mirror of
https://github.com/clearml/clearml
synced 2025-06-26 18:16:07 +00:00
Added text classification example and updated image and audio examples
This commit is contained in:
danmalowany-allegro
parent
53d0da373f
commit
8cb7c8130a
@ -1,380 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "e-YsQrBjzNdX"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"! pip install -U pip\n",
|
||||
"! pip install -U torch==1.5.0\n",
|
||||
"! pip install -U torchaudio==0.5.0\n",
|
||||
"! pip install -U torchvision==0.6.0\n",
|
||||
"! pip install -U matplotlib==3.2.1\n",
|
||||
"! pip install -U trains==0.15.0\n",
|
||||
"! pip install -U pandas==1.0.4\n",
|
||||
"! pip install -U numpy==1.18.4\n",
|
||||
"! pip install -U tensorboard==2.2.1"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "T7T0Rf26zNdm"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import PIL\n",
|
||||
"import io\n",
|
||||
"\n",
|
||||
"import pandas as pd\n",
|
||||
"import numpy as np\n",
|
||||
"from pathlib2 import Path\n",
|
||||
"import matplotlib.pyplot as plt\n",
|
||||
"\n",
|
||||
"import torch\n",
|
||||
"import torch.nn as nn\n",
|
||||
"import torch.nn.functional as F\n",
|
||||
"import torch.optim as optim\n",
|
||||
"from torch.utils.data import Dataset\n",
|
||||
"from torch.utils.tensorboard import SummaryWriter\n",
|
||||
"\n",
|
||||
"import torchaudio\n",
|
||||
"from torchvision.transforms import ToTensor\n",
|
||||
"\n",
|
||||
"from trains import Task\n",
|
||||
"\n",
|
||||
"%matplotlib inline"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"task = Task.init(project_name='Audio Example', task_name='audio classifier')\n",
|
||||
"configuration_dict = {'number_of_epochs': 10, 'batch_size': 4, 'dropout': 0.25, 'base_lr': 0.001}\n",
|
||||
"configuration_dict = task.connect(configuration_dict) # enabling configuration override by trains\n",
|
||||
"print(configuration_dict) # printing actual configuration (after override in remote mode)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "msiz7QdvzNeA",
|
||||
"scrolled": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Download UrbanSound8K dataset (https://urbansounddataset.weebly.com/urbansound8k.html)\n",
|
||||
"path_to_UrbanSound8K = './data/UrbanSound8K'"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "wXtmZe7yzNeS"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"class UrbanSoundDataset(Dataset):\n",
|
||||
"#rapper for the UrbanSound8K dataset\n",
|
||||
" def __init__(self, csv_path, file_path, folderList):\n",
|
||||
" self.file_path = file_path\n",
|
||||
" self.file_names = []\n",
|
||||
" self.labels = []\n",
|
||||
" self.folders = []\n",
|
||||
" \n",
|
||||
" #loop through the csv entries and only add entries from folders in the folder list\n",
|
||||
" csvData = pd.read_csv(csv_path)\n",
|
||||
" for i in range(0,len(csvData)):\n",
|
||||
" if csvData.iloc[i, 5] in folderList:\n",
|
||||
" self.file_names.append(csvData.iloc[i, 0])\n",
|
||||
" self.labels.append(csvData.iloc[i, 6])\n",
|
||||
" self.folders.append(csvData.iloc[i, 5])\n",
|
||||
" \n",
|
||||
" def __getitem__(self, index):\n",
|
||||
" #format the file path and load the file\n",
|
||||
" path = self.file_path / (\"fold\" + str(self.folders[index])) / self.file_names[index]\n",
|
||||
" sound, sample_rate = torchaudio.load(path, out = None, normalization = True)\n",
|
||||
"\n",
|
||||
" # UrbanSound8K uses two channels, this will convert them to one\n",
|
||||
" soundData = torch.mean(sound, dim=0, keepdim=True)\n",
|
||||
" \n",
|
||||
" #Make sure all files are the same size\n",
|
||||
" if soundData.numel() < 160000:\n",
|
||||
" fixedsize_data = torch.nn.functional.pad(soundData, (0, 160000 - soundData.numel()))\n",
|
||||
" else:\n",
|
||||
" fixedsize_data = soundData[0,:160000].reshape(1,160000)\n",
|
||||
" \n",
|
||||
" #downsample the audio\n",
|
||||
" downsample_data = fixedsize_data[::5]\n",
|
||||
" \n",
|
||||
" melspectogram_transform = torchaudio.transforms.MelSpectrogram(sample_rate=sample_rate)\n",
|
||||
" melspectogram = melspectogram_transform(downsample_data)\n",
|
||||
" melspectogram_db = torchaudio.transforms.AmplitudeToDB()(melspectogram)\n",
|
||||
"\n",
|
||||
" return fixedsize_data, sample_rate, melspectogram_db, self.labels[index]\n",
|
||||
" \n",
|
||||
" def __len__(self):\n",
|
||||
" return len(self.file_names)\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"csv_path = Path(path_to_UrbanSound8K) / 'metadata' / 'UrbanSound8K.csv'\n",
|
||||
"file_path = Path(path_to_UrbanSound8K) / 'audio'\n",
|
||||
"\n",
|
||||
"train_set = UrbanSoundDataset(csv_path, file_path, range(1,10))\n",
|
||||
"test_set = UrbanSoundDataset(csv_path, file_path, [10])\n",
|
||||
"print(\"Train set size: \" + str(len(train_set)))\n",
|
||||
"print(\"Test set size: \" + str(len(test_set)))\n",
|
||||
"\n",
|
||||
"train_loader = torch.utils.data.DataLoader(train_set, batch_size = configuration_dict.get('batch_size', 4), \n",
|
||||
" shuffle = True, pin_memory=True, num_workers=1)\n",
|
||||
"test_loader = torch.utils.data.DataLoader(test_set, batch_size = configuration_dict.get('batch_size', 4), \n",
|
||||
" shuffle = False, pin_memory=True, num_workers=1)\n",
|
||||
"\n",
|
||||
"classes = ('air_conditioner', 'car_horn', 'children_playing', 'dog_bark', 'drilling', 'engine_idling', \n",
|
||||
" 'gun_shot', 'jackhammer', 'siren', 'street_music')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "ylblw-k1zNeZ"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"class Net(nn.Module):\n",
|
||||
" def __init__(self, num_classes, dropout_value):\n",
|
||||
" super(Net,self).__init__()\n",
|
||||
" self.num_classes = num_classes\n",
|
||||
" self.dropout_value = dropout_value\n",
|
||||
" \n",
|
||||
" self.C1 = nn.Conv2d(1,16,3)\n",
|
||||
" self.C2 = nn.Conv2d(16,32,3)\n",
|
||||
" self.C3 = nn.Conv2d(32,64,3)\n",
|
||||
" self.C4 = nn.Conv2d(64,128,3)\n",
|
||||
" self.maxpool1 = nn.MaxPool2d(2,2) \n",
|
||||
" self.fc1 = nn.Linear(128*29*197,128)\n",
|
||||
" self.fc2 = nn.Linear(128,self.num_classes)\n",
|
||||
" self.dropout = nn.Dropout(self.dropout_value)\n",
|
||||
" \n",
|
||||
" def forward(self,x):\n",
|
||||
" # add sequence of convolutional and max pooling layers\n",
|
||||
" x = F.relu(self.C1(x))\n",
|
||||
" x = self.maxpool1(F.relu(self.C2(x)))\n",
|
||||
" x = F.relu(self.C3(x))\n",
|
||||
" x = self.maxpool1(F.relu(self.C4(x)))\n",
|
||||
" # flatten image input\n",
|
||||
" x = x.view(-1,128*29*197)\n",
|
||||
" x = F.relu(self.fc1(self.dropout(x)))\n",
|
||||
" x = self.fc2(self.dropout(x))\n",
|
||||
" return x\n",
|
||||
" \n",
|
||||
" \n",
|
||||
"model = Net(len(classes), configuration_dict.get('dropout', 0.25))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "3yKYru14zNef"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"optimizer = optim.SGD(model.parameters(), lr = configuration_dict.get('base_lr', 0.001), momentum = 0.9)\n",
|
||||
"scheduler = optim.lr_scheduler.StepLR(optimizer, step_size = 3, gamma = 0.1)\n",
|
||||
"criterion = nn.CrossEntropyLoss()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"device = torch.cuda.current_device() if torch.cuda.is_available() else torch.device('cpu')\n",
|
||||
"print('Device to use: {}'.format(device))\n",
|
||||
"model.to(device)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tensorboard_writer = SummaryWriter('./tensorboard_logs')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def plot_signal(signal, title, cmap=None):\n",
|
||||
" fig = plt.figure()\n",
|
||||
" if signal.ndim == 1:\n",
|
||||
" plt.plot(signal)\n",
|
||||
" else:\n",
|
||||
" plt.imshow(signal, cmap=cmap) \n",
|
||||
" plt.title(title)\n",
|
||||
" \n",
|
||||
" plot_buf = io.BytesIO()\n",
|
||||
" plt.savefig(plot_buf, format='jpeg')\n",
|
||||
" plot_buf.seek(0)\n",
|
||||
" plt.close(fig)\n",
|
||||
" return ToTensor()(PIL.Image.open(plot_buf))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "Vdthqz3JzNem"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def train(model, epoch):\n",
|
||||
" model.train()\n",
|
||||
" for batch_idx, (sounds, sample_rate, inputs, labels) in enumerate(train_loader):\n",
|
||||
" inputs = inputs.to(device)\n",
|
||||
" labels = labels.to(device)\n",
|
||||
"\n",
|
||||
" # zero the parameter gradients\n",
|
||||
" optimizer.zero_grad()\n",
|
||||
"\n",
|
||||
" # forward + backward + optimize\n",
|
||||
" outputs = model(inputs)\n",
|
||||
" _, predicted = torch.max(outputs, 1)\n",
|
||||
" loss = criterion(outputs, labels)\n",
|
||||
" loss.backward()\n",
|
||||
" optimizer.step()\n",
|
||||
" \n",
|
||||
" iteration = epoch * len(train_loader) + batch_idx\n",
|
||||
" if batch_idx % log_interval == 0: #print training stats\n",
|
||||
" print('Train Epoch: {} [{}/{} ({:.0f}%)]\\tLoss: {:.6f}'\n",
|
||||
" .format(epoch, batch_idx * len(inputs), len(train_loader.dataset), \n",
|
||||
" 100. * batch_idx / len(train_loader), loss))\n",
|
||||
" tensorboard_writer.add_scalar('training loss/loss', loss, iteration)\n",
|
||||
" tensorboard_writer.add_scalar('learning rate/lr', optimizer.param_groups[0]['lr'], iteration)\n",
|
||||
" \n",
|
||||
" \n",
|
||||
" if batch_idx % debug_interval == 0: # report debug image every 500 mini-batches\n",
|
||||
" for n, (inp, pred, label) in enumerate(zip(inputs, predicted, labels)):\n",
|
||||
" series = 'label_{}_pred_{}'.format(classes[label.cpu()], classes[pred.cpu()])\n",
|
||||
" tensorboard_writer.add_image('Train MelSpectrogram samples/{}'.format(n), \n",
|
||||
" plot_signal(inp.cpu().numpy().squeeze(), series, 'hot'), iteration)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "LBWoj7u5zNes"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def test(model, epoch):\n",
|
||||
" model.eval()\n",
|
||||
" class_correct = list(0. for i in range(10))\n",
|
||||
" class_total = list(0. for i in range(10))\n",
|
||||
" with torch.no_grad():\n",
|
||||
" for idx, (sounds, sample_rate, inputs, labels) in enumerate(test_loader):\n",
|
||||
" inputs = inputs.to(device)\n",
|
||||
" labels = labels.to(device)\n",
|
||||
"\n",
|
||||
" outputs = model(inputs)\n",
|
||||
"\n",
|
||||
" _, predicted = torch.max(outputs, 1)\n",
|
||||
" c = (predicted == labels)\n",
|
||||
" for i in range(len(inputs)):\n",
|
||||
" label = labels[i].item()\n",
|
||||
" class_correct[label] += c[i].item()\n",
|
||||
" class_total[label] += 1\n",
|
||||
" \n",
|
||||
" iteration = (epoch + 1) * len(train_loader)\n",
|
||||
" if idx % debug_interval == 0: # report debug image every 100 mini-batches\n",
|
||||
" for n, (sound, inp, pred, label) in enumerate(zip(sounds, inputs, predicted, labels)):\n",
|
||||
" series = 'label_{}_pred_{}'.format(classes[label.cpu()], classes[pred.cpu()])\n",
|
||||
" tensorboard_writer.add_audio('Test audio samples/{}'.format(n), \n",
|
||||
" sound, iteration, int(sample_rate[n]))\n",
|
||||
" tensorboard_writer.add_image('Test MelSpectrogram samples/{}_{}'.format(idx, n), \n",
|
||||
" plot_signal(inp.cpu().numpy().squeeze(), series, 'hot'), iteration)\n",
|
||||
"\n",
|
||||
" total_accuracy = 100 * sum(class_correct)/sum(class_total)\n",
|
||||
" print('[Iteration {}] Accuracy on the {} test images: {}%\\n'.format(epoch, sum(class_total), total_accuracy))\n",
|
||||
" tensorboard_writer.add_scalar('accuracy/total', total_accuracy, iteration)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "X5lx3g_5zNey",
|
||||
"scrolled": false
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"log_interval = 100\n",
|
||||
"debug_interval = 200\n",
|
||||
"for epoch in range(configuration_dict.get('number_of_epochs', 10)):\n",
|
||||
" train(model, epoch)\n",
|
||||
" test(model, epoch)\n",
|
||||
" scheduler.step()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"name": "audio_classifier_tutorial.ipynb",
|
||||
"provenance": []
|
||||
},
|
||||
"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": 1
|
||||
}
|
||||
@ -12,7 +12,7 @@
|
||||
"! pip install -U torch==1.5.0\n",
|
||||
"! pip install -U torchaudio==0.5.0\n",
|
||||
"! pip install -U matplotlib==3.2.1\n",
|
||||
"! pip install -U trains==0.15.0\n",
|
||||
"! pip install -U trains>=0.15.0\n",
|
||||
"! pip install -U tensorboard==2.2.1"
|
||||
]
|
||||
},
|
||||
@ -87,10 +87,10 @@
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"scrolled": true,
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"scrolled": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@ -125,4 +125,4 @@
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 1
|
||||
}
|
||||
}
|
||||
|
||||
@ -133,4 +133,4 @@
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
}
|
||||
|
||||
@ -45,7 +45,7 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"task = Task.init(project_name='Hyper-Parameter Search', task_name='image_classification_CIFAR10')\n",
|
||||
"task = Task.init(project_name='Image Example', task_name='image_classification_CIFAR10')\n",
|
||||
"configuration_dict = {'number_of_epochs': 3, 'batch_size': 4, 'dropout': 0.25, 'base_lr': 0.001}\n",
|
||||
"configuration_dict = task.connect(configuration_dict) # enabling configuration override by trains\n",
|
||||
"print(configuration_dict) # printing actual configuration (after override in remote mode)"
|
||||
|
||||
Loading…
Reference in New Issue
Block a user