Welcome to ML_Botting_Core!
Solving Complex UI Challenges w/ ML
pip install ml-botting-core
Public Eve Online Models
This package will auto download these models from Here at runtime and maintain a copy on your device. (and auto update)
Sample config Here with all models.
Training
Train your own models Here
Sort your training images into folders (images shape must be the same shape) and target the root for training. The classifer will train those image samples to the name of the folder they are in.
- Image names do not matter.
- PNGs only.
- Number of samples per folder do not matter, however you want enough, 80% for training, 20% for validation.
├── training_data
│ ├── char_select
│ │ ├── image_1.png
│ │ ├── image_2.png
│ │ ├── image_3.png
│ ├── connection_lost
│ │ ├── image_1.png
│ │ ├── image_2.png
│ │ ├── image_3.png
│ ├── in_flight
│ │ ├── image_1.png
│ │ ├── image_2.png
│ │ ├── image_3.png
│ ├── in_hanger
│ │ ├── image_1.png
│ │ ├── image_2.png
│ │ ├── image_3.png
Usage:
Check out the samples Here.
ml_botting_core_config.json
{
"public_models":[
{
"game":"eve_online",
"model_name":"game_state",
"download_latest":1,
"download_latest_from":"https://storage.googleapis.com/eve_online_models/",
"model_root_directory":"O:\\eve_live_models\\game_state",
"model_log_directory":"O:\\eve_live_logs\\game_state",
"save_images":0
}
]
}
Implementation
from ml_botting_core import universal_predictor
up_config = json.load(open(r'ml_botting_core_config.json'))
up = universal_predictor(config=up_config)
img = Image.open('some_image.png')
state_result = up.predict(img, 'game_state')
state_result
{
"epoc_time":"1682138565007.508",
"argmax_index":2,
"value_at_argmax":"1.0",
"class":"jump_though_first",
"classes":[
"dock_now",
"invalid",
"jump_though_first",
"jump_through_second",
"no_action",
"warp_to_dock_3",
"warp_to_dock_4"
],
"scores":[
1.2750345662162804e-15,
1.4581948495906438e-11,
1.0,
5.21881417175057e-17,
1.4712418422554443e-18,
1.2777047215389858e-12,
6.730089694497203e-17
],
"id":"98ad373b-e0a6-11ed-9b27-2cf05d9fe8eb",
"image_saved":0,
"model_name":"nav_options"
}
Metadata
Release files for ml-botting-core 1.0.7
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| ml_botting_core-1.0.7.tar.gz | 9.7 kB | Without provenance | Details for ml_botting_core-1.0.7.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| ml_botting_core-1.0.7-py3-none-any.whl | Python 3 | none | any | Details for ml_botting_core-1.0.7-py3-none-any.whl |
Total release size: 20.4 kB
Release files / ml_botting_core-1.0.7.tar.gz
| Download URL | ml_botting_core-1.0.7.tar.gz |
|---|---|
| Size | 9.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
22dea86084069a2b205ad68564372e6dbc7b7d7aebefbd1ce60408079a31b445
|
|
BLAKE2b-256 checksum How to use checksums |
6c89322c920cfbe4a0a2ab74b7cb34dbb236fdbbeed5dcaeca322f5192b4f487
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.9.16
|
Release files / ml_botting_core-1.0.7-py3-none-any.whl
| Download URL | ml_botting_core-1.0.7-py3-none-any.whl |
|---|---|
| Size | 10.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b3c3181916b34a099453d498fa56cf4839b9007ff5c5c3300e6cee0b9b289251
|
|
BLAKE2b-256 checksum How to use checksums |
8b15efc5214f9adf713a3cd2d98947c268c4077293e01baa5be40c7883328700
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.9.16
|
Security for ml-botting-core 1.0.7
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.