product-detection/kaggle_train.py
2026-06-03 10:07:23 +01:00

647 lines
27 KiB
Python

"""
kaggle_train.py — Automate Kaggle Training
============================================
Full automation of the Kaggle training pipeline:
Step 1 Zip crops_dataset/ and upload (or update) it as a Kaggle Dataset
Step 2 Patch the notebook's DATA_DIR to match the uploaded dataset path
Step 3 Push the notebook as a Kaggle Kernel and trigger a run
Step 4 Poll the kernel status every 30 s until complete or failed
Step 5 Download best.pt + class_names.json into your local runs/classify/
Requirements
------------
pip install kaggle
Set up credentials (one-time, pick one):
Option A — New token file (what Kaggle now issues):
Go to https://www.kaggle.com/settings/api → "Create New Token"
Run the command Kaggle shows you, e.g.:
mkdir -p ~/.kaggle && echo YOUR_TOKEN > ~/.kaggle/access_token
chmod 600 ~/.kaggle/access_token
Option B — Environment variable:
export KAGGLE_API_TOKEN=your_token
Option C — Legacy kaggle.json (still supported):
Settings → API → "Create Legacy API Key" → save to ~/.kaggle/kaggle.json
chmod 600 ~/.kaggle/kaggle.json
Usage
-----
# First time — creates the Kaggle dataset and notebook from scratch
python kaggle_train.py \
--dataset_dir crops_dataset \
--notebook 2_product-classifier.ipynb \
--dataset_name my-product-crops \
--kernel_name product-classifier-train \
--output_dir runs/classify
# Subsequent runs — detects existing dataset/kernel and updates them
python kaggle_train.py \
--dataset_dir crops_dataset \
--notebook 2_product-classifier.ipynb \
--dataset_name my-product-crops \
--kernel_name product-classifier-train
Arguments
---------
--dataset_dir Local crops_dataset/ folder to upload (default: crops_dataset)
--notebook Kaggle notebook .ipynb file (default: 2_product-classifier.ipynb)
--dataset_name Kaggle dataset slug (lowercase, hyphens) (default: product-dataset)
--kernel_name Kaggle kernel slug (lowercase, hyphens) (default: product-predection)
--output_dir Where to save downloaded weights (default: runs/classify)
--poll_interval Seconds between status checks (default: 30)
--timeout Max minutes to wait for kernel (default: 180)
--skip_upload Skip dataset upload (use existing version) (flag)
--skip_push Skip kernel push (use last run) (flag)
--gpu Request GPU accelerator (default: True)
--public Make dataset/kernel public (default: False)
"""
import argparse
import json
import os
import shutil
import sys
import tempfile
import time
import zipfile
from pathlib import Path
# ─────────────────────────── args ────────────────────────────────────────────
def parse_args():
p = argparse.ArgumentParser(
description="Automate Kaggle dataset upload + notebook run + output download",
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
)
p.add_argument("--dataset_dir", default="crops_dataset")
p.add_argument("--notebook", default="2_product-classifier.ipynb")
p.add_argument("--dataset_name", default="product-dataset",
help="Kaggle dataset slug — lowercase, hyphens, no spaces")
p.add_argument("--kernel_name", default="product-predection",
help="Kaggle kernel slug — lowercase, hyphens, no spaces")
p.add_argument("--output_dir", default="runs/classify")
p.add_argument("--poll_interval", type=int, default=30,
help="Seconds between kernel status polls")
p.add_argument("--timeout", type=int, default=180,
help="Max minutes to wait for the kernel to finish")
p.add_argument("--skip_upload", action="store_true",
help="Skip dataset upload — use the existing Kaggle dataset version")
p.add_argument("--skip_push", action="store_true",
help="Skip kernel push — just poll and download last run")
p.add_argument("--gpu", action="store_true", default=True,
help="Request GPU (T4) accelerator for the kernel")
p.add_argument("--no_gpu", action="store_true",
help="Override --gpu: run on CPU instead")
p.add_argument("--public", action="store_true",
help="Make dataset and kernel public (default: private)")
return p.parse_args()
# ─────────────────────────── helpers ─────────────────────────────────────────
def log(msg: str, icon: str = ""):
ts = time.strftime("%H:%M:%S")
print(f"[{ts}] {icon} {msg}", flush=True)
def fatal(msg: str):
print(f"\n[ERROR] {msg}", file=sys.stderr)
sys.exit(1)
# ── Credential paths for all 4 Kaggle auth methods ──────────────────────────
_KAGGLE_DIR = Path.home() / ".kaggle"
_ACCESS_TOKEN_PATH = _KAGGLE_DIR / "access_token" # new (Option 3)
_KAGGLE_JSON_PATH = _KAGGLE_DIR / "kaggle.json" # legacy (Option 4)
def _detect_auth_method() -> str:
"""
Return which auth method is available, in priority order:
'env_token' — KAGGLE_API_TOKEN env var (Option 2, new)
'env_legacy' — KAGGLE_USERNAME + KAGGLE_KEY (Option 2, legacy)
'access_token'— ~/.kaggle/access_token file (Option 3, new)
'kaggle_json' — ~/.kaggle/kaggle.json (Option 4, legacy)
None — nothing found
"""
if os.getenv("KAGGLE_API_TOKEN"):
return "env_token"
if os.getenv("KAGGLE_USERNAME") and os.getenv("KAGGLE_KEY"):
return "env_legacy"
if _ACCESS_TOKEN_PATH.exists():
#print(f"this is the PATH: {_ACCESS_TOKEN_PATH}")
return "access_token"
if _KAGGLE_JSON_PATH.exists():
return "kaggle_json"
return None
def check_credentials():
"""
Detect which Kaggle auth method is present and print a clear error if none.
Supports all 4 methods documented at https://github.com/Kaggle/kaggle-cli:
Option 2: KAGGLE_API_TOKEN env var (new single-token style)
Option 2: KAGGLE_USERNAME + KAGGLE_KEY (legacy env vars)
Option 3: ~/.kaggle/access_token (new token file — what Kaggle now issues)
Option 4: ~/.kaggle/kaggle.json (legacy JSON file)
"""
method = _detect_auth_method()
if method is None:
fatal(
"Kaggle credentials not found. Choose one of these options:\n\n"
"Option 1 — access_token file (what Kaggle now issues):\n"
" 1. Go to https://www.kaggle.com/settings/api\n"
" 2. Click 'Create New Token' and copy the command shown, e.g.:\n"
" mkdir -p ~/.kaggle && echo YOUR_TOKEN > ~/.kaggle/access_token\n"
" chmod 600 ~/.kaggle/access_token\n\n"
"Option 2 — environment variable (new style):\n"
" export KAGGLE_API_TOKEN=your_token\n\n"
"Option 3 — environment variables (legacy style):\n"
" export KAGGLE_USERNAME=your_username\n"
" export KAGGLE_KEY=your_api_key\n\n"
"Option 4 — kaggle.json (legacy file, still supported):\n"
" Go to Kaggle → Settings → API → 'Create Legacy API Key'\n"
" Move kaggle.json to ~/.kaggle/kaggle.json\n"
" chmod 600 ~/.kaggle/kaggle.json\n"
)
labels = {
"env_token": "KAGGLE_API_TOKEN env var",
"env_legacy": "KAGGLE_USERNAME + KAGGLE_KEY env vars",
"access_token": f"~/.kaggle/access_token (new token file)",
"kaggle_json": f"~/.kaggle/kaggle.json (legacy)",
}
log(f"Auth method: {labels[method]}", "")
def get_kaggle_username() -> str:
"""
Retrieve the Kaggle username for constructing dataset/kernel refs.
With the new access_token auth, the username is fetched from the API
itself (whoami) instead of being embedded in the credential file.
"""
# Legacy env var — username is explicit
if os.getenv("KAGGLE_USERNAME"):
return os.getenv("KAGGLE_USERNAME")
# Legacy kaggle.json — username is in the file
if _KAGGLE_JSON_PATH.exists():
try:
return json.loads(_KAGGLE_JSON_PATH.read_text())["username"]
except Exception:
pass
# New access_token / KAGGLE_API_TOKEN — must ask the API
# The kaggle package exposes this after authenticate() is called
try:
from kaggle.api.kaggle_api_extended import KaggleApiExtended
_api = KaggleApiExtended()
_api.authenticate()
# kaggle SDK stores the authenticated username here
if hasattr(_api, "get_config_value"):
uname = _api.get_config_value("username")
if uname:
return uname
# Fallback: call the whoami REST endpoint directly
resp = _api.process_response(
_api.kernel_output_with_http_info("", "")
)
except Exception:
pass
# Last resort: ask the user
print()
uname = input(" Could not auto-detect your Kaggle username.\n"
" Enter it manually (found at kaggle.com/your-username): ").strip()
if not uname:
fatal("Username is required to build dataset/kernel references.")
return uname
def slugify(name: str) -> str:
"""Ensure a slug is lowercase with hyphens."""
return name.lower().replace("_", "-").replace(" ", "-")
# ─────────────────────────── step 1: zip + upload dataset ────────────────────
def zip_dataset(dataset_dir: Path, tmp_dir: Path) -> Path:
"""Zip the dataset folder, preserving the train/val/test structure."""
zip_path = tmp_dir / "dataset.zip"
log(f"Zipping {dataset_dir}", "📦")
total = sum(1 for p in dataset_dir.rglob("*") if p.is_file())
done = 0
with zipfile.ZipFile(zip_path, "w", zipfile.ZIP_DEFLATED) as zf:
for file_path in sorted(dataset_dir.rglob("*")):
if file_path.is_file():
arcname = file_path.relative_to(dataset_dir.parent)
zf.write(file_path, arcname)
done += 1
if done % 500 == 0 or done == total:
pct = done / total * 100
print(f" Zipped {done:,}/{total:,} ({pct:.0f}%)", end="\r")
size_mb = zip_path.stat().st_size / 1e6
print()
log(f"Zip ready: {zip_path} ({size_mb:.1f} MB)", "")
return zip_path
def upload_dataset(api, username: str, dataset_name: str,
dataset_dir: Path, tmp_dir: Path, public: bool) -> str:
"""
Create or update a Kaggle dataset from dataset_dir.
Returns the full dataset reference string: username/dataset-name
"""
slug = slugify(dataset_name)
ref = f"{username}/{slug}"
# Check if dataset already exists
existing = None
try:
existing = api.dataset_status(username, slug)
except Exception:
pass # 404 = doesn't exist yet
# Write dataset-metadata.json into a staging folder
stage_dir = tmp_dir / "dataset_stage"
stage_dir.mkdir(exist_ok=True)
# Copy the crops_dataset folder into staging
dst = stage_dir / dataset_dir.name
if dst.exists():
shutil.rmtree(dst)
shutil.copytree(str(dataset_dir), str(dst))
meta = {
"title": dataset_name.replace("-", " ").title(),
"id": ref,
"licenses": [{"name": "CC0-1.0"}],
}
(stage_dir / "dataset-metadata.json").write_text(json.dumps(meta, indent=2))
if existing is None:
log(f"Creating new Kaggle dataset: {ref}", "")
api.dataset_create_new(
folder = str(stage_dir),
public = public,
quiet = False,
convert_to_csv = False,
dir_mode = "zip",
)
log(f"Dataset created: https://www.kaggle.com/datasets/{ref}", "")
else:
log(f"Updating existing Kaggle dataset: {ref}", "")
api.dataset_create_version(
folder = str(stage_dir),
version_notes = f"Updated via kaggle_train.py at {time.strftime('%Y-%m-%d %H:%M')}",
quiet = False,
convert_to_csv = False,
delete_old_versions = False,
dir_mode = "zip",
)
log(f"Dataset updated: https://www.kaggle.com/datasets/{ref}", "")
return ref
# ─────────────────────────── step 2: patch notebook ──────────────────────────
def patch_notebook(notebook_path: Path, dataset_ref: str,
tmp_dir: Path) -> Path:
"""
Patch DATA_DIR in the notebook to point to the uploaded Kaggle dataset,
and save a modified copy into tmp_dir.
The notebook's Cell 2 contains something like:
DATA_DIR = Path("/kaggle/input/your-dataset-name")
We replace the path to match the actual uploaded dataset slug.
"""
nb = json.loads(notebook_path.read_text(encoding="utf-8"))
# Extract the dataset slug from "username/slug" → "slug"
ds_slug = dataset_ref.split("/")[-1]
patched = False
for cell in nb.get("cells", []):
if cell.get("cell_type") != "code":
continue
src = "".join(cell["source"])
if "DATA_DIR" in src and "/kaggle/input/" in src:
new_lines = []
for line in cell["source"]:
if "DATA_DIR" in line and "/kaggle/input/" in line:
# Preserve indentation, replace only the path string
indent = len(line) - len(line.lstrip())
new_line = " " * indent + f'DATA_DIR = Path("/kaggle/input/{ds_slug}/{Path(ds_slug).stem}")\n'
# Try to find the inner folder name (crops_dataset by default)
# Use the dataset_dir name if we can detect it from context
new_line = " " * indent + f'DATA_DIR = Path("/kaggle/input/{ds_slug}")\n'
new_lines.append(new_line)
patched = True
log(f"Patched DATA_DIR → /kaggle/input/{ds_slug}", "")
else:
new_lines.append(line)
cell["source"] = new_lines
if not patched:
log("⚠ DATA_DIR line not found in notebook — using notebook as-is", "")
out_path = tmp_dir / notebook_path.name
out_path.write_text(json.dumps(nb, indent=1), encoding="utf-8")
return out_path
# ─────────────────────────── step 3: push kernel ─────────────────────────────
def push_kernel(api, username: str, kernel_name: str, notebook_path: Path,
dataset_ref: str, tmp_dir: Path,
gpu: bool, public: bool) -> str:
"""
Create or update a Kaggle kernel (notebook) and trigger a run.
Returns the kernel ref string: username/kernel-name
"""
slug = slugify(kernel_name)
ref = f"{username}/{slug}"
kernel_dir = tmp_dir / "kernel_push"
kernel_dir.mkdir(exist_ok=True)
# Copy patched notebook into kernel dir
nb_dest = kernel_dir / notebook_path.name
shutil.copy2(str(notebook_path), str(nb_dest))
# kernel-metadata.json — controls GPU, dataset attachment, language
meta = {
"id": ref,
"title": kernel_name.replace("-", " ").title(),
"code_file": notebook_path.name,
"language": "python",
"kernel_type": "notebook",
"is_private": not public,
"enable_gpu": gpu,
"enable_tpu": False,
"enable_internet": True,
"dataset_sources": [dataset_ref],
"competition_sources": [],
"kernel_sources": [],
"model_sources": [],
"machine_shape": "t4" if gpu else None,
}
(kernel_dir / "kernel-metadata.json").write_text(json.dumps(meta, indent=2))
log(f"Pushing kernel to Kaggle: {ref} (GPU={'yes' if gpu else 'no'})", "🚀")
try:
api.kernels_push(str(kernel_dir), timeout=None, acc="t4" if gpu else None)
except TypeError:
api.kernels_push(str(kernel_dir))
log(f"Kernel pushed — run started: https://www.kaggle.com/code/{ref}", "")
return ref
# ─────────────────────────── step 4: poll ────────────────────────────────────
def poll_kernel(api, kernel_ref: str, poll_interval: int, timeout_minutes: int) -> bool:
"""
Poll the kernel until it reaches a terminal status.
Returns True if successful, False if failed or timed out.
"""
deadline = time.time() + timeout_minutes * 60
attempt = 0
TERMINAL = {"complete", "error", "cancelled", "cancel_acknowledged"}
RUNNING = {"running", "queued", "initializing", "pending"}
log(f"Polling kernel status every {poll_interval}s "
f"(timeout {timeout_minutes} min) …", "")
while time.time() < deadline:
attempt += 1
try:
# kernels_status takes the full kernel ref "username/slug"
status_obj = api.kernels_status(kernel_ref)
# Extract status from the response object
raw_status = getattr(status_obj, "status", None)
if raw_status is not None:
if hasattr(raw_status, 'name'):
status = raw_status.name.lower()
else:
status = str(raw_status).lower()
else:
status = str(status_obj).lower()
# Clean up enum prefixes
status = status.replace("kernelworkerstatus.", "")
except Exception as e:
log(f"Poll error (will retry): {e}", "")
time.sleep(poll_interval)
continue
elapsed_min = (time.time() + timeout_minutes * 60 - deadline) / 60
print(f" [{attempt:>3}] status={status:<20} elapsed={elapsed_min:.1f} min",
end="\r", flush=True)
if status == "complete":
print()
log("Kernel completed successfully!", "")
return True
if status == "error":
print()
log("Kernel run failed — check logs at "
f"https://www.kaggle.com/code/{kernel_ref}", "")
return False
if "cancel" in status:
print()
log("Kernel was cancelled.", "")
return False
if status not in RUNNING:
print()
log(f"Unknown status: {status!r} — continuing to poll", "")
time.sleep(poll_interval)
print()
log(f"Timeout after {timeout_minutes} minutes. "
f"Check manually: https://www.kaggle.com/code/{kernel_ref}", "")
return False
# ─────────────────────────── step 5: download outputs ────────────────────────
def download_outputs(api, kernel_ref: str, output_dir: Path) -> list[Path]:
"""
Download all kernel output files and return paths to the ones we care about.
Targets: best.pt, last.pt, class_names.json, *.png
"""
username, slug = kernel_ref.split("/")
output_dir.mkdir(parents=True, exist_ok=True)
log(f"Downloading kernel outputs → {output_dir}", "")
with tempfile.TemporaryDirectory() as tmp:
try:
api.kernels_output(username, slug, path=tmp, unzip=True)
except Exception as e:
fatal(f"Could not download kernel outputs: {e}\n"
f"Try manually at https://www.kaggle.com/code/{kernel_ref}/output")
tmp_path = Path(tmp)
downloaded = []
# Walk everything the kernel produced
for f in sorted(tmp_path.rglob("*")):
if not f.is_file():
continue
# We want weights, class map, and training plots
keep = f.suffix in {".pt", ".json", ".png", ".csv"}
if not keep:
continue
dst = output_dir / f.relative_to(tmp_path)
dst.parent.mkdir(parents=True, exist_ok=True)
shutil.copy2(str(f), str(dst))
downloaded.append(dst)
log(f" {dst.relative_to(output_dir)} ({f.stat().st_size/1e6:.2f} MB)", " ")
if not downloaded:
log("No output files found. The kernel may not have saved to /kaggle/working/", "")
else:
log(f"{len(downloaded)} file(s) downloaded to {output_dir.resolve()}", "")
return downloaded
# ─────────────────────────── main ────────────────────────────────────────────
def main():
args = parse_args()
gpu = args.gpu and not args.no_gpu
check_credentials()
# Import here so missing kaggle package gives a clean error
try:
from kaggle.api.kaggle_api_extended import KaggleApi
api = KaggleApi()
api.authenticate()
except ImportError:
fatal("kaggle package not installed.\n Run: pip install kaggle")
except Exception as e:
fatal(
f"Kaggle authentication failed: {e}\n\n"
"Troubleshooting:\n"
" • New token file: ~/.kaggle/access_token (chmod 600)\n"
" • Env var: export KAGGLE_API_TOKEN=your_token\n"
" • Legacy JSON: ~/.kaggle/kaggle.json (chmod 600)\n"
" • Or run: kaggle auth login\n"
)
username = get_kaggle_username()
log(f"Authenticated as: {username}", "")
dataset_dir = Path(args.dataset_dir)
notebook_path = Path(args.notebook)
output_dir = Path(args.output_dir)
if not dataset_dir.exists():
fatal(f"Dataset directory not found: {dataset_dir}")
if not notebook_path.exists():
fatal(f"Notebook not found: {notebook_path}")
print(f"""
╔══════════════════════════════════════════════════════╗
║ Kaggle Training Automation ║
╠══════════════════════════════════════════════════════╣
Kaggle user : {username}
Dataset : {args.dataset_name} ({dataset_dir})
Kernel : {args.kernel_name}
Notebook : {notebook_path}
GPU : {'yes (T4)' if gpu else 'no (CPU)'}
Output : {output_dir}
Poll interval : {args.poll_interval}s
Timeout : {args.timeout} min
╚══════════════════════════════════════════════════════╝
""")
with tempfile.TemporaryDirectory() as tmp_str:
tmp = Path(tmp_str)
# ── Step 1: upload dataset ────────────────────────────────────────────
if not args.skip_upload:
dataset_ref = upload_dataset(
api, username, args.dataset_name,
dataset_dir, tmp, args.public
)
# Give Kaggle a moment to process the upload before pushing the kernel
log("Waiting 10 s for dataset to register on Kaggle…", "")
time.sleep(10)
else:
dataset_ref = f"{username}/{slugify(args.dataset_name)}"
log(f"Skipping upload — using existing dataset: {dataset_ref}", "")
# ── Step 2: patch notebook ────────────────────────────────────────────
patched_nb = patch_notebook(notebook_path, dataset_ref, tmp)
# ── Step 3: push kernel ───────────────────────────────────────────────
kernel_ref = f"{username}/{slugify(args.kernel_name)}"
if not args.skip_push:
kernel_ref = push_kernel(
api, username, args.kernel_name,
patched_nb, dataset_ref, tmp,
gpu, args.public,
)
else:
log(f"Skipping push — polling existing kernel: {kernel_ref}", "")
# ── Step 4: poll ──────────────────────────────────────────────────────
success = poll_kernel(api, kernel_ref, args.poll_interval, args.timeout)
if not success:
log(
f"Training did not complete successfully.\n"
f" View logs : https://www.kaggle.com/code/{kernel_ref}\n"
f" Re-run download only:\n"
f" python kaggle_train.py --skip_upload --skip_push "
f"--kernel_name {args.kernel_name}",
""
)
sys.exit(1)
# ── Step 5: download ──────────────────────────────────────────────────
downloaded = download_outputs(api, kernel_ref, output_dir)
# ── Final summary ─────────────────────────────────────────────────────────
best_pt = next((f for f in downloaded if f.name == "best.pt"), None)
cls_json = next((f for f in downloaded if f.name == "class_names.json"), None)
curves_png = next((f for f in downloaded if "curves" in f.name), None)
print()
print("" * 55)
print(" Training pipeline complete!")
if best_pt:
print(f" Weights : {best_pt}")
if cls_json:
print(f" Classes : {cls_json}")
if curves_png:
print(f" Curves : {curves_png}")
print()
print(" Next steps:")
print(f" python 3_inference.py \\")
print(f" --classifier_weights {output_dir}/best.pt \\")
print(f" --detector_weights detector/best.pt \\")
print(f" --source shelf_images/")
print("" * 55)
if __name__ == "__main__":
main()