(fake_images, real_images)\n",
    "        recon_loss.backward()\n",
    "        optimizer_G.step()\n",
    "        self.generator_losses.append(recon_loss.item())\n",
    "\n",
    "    def critic_step(self, real_images, conditioned_images, optimizer_C):\n",
    "        optimizer_C.zero_grad()\n",
    "        fake_images = self.generator(conditioned_images)\n",
    "\n",
    "        # Separate L and ab channels\n",
    "        l_real = conditioned_images\n",
    "        ab_real = real_images\n",
    "        ab_fake = fake_images\n",
    "\n",
    "        # Compute logits\n",
    "        fake_logits = self.critic(ab_fake, l_real)  # Pass two arguments\n",
    "        real_logits = self.critic(ab_real, l_real)  # Pass two arguments\n",
    "\n",
    "        # Compute the loss for the critic\n",
    "        loss_C = real_logits.mean() - fake_logits.mean()\n",
    "\n",
    "        # Compute the gradient penalty\n",
    "        alpha = torch.rand(real_images.size(0), 1, 1, 1, requires_grad=True).to(real_images.device)\n",
    "        interpolated = (alpha * ab_real + (1 - alpha) * ab_fake.detach()).requires_grad_(True)\n",
    "        interpolated_logits = self.critic(interpolated, l_real)\n",
    "\n",
    "        gradients = torch.autograd.grad(outputs=interpolated_logits, inputs=interpolated,\n",
    "                                        grad_outputs=torch.ones_like(interpolated_logits), create_graph=True, retain_graph=True)[0]\n",
    "        gradients = gradients.view(len(gradients), -1)\n",
    "        gradients_penalty = ((gradients.norm(2, dim=1) - 1) ** 2).mean()\n",
    "        loss_C += self.lambda_gp * gradients_penalty\n",
    "\n",
    "        # Compute the R1 regularization loss\n",
    "        r1_reg = gradients.pow(2).sum(1).mean()\n",
    "        loss_C += self.lambda_r1 * r1_reg\n",
    "\n",
    "        # Backpropagation\n",
    "        loss_C.backward()\n",
    "        optimizer_C.step()\n",
    "        self.critic_losses.append(loss_C.item())\n",
    "\n",
    "    def training_step(self, batch, batch_idx):\n",
    "        optimizer_C, optimizer_G = self.optimizers()\n",
    "        real_images, conditioned_images = batch\n",
    "\n",
    "        self.critic_step(real_images, conditioned_images, optimizer_C)\n",
    "        self.generator_step(real_images, conditioned_images, optimizer_G)\n",
    "\n",
    "        if self.current_epoch % self.display_step == 0 and batch_idx == 0:\n",
    "            with torch.no_grad():\n",
    "                fake_images = self.generator(conditioned_images)\n",
    "                display_progress(conditioned_images[0], real_images[0], fake_images[0], self.current_epoch)\n",
    "\n",
    "    def on_epoch_end(self):\n",
    "        gc.collect()\n",
    "        torch.cuda.empty_cache()\n",
    "\n",
    "    def forward(self, x):\n",
    "        return self.generator(x)\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "class ModelTrainer:\n",
    "    def __init__(self, config):\n",
    "        self.config = config\n",
    "        \n",
    "    def load_datasets(self):\n",
    "        self.train_dataset = torch.load(self.config.train_data_path)\n",
    "        self.test_dataset = torch.load(self.config.test_data_path)\n",
    "    \n",
    "        # Ensure these are actually datasets, not dataloaders\n",
    "        if isinstance(self.train_dataset, DataLoader):\n",
    "            self.train_dataset = self.train_dataset.dataset\n",
    "        if isinstance(self.test_dataset, DataLoader):\n",
    "            self.test_dataset = self.test_dataset.dataset\n",
    "        \n",
    "    def create_dataloaders(self):\n",
    "        self.train_dataloader = DataLoader(\n",
    "            self.train_dataset, \n",
    "            batch_size=self.config.BATCH_SIZE, \n",
    "            shuffle=True,\n",
    "        )\n",
    "        self.test_dataloader = DataLoader(\n",
    "            self.test_dataset, \n",
    "            batch_size=self.config.BATCH_SIZE, \n",
    "            shuffle=False,\n",
    "        )\n",
    "        \n",
    "        for batch in self.test_dataloader:\n",
    "            ab, L = batch\n",
    "            print(f\"Train loader batch - ab shape: {ab.shape}, L shape: {L.shape}\")\n",
    "            break  # Remove break to check shapes for all batches if needed\n",
    "\n",
    "        for batch in self.train_dataloader:\n",
    "            ab, L = batch\n",
    "            print(f\"Test loader batch - ab shape: {ab.shape}, L shape: {L.shape}\")\n",
    "            break\n",
    "        \n",
    "        \n",
    "        \n",
    "    def initialize_model(self):\n",
    "        self.model = CWGAN(\n",
    "            in_channels=self.config.INPUT_CHANNELS,\n",
    "            out_channels=self.config.OUTPUT_CHANNELS,\n",
    "            learning_rate=self.config.LEARNING_RATE,\n",
    "            lambda_recon=self.config.LAMBDA_RECON,\n",
    "            display_step=self.config.DISPLAY_STEP,\n",
    "            lambda_gp=10,  # Default value, you can make it configurable\n",
    "            lambda_r1=10   # Default value, you can make it configurable\n",
    "        )\n",
    "        \n",
    "    def train_model(self):\n",
    "        checkpoint_callback = pl.callbacks.ModelCheckpoint(\n",
    "            dirpath=self.config.root_dir,\n",
    "            filename='cwgan-{epoch:02d}-{generator_loss:.2f}',\n",
    "            save_top_k=-1,  # Save all checkpoints\n",
    "            verbose=True\n",
    "        )\n",
    "        \n",
    "        trainer = pl.Trainer(\n",
    "            max_epochs=self.config.EPOCH,\n",
    "            callbacks=[checkpoint_callback],\n",
    "            \n",
    "        )\n",
    "        \n",
    "        trainer.fit(self.model, self.train_dataloader)\n",
    "        \n",
    "    def save_model(self):\n",
    "        trained_model_dir = self.config.root_dir\n",
    "        os.makedirs(trained_model_dir, exist_ok=True)\n",
    "    \n",
    "        generator_path = os.path.join(trained_model_dir, \"cwgan_generator_final.pt\")\n",
    "        critic_path = os.path.join(trained_model_dir, \"cwgan_critic_final.pt\")\n",
    "    \n",
    "        torch.save(self.model.generator.state_dict(), generator_path)\n",
    "        torch.save(self.model.critic.state_dict(), critic_path)\n",
    "        logger.info(f\"Final models saved at {trained_model_dir}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[2024-08-24 19:39:49,395: INFO: common: yaml file: config\\config.yaml loaded successfully]\n",
      "[2024-08-24 19:39:49,400: INFO: common: yaml file: params.yaml loaded successfully]\n",
      "[2024-08-24 19:39:49,404: INFO: common: created directory at: artifacts]\n",
      "[2024-08-24 19:39:49,405: INFO: common: created directory at: artifacts/trained_model]\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\azizu\\AppData\\Local\\Temp\\ipykernel_19820\\1928993369.py:7: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
      "  self.train_dataset = torch.load(self.config.train_data_path)\n",
      "C:\\Users\\azizu\\AppData\\Local\\Temp\\ipykernel_19820\\1928993369.py:8: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
      "  self.test_dataset = torch.load(self.config.test_data_path)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[2024-08-24 19:39:58,617: ERROR: 129140692: Error during model training: pic should be 2/3 dimensional. Got 4 dimensions.]\n"
     ]
    },
    {
     "ename": "ValueError",
     "evalue": "pic should be 2/3 dimensional. Got 4 dimensions.",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[11], line 15\u001b[0m\n\u001b[0;32m     13\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[0;32m     14\u001b[0m     logger\u001b[38;5;241m.\u001b[39merror(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mError during model training: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00me\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m---> 15\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m e\n",
      "Cell \u001b[1;32mIn[11], line 6\u001b[0m\n\u001b[0;32m      4\u001b[0m model_trainer \u001b[38;5;241m=\u001b[39m ModelTrainer(config\u001b[38;5;241m=\u001b[39mmodel_trainer_config)\n\u001b[0;32m      5\u001b[0m model_trainer\u001b[38;5;241m.\u001b[39mload_datasets()\n\u001b[1;32m----> 6\u001b[0m \u001b[43mmodel_trainer\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcreate_dataloaders\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     10\u001b[0m model_trainer\u001b[38;5;241m.\u001b[39minitialize_model()\n\u001b[0;32m     11\u001b[0m model_trainer\u001b[38;5;241m.\u001b[39mtrain_model()\n",
      "Cell \u001b[1;32mIn[10], line 28\u001b[0m, in \u001b[0;36mModelTrainer.create_dataloaders\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m     17\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtrain_dataloader \u001b[38;5;241m=\u001b[39m DataLoader(\n\u001b[0;32m     18\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtrain_dataset, \n\u001b[0;32m     19\u001b[0m     batch_size\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconfig\u001b[38;5;241m.\u001b[39mBATCH_SIZE, \n\u001b[0;32m     20\u001b[0m     shuffle\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m,\n\u001b[0;32m     21\u001b[0m )\n\u001b[0;32m     22\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtest_dataloader \u001b[38;5;241m=\u001b[39m DataLoader(\n\u001b[0;32m     23\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtest_dataset, \n\u001b[0;32m     24\u001b[0m     batch_size\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconfig\u001b[38;5;241m.\u001b[39mBATCH_SIZE, \n\u001b[0;32m     25\u001b[0m     shuffle\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[0;32m     26\u001b[0m )\n\u001b[1;32m---> 28\u001b[0m \u001b[43m\u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mbatch\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtest_dataloader\u001b[49m\u001b[43m:\u001b[49m\n\u001b[0;32m     29\u001b[0m \u001b[43m    \u001b[49m\u001b[43mab\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mL\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mbatch\u001b[49m\n\u001b[0;32m     30\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43mprint\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;124;43mf\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mTrain loader batch - ab shape: \u001b[39;49m\u001b[38;5;132;43;01m{\u001b[39;49;00m\u001b[43mab\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mshape\u001b[49m\u001b[38;5;132;43;01m}\u001b[39;49;00m\u001b[38;5;124;43m, L shape: \u001b[39;49m\u001b[38;5;132;43;01m{\u001b[39;49;00m\u001b[43mL\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mshape\u001b[49m\u001b[38;5;132;43;01m}\u001b[39;49;00m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n",
      "File \u001b[1;32mc:\\Users\\azizu\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\torch\\utils\\data\\dataloader.py:630\u001b[0m, in \u001b[0;36m_BaseDataLoaderIter.__next__\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    627\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_sampler_iter \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m    628\u001b[0m     \u001b[38;5;66;03m# TODO(https://github.com/pytorch/pytorch/issues/76750)\u001b[39;00m\n\u001b[0;32m    629\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_reset()  \u001b[38;5;66;03m# type: ignore[call-arg]\u001b[39;00m\n\u001b[1;32m--> 630\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_next_data\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    631\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_num_yielded \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[0;32m    632\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_dataset_kind \u001b[38;5;241m==\u001b[39m _DatasetKind\u001b[38;5;241m.\u001b[39mIterable \u001b[38;5;129;01mand\u001b[39;00m \\\n\u001b[0;32m    633\u001b[0m         \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_IterableDataset_len_called \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m \\\n\u001b[0;32m    634\u001b[0m         \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_num_yielded \u001b[38;5;241m>\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_IterableDataset_len_called:\n",
      "File \u001b[1;32mc:\\Users\\azizu\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\torch\\utils\\data\\dataloader.py:673\u001b[0m, in \u001b[0;36m_SingleProcessDataLoaderIter._next_data\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    671\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_next_data\u001b[39m(\u001b[38;5;28mself\u001b[39m):\n\u001b[0;32m    672\u001b[0m     index \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_next_index()  \u001b[38;5;66;03m# may raise StopIteration\u001b[39;00m\n\u001b[1;32m--> 673\u001b[0m     data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_dataset_fetcher\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfetch\u001b[49m\u001b[43m(\u001b[49m\u001b[43mindex\u001b[49m\u001b[43m)\u001b[49m  \u001b[38;5;66;03m# may raise StopIteration\u001b[39;00m\n\u001b[0;32m    674\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_pin_memory:\n\u001b[0;32m    675\u001b[0m         data \u001b[38;5;241m=\u001b[39m _utils\u001b[38;5;241m.\u001b[39mpin_memory\u001b[38;5;241m.\u001b[39mpin_memory(data, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_pin_memory_device)\n",
      "File \u001b[1;32mc:\\Users\\azizu\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\torch\\utils\\data\\_utils\\fetch.py:52\u001b[0m, in \u001b[0;36m_MapDatasetFetcher.fetch\u001b[1;34m(self, possibly_batched_index)\u001b[0m\n\u001b[0;32m     50\u001b[0m         data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdataset\u001b[38;5;241m.\u001b[39m__getitems__(possibly_batched_index)\n\u001b[0;32m     51\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m---> 52\u001b[0m         data \u001b[38;5;241m=\u001b[39m \u001b[43m[\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdataset\u001b[49m\u001b[43m[\u001b[49m\u001b[43midx\u001b[49m\u001b[43m]\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43midx\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mpossibly_batched_index\u001b[49m\u001b[43m]\u001b[49m\n\u001b[0;32m     53\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m     54\u001b[0m     data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdataset[possibly_batched_index]\n",
      "File \u001b[1;32mc:\\Users\\azizu\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\torch\\utils\\data\\_utils\\fetch.py:52\u001b[0m, in \u001b[0;36m<listcomp>\u001b[1;34m(.0)\u001b[0m\n\u001b[0;32m     50\u001b[0m         data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdataset\u001b[38;5;241m.\u001b[39m__getitems__(possibly_batched_index)\n\u001b[0;32m     51\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m---> 52\u001b[0m         data \u001b[38;5;241m=\u001b[39m [\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdataset\u001b[49m\u001b[43m[\u001b[49m\u001b[43midx\u001b[49m\u001b[43m]\u001b[49m \u001b[38;5;28;01mfor\u001b[39;00m idx \u001b[38;5;129;01min\u001b[39;00m possibly_batched_index]\n\u001b[0;32m     53\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m     54\u001b[0m     data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdataset[possibly_batched_index]\n",
      "File \u001b[1;32mc:\\mlops project\\image-colorization-mlops\\src\\imagecolorization\\conponents\\data_tranformation.py:22\u001b[0m, in \u001b[0;36mImageColorizationDataset.__getitem__\u001b[1;34m(self, idx)\u001b[0m\n\u001b[0;32m     20\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__getitem__\u001b[39m(\u001b[38;5;28mself\u001b[39m, idx):\n\u001b[0;32m     21\u001b[0m     L \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39marray(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdataset[\u001b[38;5;241m0\u001b[39m][idx])\u001b[38;5;241m.\u001b[39mreshape(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mimage_size \u001b[38;5;241m+\u001b[39m (\u001b[38;5;241m1\u001b[39m,))\n\u001b[1;32m---> 22\u001b[0m     L \u001b[38;5;241m=\u001b[39m \u001b[43mtransforms\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mToTensor\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m(\u001b[49m\u001b[43mL\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     24\u001b[0m     ab \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39marray(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdataset[\u001b[38;5;241m1\u001b[39m][idx])\n\u001b[0;32m     25\u001b[0m     ab \u001b[38;5;241m=\u001b[39m transforms\u001b[38;5;241m.\u001b[39mToTensor()(ab)\n",
      "File \u001b[1;32mc:\\Users\\azizu\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\torchvision\\transforms\\transforms.py:137\u001b[0m, in \u001b[0;36mToTensor.__call__\u001b[1;34m(self, pic)\u001b[0m\n\u001b[0;32m    129\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__call__\u001b[39m(\u001b[38;5;28mself\u001b[39m, pic):\n\u001b[0;32m    130\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m    131\u001b[0m \u001b[38;5;124;03m    Args:\u001b[39;00m\n\u001b[0;32m    132\u001b[0m \u001b[38;5;124;03m        pic (PIL Image or numpy.ndarray): Image to be converted to tensor.\u001b[39;00m\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    135\u001b[0m \u001b[38;5;124;03m        Tensor: Converted image.\u001b[39;00m\n\u001b[0;32m    136\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[1;32m--> 137\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mF\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mto_tensor\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpic\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[1;32mc:\\Users\\azizu\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\torchvision\\transforms\\functional.py:145\u001b[0m, in \u001b[0;36mto_tensor\u001b[1;34m(pic)\u001b[0m\n\u001b[0;32m    142\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpic should be PIL Image or ndarray. Got \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mtype\u001b[39m(pic)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m    144\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m _is_numpy(pic) \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m _is_numpy_image(pic):\n\u001b[1;32m--> 145\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpic should be 2/3 dimensional. Got \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpic\u001b[38;5;241m.\u001b[39mndim\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m dimensions.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m    147\u001b[0m default_float_dtype \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39mget_default_dtype()\n\u001b[0;32m    149\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(pic, np\u001b[38;5;241m.\u001b[39mndarray):\n\u001b[0;32m    150\u001b[0m     \u001b[38;5;66;03m# handle numpy array\u001b[39;00m\n",
      "\u001b[1;31mValueError\u001b[0m: pic should be 2/3 dimensional. Got 4 dimensions."
     ]
    }
   ],
   "source": [
    "try:\n",
    "    config_manager = ConfigurationManager()\n",
    "    model_trainer_config = config_manager.get_model_trainer_config()\n",
    "    model_trainer = ModelTrainer(config=model_trainer_config)\n",
    "    model_trainer.load_datasets()\n",
    "    model_trainer.create_dataloaders()\n",
    "    \n",
    "    \n",
    "\n",
    "    model_trainer.initialize_model()\n",
    "    model_trainer.train_model()\n",
    "    model_trainer.save_model()\n",
    "except Exception as e:\n",
    "    logger.error(f\"Error during model training: {e}\")\n",
    "    raise e"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "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": "3.11.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}