Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update notebooks with JSON Reporting #92

Merged
merged 5 commits into from
Jan 26, 2024
Merged

Update notebooks with JSON Reporting #92

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
bed3d4c
Update notebooks
mehrinkiani Jan 25, 2024
31d2d3a
update scan command
mehrinkiani Jan 25, 2024
4c6425d
update readme
mehrinkiani Jan 26, 2024
901ee77
Fixed typos
mehrinkiani Jan 26, 2024
16f5e62
update readme
mehrinkiani Jan 26, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,6 +116,9 @@ ModelScan supports the following arguments via the CLI:
| ```modelscan -p /path/to/model_file``` | -p or --path | Scan a locally stored model |
| ```modelscan -p /path/to/model_file --settings-file ./modelscan-settings.toml``` | --settings-file | Scan a locally stored model using custom configurations |
| ```modelscan create-settings-file``` | -l or --location | Create a configurable settings file |
| ```modelscan -r``` | -r or --reporting-format | Format of the output. Options are console, json, or custom (to be defined in settings-file). Default is console |
| ```modelscan -r reporting-format -o file-name``` | -o or --output-file | Optional file name for output report |
| ```modelscan --show-skipped``` | --show-skipped | Print a list of files that were skipped during the scan |


Remember models are just like any other form of digital media, you should scan content from any untrusted source before use.
Expand Down
110 changes: 86 additions & 24 deletions notebooks/keras_fashion_mnist.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,9 +11,18 @@
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"modelscan, version 0.5.0\n"
]
}
],
"source": [
"!pip install -q modelscan"
"!pip install -q modelscan\n",
"!modelscan -v"
]
},
{
Expand Down Expand Up @@ -58,35 +67,35 @@
"output_type": "stream",
"text": [
"Epoch 1/10\n",
"1875/1875 [==============================] - 2s 773us/step - loss: 0.5034 - accuracy: 0.8228\n",
"1875/1875 [==============================] - 2s 1ms/step - loss: 0.4986 - accuracy: 0.8258\n",
"Epoch 2/10\n",
"1875/1875 [==============================] - 1s 738us/step - loss: 0.3762 - accuracy: 0.8640\n",
"1875/1875 [==============================] - 2s 800us/step - loss: 0.3741 - accuracy: 0.8649\n",
"Epoch 3/10\n",
"1875/1875 [==============================] - 1s 760us/step - loss: 0.3358 - accuracy: 0.8769\n",
"1875/1875 [==============================] - 1s 772us/step - loss: 0.3391 - accuracy: 0.8766\n",
"Epoch 4/10\n",
"1875/1875 [==============================] - 1s 733us/step - loss: 0.3114 - accuracy: 0.8854\n",
"1875/1875 [==============================] - 1s 755us/step - loss: 0.3125 - accuracy: 0.8852\n",
"Epoch 5/10\n",
"1875/1875 [==============================] - 1s 743us/step - loss: 0.2949 - accuracy: 0.8909\n",
"1875/1875 [==============================] - 2s 965us/step - loss: 0.2955 - accuracy: 0.8908\n",
"Epoch 6/10\n",
"1875/1875 [==============================] - 1s 731us/step - loss: 0.2816 - accuracy: 0.8962\n",
"1875/1875 [==============================] - 2s 905us/step - loss: 0.2808 - accuracy: 0.8963\n",
"Epoch 7/10\n",
"1875/1875 [==============================] - 1s 743us/step - loss: 0.2687 - accuracy: 0.9000\n",
"1875/1875 [==============================] - 2s 1ms/step - loss: 0.2696 - accuracy: 0.9004\n",
"Epoch 8/10\n",
"1875/1875 [==============================] - 1s 762us/step - loss: 0.2567 - accuracy: 0.9044\n",
"1875/1875 [==============================] - 2s 895us/step - loss: 0.2587 - accuracy: 0.9039\n",
"Epoch 9/10\n",
"1875/1875 [==============================] - 1s 766us/step - loss: 0.2464 - accuracy: 0.9075\n",
"1875/1875 [==============================] - 2s 925us/step - loss: 0.2479 - accuracy: 0.9068\n",
"Epoch 10/10\n",
"1875/1875 [==============================] - 1s 737us/step - loss: 0.2372 - accuracy: 0.9113\n",
"313/313 [==============================] - 0s 490us/step - loss: 0.3440 - accuracy: 0.8827\n",
"1875/1875 [==============================] - 2s 893us/step - loss: 0.2406 - accuracy: 0.9112\n",
"313/313 [==============================] - 0s 555us/step - loss: 0.3496 - accuracy: 0.8790\n",
"\n",
"Model trained with test accuracy: 0.8827000260353088\n"
"Model trained with test accuracy: 0.8790000081062317\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/mehrinkiani/mambaforge/envs/notebooks-xgb-2/lib/python3.9/site-packages/keras/src/engine/training.py:3000: UserWarning: You are saving your model as an HDF5 file via `model.save()`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')`.\n",
"/Users/mehrinkiani/mambaforge/envs/py310/lib/python3.10/site-packages/keras/src/engine/training.py:3000: UserWarning: You are saving your model as an HDF5 file via `model.save()`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')`.\n",
" saving_api.save_model(\n"
]
}
Expand Down Expand Up @@ -117,9 +126,9 @@
"name": "stdout",
"output_type": "stream",
"text": [
"1/1 [==============================] - 0s 35ms/step\n",
"1/1 [==============================] - 0s 42ms/step\n",
"\n",
"The model predicts: ['Ankle boot', 'Pullover', 'Trouser'] with probabilities: [ 98.059 99.993996 100. ]\n",
"The model predicts: ['Ankle boot', 'Pullover', 'Trouser'] with probabilities: [ 98.948 99.926 100. ]\n",
"\n",
"The true labels are ['Ankle boot', 'Pullover', 'Trouser']\n"
]
Expand Down Expand Up @@ -159,7 +168,9 @@
"name": "stdout",
"output_type": "stream",
"text": [
"Scanning /Users/mehrinkiani/Documents/modelscan/notebooks/KerasModels/safe_model.h5 using hdf5 model scan\n",
"No settings file detected at /Users/mehrinkiani/Documents/modelscan/notebooks/modelscan-settings.toml. Using defaults. \n",
"\n",
"Scanning /Users/mehrinkiani/Documents/modelscan/notebooks/KerasModels/safe_model.h5 using modelscan.scanners.H5LambdaDetectScan model scan\n",
"\n",
"\u001b[34m--- Summary ---\u001b[0m\n",
"\n",
Expand Down Expand Up @@ -244,9 +255,9 @@
"aws_secret_access_key=<aws_secret_key>\n",
"aws_access_key_id=<access_key_id>\n",
"aws_secret_access_key=<aws_secret_key>\n",
"1/1 [==============================] - 0s 29ms/step\n",
"1/1 [==============================] - 0s 35ms/step\n",
"\n",
"The model predicts: ['Ankle boot', 'Pullover', 'Trouser'] with probabilities: [ 98.059 99.993996 100. ]\n",
"The model predicts: ['Ankle boot', 'Pullover', 'Trouser'] with probabilities: [ 98.948 99.926 100. ]\n",
"\n",
"The true labels are ['Ankle boot', 'Pullover', 'Trouser']\n"
]
Expand Down Expand Up @@ -289,7 +300,9 @@
"name": "stdout",
"output_type": "stream",
"text": [
"Scanning /Users/mehrinkiani/Documents/modelscan/notebooks/KerasModels/unsafe_model.h5 using hdf5 model scan\n",
"No settings file detected at /Users/mehrinkiani/Documents/modelscan/notebooks/modelscan-settings.toml. Using defaults. \n",
"\n",
"Scanning /Users/mehrinkiani/Documents/modelscan/notebooks/KerasModels/unsafe_model.h5 using modelscan.scanners.H5LambdaDetectScan model scan\n",
"\n",
"\u001b[34m--- Summary ---\u001b[0m\n",
"\n",
Expand Down Expand Up @@ -317,6 +330,55 @@
"!modelscan -p KerasModels/unsafe_model.h5"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Reporting Format\n",
"ModelScan can report scan results in console (default), JSON, or custom report (to be defined by user in settings-file). For mode details, please see: ` modelscan -h` "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## JSON Report\n",
"\n",
"For JSON reporting: `modelscan -p ./path-to/file -r json -o output-file-name.json` \n"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"No settings file detected at /Users/mehrinkiani/Documents/modelscan/notebooks/modelscan-settings.toml. Using defaults. \n",
"\n",
"Scanning /Users/mehrinkiani/Documents/modelscan/notebooks/KerasModels/unsafe_model.h5 using modelscan.scanners.H5LambdaDetectScan model scan\n",
"\u001b[1m{\u001b[0m\u001b[32m\"modelscan_version\"\u001b[0m: \u001b[32m\"0.5.0\"\u001b[0m, \u001b[32m\"timestamp\"\u001b[0m: \u001b[32m\"2024-01-25T17:56:36.776966\"\u001b[0m, \n",
"\u001b[32m\"input_path\"\u001b[0m: \n",
"\u001b[32m\"/Users/mehrinkiani/Documents/modelscan/notebooks/KerasModels/unsafe_model.h5\"\u001b[0m, \n",
"\u001b[32m\"total_issues\"\u001b[0m: \u001b[1;36m1\u001b[0m, \u001b[32m\"summary\"\u001b[0m: \u001b[1m{\u001b[0m\u001b[32m\"total_issues_by_severity\"\u001b[0m: \u001b[1m{\u001b[0m\u001b[32m\"LOW\"\u001b[0m: \u001b[1;36m0\u001b[0m, \u001b[32m\"MEDIUM\"\u001b[0m: \n",
"\u001b[1;36m1\u001b[0m, \u001b[32m\"HIGH\"\u001b[0m: \u001b[1;36m0\u001b[0m, \u001b[32m\"CRITICAL\"\u001b[0m: \u001b[1;36m0\u001b[0m\u001b[1m}\u001b[0m\u001b[1m}\u001b[0m, \u001b[32m\"issues_by_severity\"\u001b[0m: \u001b[1m{\u001b[0m\u001b[32m\"MEDIUM\"\u001b[0m: \u001b[1m[\u001b[0m\u001b[1m{\u001b[0m\u001b[32m\"description\"\u001b[0m:\n",
"\u001b[32m\"Use of unsafe operator 'Lambda' from module 'Keras'\"\u001b[0m, \u001b[32m\"operator\"\u001b[0m: \u001b[32m\"Lambda\"\u001b[0m, \n",
"\u001b[32m\"module\"\u001b[0m: \u001b[32m\"Keras\"\u001b[0m, \u001b[32m\"source\"\u001b[0m: \n",
"\u001b[32m\"/Users/mehrinkiani/Documents/modelscan/notebooks/KerasModels/unsafe_model.h5\"\u001b[0m, \n",
"\u001b[32m\"scanner\"\u001b[0m: \u001b[32m\"modelscan.scanners.H5LambdaDetectScan\"\u001b[0m\u001b[1m}\u001b[0m\u001b[1m]\u001b[0m\u001b[1m}\u001b[0m, \u001b[32m\"errors\"\u001b[0m: \u001b[1m[\u001b[0m\u001b[1m]\u001b[0m, \u001b[32m\"scanned\"\u001b[0m: \n",
"\u001b[1m{\u001b[0m\u001b[32m\"total_scanned\"\u001b[0m: \u001b[1;36m1\u001b[0m, \u001b[32m\"scanned_files\"\u001b[0m: \n",
"\u001b[1m[\u001b[0m\u001b[32m\"/Users/mehrinkiani/Documents/modelscan/notebooks/KerasModels/unsafe_model.h5\"\u001b[0m\u001b[1m]\u001b[0m\n",
"\u001b[1m}\u001b[0m\u001b[1m}\u001b[0m\n"
]
}
],
"source": [
"# This will save the scan results in file: keras-model-scan-results.json\n",
"!modelscan --path KerasModels/unsafe_model.h5 -r json -o keras-model-scan-results.json"
]
},
{
"cell_type": "code",
"execution_count": null,
Expand All @@ -327,7 +389,7 @@
],
"metadata": {
"kernelspec": {
"display_name": "Python 3.9.16 ('notebooks-xgb-2')",
"display_name": "Python 3.10.13 ('py310')",
"language": "python",
"name": "python3"
},
Expand All @@ -341,12 +403,12 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.16"
"version": "3.10.13"
},
"orig_nbformat": 4,
"vscode": {
"interpreter": {
"hash": "8792b9cba3843e3778a70fb92fd4a6e11f0e29f4d97b60d08b903ca0b490cce6"
"hash": "bd638e2064d9001d4ca93bc8e56e039dad230900dd235e8a6196f1614960903a"
}
}
},
Expand Down
Loading
Loading