simonfranken/mmp_wise2526_franksim
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

adapts document

Browse Source
This commit is contained in:
franksim
2025-11-04 09:35:16 +01:00
parent 78bdb7155b
commit ef540f128e
3 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

BIN
mmp/a3/document.pdf
View File

Binary file not shown.

2
mmp/a3/document.tex
View File

@@ -74,6 +74,8 @@
\hline Accuracy & 78.90 \% \\ \hline Accuracy & 78.90 \% \\
\hline \hline
\end{tabular} \end{tabular}
\\
The accuracy metric isn’t ideal because it’s quite intuitive to classify whether an object appears once or more in an image. In this case, the model might not have guessed the correct number of objects (e.g., 3 instead of 2), but the result will still be interpreted as accurate. This also makes it more challenging to backpropagate. A better approach would be to output the actual number of objects (in this case, humans).
%------------------ END OF ASSIGNMENT ----------------------- %------------------ END OF ASSIGNMENT -----------------------

4
mmp/a3/main.py
View File

@@ -15,11 +15,11 @@ def main():
train_epochs = 10 train_epochs = 10
model = MmpNet(num_classes=2).to(device=device) model = MmpNet(num_classes=2).to(device=device)
dataloader_train = get_dataloader( dataloader_train = get_dataloader(
path_to_data="/home/ubuntu/mmp_wise2526_franksim/.data/mmp-public-3.2", path_to_data=".data/mmp-public-3.2",
image_size=244, batch_size=32, num_workers=6, is_train=True image_size=244, batch_size=32, num_workers=6, is_train=True
) )
dataloader_eval = get_dataloader( dataloader_eval = get_dataloader(
path_to_data="/home/ubuntu/mmp_wise2526_franksim/.data/mmp-public-3.2", path_to_data=".data/mmp-public-3.2",
image_size=244, batch_size=32, num_workers=6, is_train=False image_size=244, batch_size=32, num_workers=6, is_train=False
) )
criterion, optimizer = get_criterion_optimizer(model=model) criterion, optimizer = get_criterion_optimizer(model=model)