In this project, you'll label the pixels of a road in images using a Fully Convolutional Network (FCN).
main.py
will check to make sure you are using GPU - if you don't have a GPU on your system, you can use AWS or another cloud computing platform.
Make sure you have the following is installed:
Download the Kitti Road dataset from here. Extract the dataset in the data
folder. This will create the folder data_road
with all the training a test images.
Implement the code in the main.py
module indicated by the "TODO" comments.
The comments indicated with "OPTIONAL" tag are not required to complete.
Run the following command to run the project:
python main.py
Note If running this in Jupyter Notebook system messages, such as those regarding test status, may appear in the terminal rather than the notebook.
- Ensure you've passed all the unit tests.
- Ensure you pass all points on the rubric.
- Submit the following in a zip file.
helper.py
main.py
project_tests.py
- Newest inference images from
runs
folder (all images from the most recent run)
- The link for the frozen
VGG16
model is hardcoded intohelper.py
. The model can be found here. - The model is not vanilla
VGG16
, but a fully convolutional version, which already contains the 1x1 convolutions to replace the fully connected layers. Please see this post for more information. A summary of additional points, follow. - The original FCN-8s was trained in stages. The authors later uploaded a version that was trained all at once to their GitHub repo. The version in the GitHub repo has one important difference: The outputs of pooling layers 3 and 4 are scaled before they are fed into the 1x1 convolutions. As a result, some students have found that the model learns much better with the scaling layers included. The model may not converge substantially faster, but may reach a higher IoU and accuracy.
- When adding l2-regularization, setting a regularizer in the arguments of the
tf.layers
is not enough. Regularization loss terms must be manually added to your loss function. otherwise regularization is not implemented.
If you are unfamiliar with GitHub , Udacity has a brief GitHub tutorial to get you started. Udacity also provides a more detailed free course on git and GitHub.
To learn about REAMDE files and Markdown, Udacity provides a free course on READMEs, as well.
GitHub also provides a tutorial about creating Markdown files.
I ended up implementing simple FCN model as suggested in walkthrough video. I have trained this model on my laptop without any GPU. I tain the model with following parameters
# Hyper parameters
KEEP_PROB = 0.75 # Dropout probability to keep a neuron alive
LEARN_RATE = 0.001 # learning rate for training
REG_SCALE = 0.0001 # A contant multiplier for regularization losses
WT_STDDEV = 0.001 # Standard deviation for weight initializer
BATCH_SIZE = 8 # Number of images in a batch for training
EPOCHS = 25 # number of epochs to train network
At the end of 25th epoch, model achieves training mean loss of 0.0415. Output of the prgram is captured in logs.txt
. Following plot shows training loss for each epoch.
Following gif is created from ouput on test images in runs directory containing inference output.