|
|
--- |
|
|
library_name: keras |
|
|
tags: |
|
|
- keras |
|
|
pipeline_tag: image-to-text |
|
|
--- |
|
|
``` |
|
|
API_URL = "https://api-inference.huggingface.co/models/CIS-5190-CIA/Ensamble" |
|
|
|
|
|
from huggingface_hub import InferenceClient |
|
|
|
|
|
client = InferenceClient( |
|
|
"CIS-5190-CIA/Ensamble", |
|
|
token="TOKEN HERE", |
|
|
) |
|
|
``` |
|
|
|
|
|
## How to Run |
|
|
In the notebook Run_ensamble.ipynb, replace the line: |
|
|
```python |
|
|
dataset_test = load_dataset("gydou/released_img") |
|
|
``` |
|
|
with the proper location of the testing dataset. |
|
|
|
|
|
## Training Dataset Statistics |
|
|
```python |
|
|
lat_mean = 39.95173281562989 |
|
|
lat_std = 0.0006925131397316982 |
|
|
lon_mean = -75.19143805846498 |
|
|
lon_std = 0.0006552266653111098 |
|
|
``` |
|
|
|
|
|
## Helper Functions to Predict from & Evaluate Ensamble |
|
|
These functions will allow you to use the ensamble to predict and evaluate the model |
|
|
|
|
|
They use the following paramaters: |
|
|
- models: this is a dictionary of the models, in the format of: |
|
|
``` |
|
|
models = { |
|
|
"RNNModel1": CNNModel1(num_outputs=2).to(device), |
|
|
"RNNModel2": CNNModel2(num_outputs=2).to(device), |
|
|
"RNNModel3": CNNModel3(num_outputs=2).to(device), |
|
|
} |
|
|
``` |
|
|
- dataloader: this is the data loader provided to us for the project |
|
|
- lat_mean, lon_mean, lat_std, lon_std |
|
|
|
|
|
|
|
|
|
|
|
``` |
|
|
def ensemble_predict(models, dataloader, lat_mean, lon_mean, lat_std, lon_std): |
|
|
model_outputs = [] |
|
|
for model_name, model in models.items(): |
|
|
model.eval() |
|
|
outputs = [] |
|
|
with torch.no_grad(): |
|
|
for images, _ in dataloader: |
|
|
images = images.to(device) |
|
|
outputs.append(model(images)) |
|
|
model_outputs.append(torch.cat(outputs, dim=0)) |
|
|
|
|
|
# average the predictions across all models |
|
|
ensemble_output = torch.stack(model_outputs, dim=0).mean(dim=0) |
|
|
|
|
|
# denormalize the ensemble predictions |
|
|
ensemble_output_denorm = ensemble_output.cpu().numpy() * np.array([lat_std, lon_std]) + np.array([lat_mean, lon_mean]) |
|
|
return ensemble_output_denorm |
|
|
|
|
|
# evaluate Ensemble with Geodesic Distance |
|
|
def evaluate_ensemble(models, dataloader, lat_mean, lon_mean, lat_std, lon_std): |
|
|
ensemble_outputs = ensemble_predict(models, dataloader, lat_mean, lon_mean, lat_std, lon_std) |
|
|
|
|
|
all_targets = [] |
|
|
for _, targets in dataloader: |
|
|
all_targets.append(targets) |
|
|
all_targets = torch.cat(all_targets, dim=0).cpu().numpy() |
|
|
all_targets_denorm = all_targets * np.array([lat_std, lon_std]) + np.array([lat_mean, lon_mean]) |
|
|
|
|
|
total_samples = all_targets_denorm.shape[0] |
|
|
ensemble_loss = 0.0 |
|
|
|
|
|
# compute Geodesic Distance Metrics |
|
|
for pred, actual in zip(ensemble_outputs, all_targets_denorm): |
|
|
distance = geodesic((actual[0], actual[1]), (pred[0], pred[1])).meters |
|
|
ensemble_loss += distance ** 2 |
|
|
|
|
|
ensemble_loss /= total_samples |
|
|
ensemble_rmse = np.sqrt(ensemble_loss) |
|
|
return ensemble_loss, ensemble_rmse |
|
|
``` |
|
|
|
|
|
# Our Custom Models for the ensamble |
|
|
|
|
|
We used the following 3 model architectures and then created the ensamble to create an output |
|
|
|
|
|
## Model 1: |
|
|
``` |
|
|
class CNNModel1(nn.Module): |
|
|
def __init__(self, num_outputs=2): |
|
|
super(CNNModel1, self).__init__() |
|
|
self.features = nn.Sequential( |
|
|
nn.Conv2d(3, 64, kernel_size=11, stride=4, padding=2), |
|
|
nn.ReLU(inplace=True), |
|
|
nn.MaxPool2d(kernel_size=3, stride=2), |
|
|
nn.BatchNorm2d(64), |
|
|
nn.Conv2d(64, 192, kernel_size=5, padding=2), |
|
|
nn.ReLU(inplace=True), |
|
|
nn.MaxPool2d(kernel_size=3, stride=2), |
|
|
nn.BatchNorm2d(192), |
|
|
nn.Conv2d(192, 384, kernel_size=3, padding=1), |
|
|
nn.ReLU(inplace=True), |
|
|
nn.Conv2d(384, 256, kernel_size=3, padding=1), |
|
|
nn.ReLU(inplace=True), |
|
|
nn.Conv2d(256, 256, kernel_size=3, padding=1), |
|
|
nn.ReLU(inplace=True), |
|
|
nn.MaxPool2d(kernel_size=3, stride=2) |
|
|
) |
|
|
self.classifier = nn.Sequential( |
|
|
nn.Dropout(), |
|
|
nn.Linear(256 * 6 * 6, 4096), |
|
|
nn.ReLU(inplace=True), |
|
|
nn.Dropout(), |
|
|
nn.Linear(4096, 4096), |
|
|
nn.ReLU(inplace=True), |
|
|
nn.Linear(4096, num_outputs) |
|
|
) |
|
|
|
|
|
def forward(self, x): |
|
|
x = self.features(x) |
|
|
x = x.view(x.size(0), -1) |
|
|
x = self.classifier(x) |
|
|
return x |
|
|
``` |
|
|
## Model 2: |
|
|
``` |
|
|
class ResidualBlock(nn.Module): |
|
|
def __init__(self, in_channels, out_channels, stride=1, downsample=None): |
|
|
super(ResidualBlock, self).__init__() |
|
|
self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride, padding=1) |
|
|
self.bn1 = nn.BatchNorm2d(out_channels) |
|
|
self.relu = nn.ReLU(inplace=True) |
|
|
self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=1) |
|
|
self.bn2 = nn.BatchNorm2d(out_channels) |
|
|
self.downsample = downsample |
|
|
|
|
|
def forward(self, x): |
|
|
identity = x |
|
|
if self.downsample: |
|
|
identity = self.downsample(x) |
|
|
out = self.conv1(x) |
|
|
out = self.bn1(out) |
|
|
out = self.relu(out) |
|
|
out = self.conv2(out) |
|
|
out = self.bn2(out) |
|
|
out += identity |
|
|
out = self.relu(out) |
|
|
return out |
|
|
|
|
|
class CNNModel2(nn.Module): |
|
|
def __init__(self, num_outputs=2): |
|
|
super(CNNModel2, self).__init__() |
|
|
self.in_channels = 64 |
|
|
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3) |
|
|
self.bn1 = nn.BatchNorm2d(64) |
|
|
self.relu = nn.ReLU(inplace=True) |
|
|
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) |
|
|
|
|
|
self.layer1 = self._make_layer(64, 2, stride=1) |
|
|
self.layer2 = self._make_layer(128, 2, stride=2) |
|
|
self.layer3 = self._make_layer(256, 2, stride=2) |
|
|
self.layer4 = self._make_layer(512, 2, stride=2) |
|
|
|
|
|
self.avgpool = nn.AdaptiveAvgPool2d((1, 1)) |
|
|
self.fc = nn.Linear(512, num_outputs) |
|
|
|
|
|
def _make_layer(self, out_channels, blocks, stride): |
|
|
downsample = None |
|
|
if stride != 1 or self.in_channels != out_channels: |
|
|
downsample = nn.Sequential( |
|
|
nn.Conv2d(self.in_channels, out_channels, kernel_size=1, stride=stride), |
|
|
nn.BatchNorm2d(out_channels) |
|
|
) |
|
|
layers = [] |
|
|
layers.append(ResidualBlock(self.in_channels, out_channels, stride, downsample)) |
|
|
self.in_channels = out_channels |
|
|
for _ in range(1, blocks): |
|
|
layers.append(ResidualBlock(out_channels, out_channels)) |
|
|
return nn.Sequential(*layers) |
|
|
|
|
|
def forward(self, x): |
|
|
x = self.conv1(x) |
|
|
x = self.bn1(x) |
|
|
x = self.relu(x) |
|
|
x = self.maxpool(x) |
|
|
x = self.layer1(x) |
|
|
x = self.layer2(x) |
|
|
x = self.layer3(x) |
|
|
x = self.layer4(x) |
|
|
x = self.avgpool(x) |
|
|
x = x.view(x.size(0), -1) |
|
|
x = self.fc(x) |
|
|
return x |
|
|
``` |
|
|
|
|
|
## Model 3: |
|
|
``` |
|
|
class InceptionModule(nn.Module): |
|
|
def __init__(self, in_channels, ch1x1, ch3x3_reduce, ch3x3, ch5x5_reduce, ch5x5, pool_proj): |
|
|
super(InceptionModule, self).__init__() |
|
|
self.branch1 = nn.Sequential( |
|
|
nn.Conv2d(in_channels, ch1x1, kernel_size=1), |
|
|
nn.ReLU(inplace=True) |
|
|
) |
|
|
self.branch2 = nn.Sequential( |
|
|
nn.Conv2d(in_channels, ch3x3_reduce, kernel_size=1), |
|
|
nn.ReLU(inplace=True), |
|
|
nn.Conv2d(ch3x3_reduce, ch3x3, kernel_size=3, padding=1), |
|
|
nn.ReLU(inplace=True) |
|
|
) |
|
|
self.branch3 = nn.Sequential( |
|
|
nn.Conv2d(in_channels, ch5x5_reduce, kernel_size=1), |
|
|
nn.ReLU(inplace=True), |
|
|
nn.Conv2d(ch5x5_reduce, ch5x5, kernel_size=5, padding=2), |
|
|
nn.ReLU(inplace=True) |
|
|
) |
|
|
self.branch4 = nn.Sequential( |
|
|
nn.MaxPool2d(kernel_size=3, stride=1, padding=1), |
|
|
nn.Conv2d(in_channels, pool_proj, kernel_size=1), |
|
|
nn.ReLU(inplace=True) |
|
|
) |
|
|
|
|
|
def forward(self, x): |
|
|
branch1 = self.branch1(x) |
|
|
branch2 = self.branch2(x) |
|
|
branch3 = self.branch3(x) |
|
|
branch4 = self.branch4(x) |
|
|
outputs = torch.cat([branch1, branch2, branch3, branch4], 1) |
|
|
return outputs |
|
|
|
|
|
class CNNModel3(nn.Module): |
|
|
def __init__(self, num_outputs=2): |
|
|
super(CNNModel3, self).__init__() |
|
|
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3) |
|
|
self.maxpool1 = nn.MaxPool2d(3, stride=2) |
|
|
self.conv2 = nn.Conv2d(64, 192, kernel_size=3, padding=1) |
|
|
self.maxpool2 = nn.MaxPool2d(3, stride=2) |
|
|
|
|
|
self.inception3a = InceptionModule(192, 64, 96, 128, 16, 32, 32) |
|
|
self.inception3b = InceptionModule(256, 128, 128, 192, 32, 96, 64) |
|
|
self.maxpool3 = nn.MaxPool2d(3, stride=2) |
|
|
|
|
|
self.inception4a = InceptionModule(480, 192, 96, 208, 16, 48, 64) |
|
|
self.inception4b = InceptionModule(512, 160, 112, 224, 24, 64, 64) |
|
|
self.maxpool4 = nn.MaxPool2d(3, stride=2) |
|
|
|
|
|
self.avgpool = nn.AdaptiveAvgPool2d((1, 1)) |
|
|
self.dropout = nn.Dropout(0.4) |
|
|
self.fc = nn.Linear(512, num_outputs) |
|
|
|
|
|
def forward(self, x): |
|
|
x = self.conv1(x) |
|
|
x = self.maxpool1(x) |
|
|
x = self.conv2(x) |
|
|
x = self.maxpool2(x) |
|
|
x = self.inception3a(x) |
|
|
x = self.inception3b(x) |
|
|
x = self.maxpool3(x) |
|
|
x = self.inception4a(x) |
|
|
x = self.inception4b(x) |
|
|
x = self.maxpool4(x) |
|
|
x = self.avgpool(x) |
|
|
x = x.view(x.size(0), -1) |
|
|
x = self.dropout(x) |
|
|
x = self.fc(x) |
|
|
return x |
|
|
``` |
