Skip to content

Commit

Permalink
transferability check
Browse files Browse the repository at this point in the history
  • Loading branch information
@prabhant
prabhant committed Dec 12, 2017
1 parent 377275d commit 120076f
Show file tree
Hide file tree
Showing 13 changed files with 660 additions and 53 deletions.
20 changes: 9 additions & 11 deletions .ipynb_checkpoints/Adversarial-checkpoint.ipynb
View file
Expand Up @@ -741,30 +741,28 @@
},
{
"cell_type": "code",
"execution_count": 72,
"execution_count": 78,
"metadata": {},
"outputs": [
{
"ename": "TypeError",
"evalue": "arg_scope() missing 1 required positional argument: 'list_ops_or_scope'",
"ename": "AttributeError",
"evalue": "module 'tensorflow.contrib.slim.python.slim.nets.inception' has no attribute 'inception_resnet_v2_arg_scope'",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-72-39994928780b>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 9\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mlogits\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mprobs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 10\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 11\u001b[0;31m \u001b[0mlogits\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mprobs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mResnet\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimage\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mreuse\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;32m<ipython-input-72-39994928780b>\u001b[0m in \u001b[0;36mResnet\u001b[0;34m(image, reuse)\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mResnet\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimage\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mreuse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[0mpreprocessed\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmultiply\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msubtract\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexpand_dims\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimage\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m0.5\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m2.0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 3\u001b[0;31m \u001b[0marg_scope\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnets\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mresnet_v2\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0marg_scope\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mweight_decay\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0.0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 4\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mslim\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0marg_scope\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0marg_scope\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m logits, _ = nets.resnet.resnet_v2(\n",
"\u001b[0;32m/usr/lib/python3.5/contextlib.py\u001b[0m in \u001b[0;36mhelper\u001b[0;34m(*args, **kwds)\u001b[0m\n\u001b[1;32m 131\u001b[0m \u001b[0;34m@\u001b[0m\u001b[0mwraps\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfunc\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 132\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mhelper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 133\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0m_GeneratorContextManager\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfunc\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 134\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mhelper\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 135\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/lib/python3.5/contextlib.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, func, args, kwds)\u001b[0m\n\u001b[1;32m 36\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 37\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m__init__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 38\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgen\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 39\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfunc\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkwds\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwds\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 40\u001b[0m \u001b[0;31m# Issue 19330: ensure context manager instances have good docstrings\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mTypeError\u001b[0m: arg_scope() missing 1 required positional argument: 'list_ops_or_scope'"
"\u001b[0;31mAttributeError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-78-0f06d96add24>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 9\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mlogits\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mprobs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 10\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 11\u001b[0;31m \u001b[0mlogits\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mprobs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mResnet\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimage\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mreuse\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;32m<ipython-input-78-0f06d96add24>\u001b[0m in \u001b[0;36mResnet\u001b[0;34m(image, reuse)\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mResnet\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimage\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mreuse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[0mpreprocessed\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmultiply\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msubtract\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexpand_dims\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimage\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m0.5\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m2.0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 3\u001b[0;31m \u001b[0marg_scope\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnets\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minception\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minception_resnet_v2_arg_scope\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mweight_decay\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0.0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 4\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mslim\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0marg_scope\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0marg_scope\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m logits, _ = nets.inception.inception_resnet_v2_base(\n",
"\u001b[0;31mAttributeError\u001b[0m: module 'tensorflow.contrib.slim.python.slim.nets.inception' has no attribute 'inception_resnet_v2_arg_scope'"
]
}
],
"source": [
"def Resnet(image, reuse):\n",
" preprocessed = tf.multiply(tf.subtract(tf.expand_dims(image, 0), 0.5), 2.0)\n",
" arg_scope = nets.inception.resnet_v2.arg_scope(weight_decay=0.0)\n",
" arg_scope = nets.inception.inception_resnet_v2_arg_scope(weight_decay=0.0)\n",
" with slim.arg_scope(arg_scope):\n",
" logits, _ = nets.inception.inception_v3(\n",
" logits, _ = nets.inception.inception_resnet_v2_base(\n",
" preprocessed, 1001, is_training=False, reuse=reuse)\n",
" logits = logits[:,1:]\n",
" probs = tf.nn.softmax(logits)\n",
Expand Down
6 changes: 6 additions & 0 deletions .ipynb_checkpoints/classify-checkpoint.ipynb
View file
@@ -0,0 +1,6 @@
{
"cells": [],
"metadata": {},
"nbformat": 4,
"nbformat_minor": 2
}
110 changes: 68 additions & 42 deletions Adversarial.ipynb
View file

Large diffs are not rendered by default.

Binary file added __pycache__/imagenet_utils.cpython-35.pyc
View file
Binary file not shown.
Binary file added __pycache__/resnet50.cpython-35.pyc
View file
Binary file not shown.
230 changes: 230 additions & 0 deletions classify.ipynb
View file
@@ -0,0 +1,230 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Predicted: [('n02123045', 'tabby', 0.84942955), ('n02123159', 'tiger_cat', 0.072093554), ('n02124075', 'Egyptian_cat', 0.069290839)]\n"
]
}
],
"source": [
"from keras.applications.resnet50 import ResNet50\n",
"from keras.preprocessing import image\n",
"from keras.applications.resnet50 import preprocess_input, decode_predictions\n",
"import numpy as np\n",
"\n",
"model = ResNet50(weights='imagenet')\n",
"\n",
"img_path = 'outfile4.jpg'\n",
"img = image.load_img(img_path, target_size=(224, 224))\n",
"x = image.img_to_array(img)\n",
"x = np.expand_dims(x, axis=0)\n",
"x = preprocess_input(x)\n",
"\n",
"preds = model.predict(x)\n",
"# decode the results into a list of tuples (class, description, probability)\n",
"# (one such list for each sample in the batch)\n",
"print('Predicted:', decode_predictions(preds, top=3)[0])"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [],
"source": [
"import keras\n",
"model=keras.applications.inception_v3.InceptionV3(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000)"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Predicted: [('n02747177', 'ashcan', 0.99999988), ('n03873416', 'paddle', 6.22831e-08), ('n03047690', 'clog', 4.9466548e-10)]\n"
]
}
],
"source": [
"preds = model.predict(x)\n",
"# decode the results into a list of tuples (class, description, probability)\n",
"# (one such list for each sample in the batch)\n",
"print('Predicted:', decode_predictions(preds, top=3)[0])"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [],
"source": [
"model=keras.applications.inception_resnet_v2.InceptionResNetV2(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000)"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Predicted: [('n06596364', 'comic_book', 1.0), ('n04517823', 'vacuum', 2.6264047e-12), ('n02791124', 'barber_chair', 5.7342921e-29)]\n"
]
}
],
"source": [
"preds = model.predict(x)\n",
"# decode the results into a list of tuples (class, description, probability)\n",
"# (one such list for each sample in the batch)\n",
"print('Predicted:', decode_predictions(preds, top=3)[0])"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Downloading data from https://github.com/fchollet/deep-learning-models/releases/download/v0.4/xception_weights_tf_dim_ordering_tf_kernels.h5\n",
"91889664/91884032 [==============================] - 34s 0us/step\n"
]
}
],
"source": [
"model=keras.applications.xception.Xception(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000)"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Predicted: [('n03814906', 'necklace', 0.81945795), ('n02834397', 'bib', 0.17957036), ('n03594945', 'jeep', 0.00075779692)]\n"
]
}
],
"source": [
"preds = model.predict(x)\n",
"# decode the results into a list of tuples (class, description, probability)\n",
"# (one such list for each sample in the batch)\n",
"print('Predicted:', decode_predictions(preds, top=3)[0])"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Downloading data from https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg19_weights_tf_dim_ordering_tf_kernels.h5\n",
"574717952/574710816 [==============================] - 158s 0us/step\n"
]
}
],
"source": [
"model=keras.applications.vgg19.VGG19(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000)"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Predicted: [('n02123045', 'tabby', 0.5318045), ('n02123159', 'tiger_cat', 0.30907613), ('n02124075', 'Egyptian_cat', 0.132202)]\n"
]
}
],
"source": [
"preds = model.predict(x)\n",
"# decode the results into a list of tuples (class, description, probability)\n",
"# (one such list for each sample in the batch)\n",
"print('Predicted:', decode_predictions(preds, top=3)[0])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Downloading data from https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg16_weights_tf_dim_ordering_tf_kernels.h5\n",
"433479680/553467096 [======================>.......] - ETA: 45s"
]
}
],
"source": [
"model=keras.applications.vgg16.VGG16(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"preds = model.predict(x)\n",
"# decode the results into a list of tuples (class, description, probability)\n",
"# (one such list for each sample in the batch)\n",
"print('Predicted:', decode_predictions(preds, top=3)[0])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.5.2"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
48 changes: 48 additions & 0 deletions imagenet_utils.py
View file
@@ -0,0 +1,48 @@
import numpy as np
import json

from keras.utils.data_utils import get_file
from keras import backend as K

CLASS_INDEX = None
CLASS_INDEX_PATH = 'https://s3.amazonaws.com/deep-learning-models/image-models/imagenet_class_index.json'


def preprocess_input(x, dim_ordering='default'):
if dim_ordering == 'default':
dim_ordering = K.image_dim_ordering()
assert dim_ordering in {'tf', 'th'}

if dim_ordering == 'th':
x[:, 0, :, :] -= 103.939
x[:, 1, :, :] -= 116.779
x[:, 2, :, :] -= 123.68
# 'RGB'->'BGR'
x = x[:, ::-1, :, :]
else:
x[:, :, :, 0] -= 103.939
x[:, :, :, 1] -= 116.779
x[:, :, :, 2] -= 123.68
# 'RGB'->'BGR'
x = x[:, :, :, ::-1]
return x


def decode_predictions(preds, top=5):
global CLASS_INDEX
if len(preds.shape) != 2 or preds.shape[1] != 1000:
raise ValueError('`decode_predictions` expects '
'a batch of predictions '
'(i.e. a 2D array of shape (samples, 1000)). '
'Found array with shape: ' + str(preds.shape))
if CLASS_INDEX is None:
fpath = get_file('imagenet_class_index.json',
CLASS_INDEX_PATH,
cache_subdir='models')
CLASS_INDEX = json.load(open(fpath))
results = []
for pred in preds:
top_indices = pred.argsort()[-top:][::-1]
result = [tuple(CLASS_INDEX[str(i)]) + (pred[i],) for i in top_indices]
results.append(result)
return results
Binary file added my.png
View file
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added outfile.jpg
View file
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added outfile2.jpg
View file
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added outfile3.jpg
View file
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added outfile4.jpg
View file
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.

0 comments on commit 120076f

Please sign in to comment.