- on
asdc
server infrastructure, for development users - for deployment users.
There is code provided for two types of users:
are users who want to run a server infrastructure for further development and usage of models for research purposes
- shell scripts are provided for wrapping
yolov5
code to run multiple training and testing instances in:train_test_model.sh
trains and tests multiple model combinations on multiple datasetstest_model.sh
only tests a single provided model on a range of specified datasets
- Jupyter notebooks for running inference with the
SAHI
package and previously developed models:inference_for_yolov5
is a notebook which is dynamically updated frominference_for_yolov5.py
. This is the basic notebook for running inference withSAHI
and a previously developed model, which will only output visualisationsinference_single_image
is a notebook which is dynamically updated frominference_single_image.py
which, despite its name, inferences each image individually and is thus capable of outputting label files!
are users who want to run inference on their local structure and want to process folders of large images. The scripts have been developed according to the workflow documented in Issue#3. The general structure is that a site
is split into multiple flights
process_flight.py
is a script to run a single flight.- provides command line utilities, so that it need only be run from the command line via
python process_flight.py -i <input_folder> [OPTIONS]
- it contains the function
run_single_flight
, which runs a single flight directory and is in shared use with the second script - includes (rudimentary) logging to skip images that have previously been processed
- provides command line utilities, so that it need only be run from the command line via
process_site.py
is a script to run multiple flights from a single site.- provides command line utilities, so that it need only be run from the command line via
python process_site.py -i <input_folder> [OPTIONS]
- Looks for subdirectories containining the word
flight
(without spell-checking...) and will run arun_single_flight
fromprocess_flight
for each of them. - Includes (rudimentary) logging to skip already processed flights.
- provides command line utilities, so that it need only be run from the command line via
- A
config file
provides configurations for visualisations, such as minimum IoU and bounding box thickness.
Code which is of importance to both types of users is provided in files post-fixed with _utils.py
, at the current stage:
log_utils.py
for utilities pertaining to writing logsmodel_utils.py
for utilities concerning model loading, file format handling, processing and visualisationfile_utils.py
for utilities concerning file handling, such as loading folders and listing files
.pt
files are kept in the config
subfolder.
Default data directories should be stored as subdirectories in the data
folder
- install miniconda (see online instructions)
- install conda environment through
conda env install -f environment.yml
- install pip into conda environment through
conda install pip
- install rest of requirements through pip
pip install -r pipreq.txt --default-timeout=100