BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//American Young Coder - ECPv6.10.1.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:American Young Coder
X-ORIGINAL-URL:https://www.ayclogic.com
X-WR-CALDESC:Events for American Young Coder
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20260308T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20261101T090000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20260126T190000
DTEND;TZID=America/Los_Angeles:20260126T200000
DTSTAMP:20260419T160743
CREATED:20260127T051814Z
LAST-MODIFIED:20260127T051814Z
UID:32291-1769454000-1769457600@www.ayclogic.com
SUMMARY:7 PM – AI/ML – Darin
DESCRIPTION:Today’s Activities:\n\nLearnt a bit about tensors\, pre-trained models\, model sizes\nExported our trained AI model to a .pkl file for use outside of kaggle\nRan a quick streamlit app to visualize model working on the browser\n\nHomework:\n\nRun training again like we did in class\, but this time using 3 different AI backbones (replacing the ‘resnet34’ under the vision_learner function call) like last week.\nReferences for model types: \nhttps://docs.pytorch.org/vision/stable/models.html#initializing-pre-trained-models\nhttps://docs.fast.ai/vision.learner.html#vision_learner\nSAVE these models as .pkl files and put them in your pycharm project directory.\nFinally modify the pycharm file to be able to select between different models you have trained for evaluation.\nYou can add this section beneath the “created by” code to replace the load_learner for multi model selection functionality. \n\nMODELS_DIR = Path("models")\n\n# Find all .pkl files in models/\nmodel_paths = sorted(MODELS_DIR.glob("*.pkl"))\nmodel_names = [p.name for p in model_paths]\n\nif not model_paths:\n    st.error(f"No .pkl models found in: {MODELS_DIR.resolve()}")\n    st.stop()\n\n# UI: choose which model to use\nselected_name = st.selectbox("Select a model to use:"\, model_names)\n\n@st.cache_resource  # cache the loaded learner per selected model\ndef get_model(model_path_str: str):\n    return load_learner(model_path_str)\n\nmodel_path = str(MODELS_DIR / selected_name)\ncat_vs_dog_model = get_model(model_path)\n\nst.caption(f"Loaded model: {selected_name}")\n\n\nRUN your app with “streamlit run <python file path>” such as “streamlit run src/Jan26_CatVSDog_Evaluation.py”\n\nUpload the file Jan26_CatVSDog_Evaluation.py to the google drive when you are done. \nNotes:\nYou can reach me at ddjapri@ayclogic.com. \nAll class notes can be found here.
URL:https://www.ayclogic.com/event/7-pm-ai-ml-darin-3/
CATEGORIES:AI/ML,Python Class
END:VEVENT
END:VCALENDAR