Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Updated timm imports #61

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
Open

Updated timm imports #61

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
9129911
updated imports
y-arjun-y Jul 23, 2023
b60a655
updated imports
y-arjun-y Jul 23, 2023
e0f6552
replaced with pytorch
y-arjun-y Aug 5, 2023
c81f719
final (?) commit
y-arjun-y Aug 13, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
236 changes: 236 additions & 0 deletions MNIST_VAE.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,236 @@
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"gpuType": "V100",
"authorship_tag": "ABX9TyNFv7cc7urUaP8u9gPrfY3s",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
},
"accelerator": "GPU"
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/github/y-arjun-y/EfficientFormer/blob/main/MNIST_VAE.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "code",
"source": [
"import torch\n",
"import torch.nn as nn\n",
"import torch.nn.functional as F\n",
"import torch.optim as optim\n",
"from torchvision import datasets, transforms\n",
"from torch.autograd import Variable\n",
"from torchvision.utils import save_image\n",
"\n",
"class VAE(nn.Module):\n",
" def __init__(self, x_dim, h_dim1, h_dim2, z_dim):\n",
" super(VAE, self).__init__()\n",
"\n",
" # encoder part\n",
" self.fc1 = nn.Linear(x_dim, h_dim1)\n",
" self.fc2 = nn.Linear(h_dim1, h_dim2)\n",
" self.fc31 = nn.Linear(h_dim2, z_dim)\n",
" self.fc32 = nn.Linear(h_dim2, z_dim)\n",
" # decoder part\n",
" self.fc4 = nn.Linear(z_dim, h_dim2)\n",
" self.fc5 = nn.Linear(h_dim2, h_dim1)\n",
" self.fc6 = nn.Linear(h_dim1, x_dim)\n",
"\n",
" def encoder(self, x):\n",
" h = F.relu(self.fc1(x))\n",
" h = F.relu(self.fc2(h))\n",
" return self.fc31(h), self.fc32(h) # mu, log_var\n",
"\n",
" def sampling(self, mu, log_var):\n",
" std = torch.exp(0.5*log_var)\n",
" eps = torch.randn_like(std)\n",
" return eps.mul(std).add_(mu) # return z sample\n",
"\n",
" def decoder(self, z):\n",
" h = F.relu(self.fc4(z))\n",
" h = F.relu(self.fc5(h))\n",
" return F.sigmoid(self.fc6(h))\n",
"\n",
" def forward(self, x):\n",
" mu, log_var = self.encoder(x.view(-1, 784))\n",
" z = self.sampling(mu, log_var)\n",
" return self.decoder(z), mu, log_var\n",
"\n",
"# build model\n",
"vae = VAE(x_dim=784, h_dim1= 512, h_dim2=256, z_dim=2)\n",
"if torch.cuda.is_available():\n",
" vae.cuda()"
],
"metadata": {
"id": "aUrAwRsuczhT"
},
"execution_count": 5,
"outputs": []
},
{
"cell_type": "code",
"source": [
"optimizer = optim.Adam(vae.parameters())\n",
"# return reconstruction error + KL divergence losses\n",
"def loss_function(recon_x, x, mu, log_var):\n",
" BCE = F.binary_cross_entropy(recon_x, x.view(-1, 784), reduction='sum')\n",
" KLD = -0.5 * torch.sum(1 + log_var - mu.pow(2) - log_var.exp())\n",
" return BCE + KLD"
],
"metadata": {
"id": "wjm2uRBuCwRw"
},
"execution_count": 6,
"outputs": []
},
{
"cell_type": "code",
"source": [
"def train(epoch):\n",
" vae.train()\n",
" train_loss = 0\n",
" for batch_idx, (data, _) in enumerate(train_loader):\n",
" data = data.cuda()\n",
" optimizer.zero_grad()\n",
"\n",
" recon_batch, mu, log_var = vae(data)\n",
" loss = loss_function(recon_batch, data, mu, log_var)\n",
"\n",
" loss.backward()\n",
" train_loss += loss.item()\n",
" optimizer.step()\n",
"\n",
" if batch_idx % 100 == 0:\n",
" print('Train Epoch: {} [{}/{} ({:.0f}%)]\\tLoss: {:.6f}'.format(\n",
" epoch, batch_idx * len(data), len(train_loader.dataset),\n",
" 100. * batch_idx / len(train_loader), loss.item() / len(data)))\n",
" print('====> Epoch: {} Average loss: {:.4f}'.format(epoch, train_loss / len(train_loader.dataset)))"
],
"metadata": {
"id": "uEW-KyH9CyRl"
},
"execution_count": 7,
"outputs": []
},
{
"cell_type": "code",
"source": [
"def test():\n",
" vae.eval()\n",
" test_loss= 0\n",
" with torch.no_grad():\n",
" for data, _ in test_loader:\n",
" data = data.cuda()\n",
" recon, mu, log_var = vae(data)\n",
"\n",
" # sum up batch loss\n",
" test_loss += loss_function(recon, data, mu, log_var).item()\n",
"\n",
" test_loss /= len(test_loader.dataset)\n",
" print('====> Test set loss: {:.4f}'.format(test_loss))"
],
"metadata": {
"id": "KzRp7-ejC3-c"
},
"execution_count": 9,
"outputs": []
},
{
"cell_type": "code",
"source": [
"bs = 100\n",
"# MNIST Dataset\n",
"train_dataset = datasets.MNIST(root='./mnist_data/', train=True, transform=transforms.ToTensor(), download=True)\n",
"test_dataset = datasets.MNIST(root='./mnist_data/', train=False, transform=transforms.ToTensor(), download=False)\n",
"\n",
"# Data Loader (Input Pipeline)\n",
"train_loader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=bs, shuffle=True)\n",
"test_loader = torch.utils.data.DataLoader(dataset=test_dataset, batch_size=bs, shuffle=False)\n",
"\n",
"for epoch in range(1, 5):\n",
" train(epoch)\n",
" test()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "ZZw1jZc6C5ej",
"outputId": "6313b1c8-1b6d-4ab3-f6aa-a96b893bcbe4"
},
"execution_count": 14,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Train Epoch: 1 [0/60000 (0%)]\tLoss: 132.513184\n",
"Train Epoch: 1 [10000/60000 (17%)]\tLoss: 145.551279\n",
"Train Epoch: 1 [20000/60000 (33%)]\tLoss: 143.799668\n",
"Train Epoch: 1 [30000/60000 (50%)]\tLoss: 144.562568\n",
"Train Epoch: 1 [40000/60000 (67%)]\tLoss: 133.205791\n",
"Train Epoch: 1 [50000/60000 (83%)]\tLoss: 134.887256\n",
"====> Epoch: 1 Average loss: 141.1480\n",
"====> Test set loss: 142.4788\n",
"Train Epoch: 2 [0/60000 (0%)]\tLoss: 141.568389\n",
"Train Epoch: 2 [10000/60000 (17%)]\tLoss: 131.814111\n",
"Train Epoch: 2 [20000/60000 (33%)]\tLoss: 131.404941\n",
"Train Epoch: 2 [30000/60000 (50%)]\tLoss: 135.604023\n",
"Train Epoch: 2 [40000/60000 (67%)]\tLoss: 138.471006\n",
"Train Epoch: 2 [50000/60000 (83%)]\tLoss: 143.901602\n",
"====> Epoch: 2 Average loss: 140.6990\n",
"====> Test set loss: 141.7708\n",
"Train Epoch: 3 [0/60000 (0%)]\tLoss: 151.875791\n",
"Train Epoch: 3 [10000/60000 (17%)]\tLoss: 143.209922\n",
"Train Epoch: 3 [20000/60000 (33%)]\tLoss: 136.077578\n",
"Train Epoch: 3 [30000/60000 (50%)]\tLoss: 137.678623\n",
"Train Epoch: 3 [40000/60000 (67%)]\tLoss: 132.750098\n",
"Train Epoch: 3 [50000/60000 (83%)]\tLoss: 138.461543\n",
"====> Epoch: 3 Average loss: 140.3149\n",
"====> Test set loss: 141.3095\n",
"Train Epoch: 4 [0/60000 (0%)]\tLoss: 141.891445\n",
"Train Epoch: 4 [10000/60000 (17%)]\tLoss: 136.609824\n",
"Train Epoch: 4 [20000/60000 (33%)]\tLoss: 138.829805\n",
"Train Epoch: 4 [30000/60000 (50%)]\tLoss: 139.648555\n",
"Train Epoch: 4 [40000/60000 (67%)]\tLoss: 140.374023\n",
"Train Epoch: 4 [50000/60000 (83%)]\tLoss: 132.872568\n",
"====> Epoch: 4 Average loss: 140.0112\n",
"====> Test set loss: 141.5408\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"with torch.no_grad():\n",
" z = torch.randn(64, 2).cuda()\n",
" sample = vae.decoder(z).cuda()\n",
"\n",
" save_image(sample.view(64, 1, 28, 28), 'a.png')"
],
"metadata": {
"id": "11Vv5N75g1ND"
},
"execution_count": 20,
"outputs": []
}
]
}
3 changes: 1 addition & 2 deletions detection/backbone.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,9 +8,8 @@
import itertools

from timm.data import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD
from timm.models.layers import DropPath, trunc_normal_
from timm.models.layers import DropPath, trunc_normal_, to_2tuple
from timm.models.registry import register_model
from timm.models.layers.helpers import to_2tuple

try:
from mmdet.models.builder import BACKBONES as det_BACKBONES
Expand Down
3 changes: 1 addition & 2 deletions detection/backbonev2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,9 +8,8 @@
import itertools

from timm.data import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD
from timm.models.layers import DropPath, trunc_normal_
from timm.models.layers import DropPath, trunc_normal_, to_2tuple
from timm.models.registry import register_model
from timm.models.layers.helpers import to_2tuple

try:
from mmdet.models.builder import BACKBONES as det_BACKBONES
Expand Down
3 changes: 1 addition & 2 deletions models/efficientformer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,9 +10,8 @@
import itertools

from timm.data import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD
from timm.models.layers import DropPath, trunc_normal_
from timm.models.layers import DropPath, trunc_normal_, to_2tuple
from timm.models.registry import register_model
from timm.models.layers.helpers import to_2tuple

EfficientFormer_width = {
'l1': [48, 96, 224, 448],
Expand Down
3 changes: 1 addition & 2 deletions models/efficientformer_v2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,9 +11,8 @@
import itertools

from timm.data import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD
from timm.models.layers import DropPath, trunc_normal_
from timm.models.layers import DropPath, trunc_normal_, to_2tuple
from timm.models.registry import register_model
from timm.models.layers.helpers import to_2tuple

EfficientFormer_width = {
'L': [40, 80, 192, 384], # 26m 83.3% 6attn
Expand Down
3 changes: 1 addition & 2 deletions segmentation/backbone.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,9 +11,8 @@
import itertools

from timm.data import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD
from timm.models.layers import DropPath, trunc_normal_
from timm.models.layers import DropPath, trunc_normal_, to_2tuple
from timm.models.registry import register_model
from timm.models.layers.helpers import to_2tuple

try:
from mmseg.models.builder import BACKBONES as seg_BACKBONES
Expand Down
3 changes: 1 addition & 2 deletions segmentation/backbonev2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,9 +8,8 @@
import itertools

from timm.data import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD
from timm.models.layers import DropPath, trunc_normal_
from timm.models.layers import DropPath, trunc_normal_, to_2tuple
from timm.models.registry import register_model
from timm.models.layers.helpers import to_2tuple

try:
from mmseg.models.builder import BACKBONES as seg_BACKBONES
Expand Down