diff options
| author | CoprDistGit <infra@openeuler.org> | 2023-06-09 01:25:34 +0000 |
|---|---|---|
| committer | CoprDistGit <infra@openeuler.org> | 2023-06-09 01:25:34 +0000 |
| commit | e38e53ad3be9ccf9c48b2206a122dcc8366d1815 (patch) | |
| tree | 204035283b81f8f2689766ba24e2ca3de6335bd5 | |
| parent | 3e9bd0dbca26bb77e1663399a74a384936eb7786 (diff) | |
automatic import of python-tf-keras-visopeneuler20.03
| -rw-r--r-- | .gitignore | 1 | ||||
| -rw-r--r-- | python-tf-keras-vis.spec | 797 | ||||
| -rw-r--r-- | sources | 1 |
3 files changed, 799 insertions, 0 deletions
@@ -0,0 +1 @@ +/tf-keras-vis-0.8.5.tar.gz diff --git a/python-tf-keras-vis.spec b/python-tf-keras-vis.spec new file mode 100644 index 0000000..0abcf0d --- /dev/null +++ b/python-tf-keras-vis.spec @@ -0,0 +1,797 @@ +%global _empty_manifest_terminate_build 0 +Name: python-tf-keras-vis +Version: 0.8.5 +Release: 1 +Summary: Neural network visualization toolkit for tf.keras +License: MIT License +URL: https://github.com/keisen/tf-keras-vis +Source0: https://mirrors.aliyun.com/pypi/web/packages/fc/98/a542ccb528a764302b7db123c9ff19736879a81d5d326a5d2899f99561e8/tf-keras-vis-0.8.5.tar.gz +BuildArch: noarch + +Requires: python3-scipy +Requires: python3-pillow +Requires: python3-deprecated +Requires: python3-imageio +Requires: python3-packaging +Requires: python3-importlib-metadata +Requires: python3-flake8 +Requires: python3-flake8-docstrings +Requires: python3-isort +Requires: python3-yapf +Requires: python3-pytest +Requires: python3-pytest-pycodestyle +Requires: python3-pytest-cov +Requires: python3-pytest-env +Requires: python3-pytest-xdist +Requires: python3-sphinx +Requires: python3-sphinx-autobuild +Requires: python3-sphinx-rtd-theme +Requires: python3-myst-parser +Requires: python3-nbsphinx +Requires: python3-pandoc +Requires: python3-jupyterlab +Requires: python3-matplotlib + +%description +# [tf-keras-vis](https://keisen.github.io/tf-keras-vis-docs/) + +<!-- sec.0 --> + +[](https://pepy.tech/project/tf-keras-vis) +[](https://badge.fury.io/py/tf-keras-vis) +[](https://badge.fury.io/py/tf-keras-vis) +[](https://github.com/keisen/tf-keras-vis/actions/workflows/python-package.yml) +[](https://opensource.org/licenses/MIT) +[](https://keisen.github.io/tf-keras-vis-docs/) + +<!-- ./sec.0 --> + + <!-- sec.1 --> + +<!-- ./sec.1 --> + +## Web documents + +https://keisen.github.io/tf-keras-vis-docs/ + + +## Overview + +<!-- sec.2 --> + +tf-keras-vis is a visualization toolkit for debugging `tf.keras.Model` in Tensorflow2.0+. +Currently supported methods for visualization include: + +* Feature Visualization + - ActivationMaximization ([web](https://distill.pub/2017/feature-visualization/), [github](https://github.com/raghakot/keras-vis)) +* Class Activation Maps + - GradCAM ([paper](https://arxiv.org/pdf/1610.02391v1.pdf)) + - GradCAM++ ([paper](https://arxiv.org/pdf/1710.11063.pdf)) + - ScoreCAM ([paper](https://arxiv.org/pdf/1910.01279.pdf), [github](https://github.com/haofanwang/Score-CAM)) + - Faster-ScoreCAM ([github](https://github.com/tabayashi0117/Score-CAM/blob/master/README.md#faster-score-cam)) + - LayerCAM ([paper](http://mftp.mmcheng.net/Papers/21TIP_LayerCAM.pdf), [github](https://github.com/PengtaoJiang/LayerCAM)) :new::zap: +* Saliency Maps + - Vanilla Saliency ([paper](https://arxiv.org/pdf/1312.6034.pdf)) + - SmoothGrad ([paper](https://arxiv.org/pdf/1706.03825.pdf)) + +tf-keras-vis is designed to be light-weight, flexible and ease of use. +All visualizations have the features as follows: + +* Support **N-dim image inputs**, that's, not only support pictures but also such as 3D images. +* Support **batch wise** processing, so, be able to efficiently process multiple input images. +* Support the model that have either **multiple inputs** or **multiple outputs**, or both. +* Support the **mixed-precision** model. + +And in ActivationMaximization, + +* Support Optimizers that are built to tf.keras. + +<!-- ./sec.2 --> + +### Visualizations + +<!-- sec.3 --> + +#### Dense Unit + +<img src='https://github.com/keisen/tf-keras-vis/raw/master/docs/examples/images/visualize-dense-layer.png' width='600px' /> + +#### Convolutional Filter + +<img src='https://github.com/keisen/tf-keras-vis/raw/master/docs/examples/images/visualize-filters.png' width='600px' /> + +#### Class Activation Map + +<img src='https://github.com/keisen/tf-keras-vis/raw/master/docs/examples/images/gradcam_plus_plus.png' width='600px' /> + +The images above are generated by `GradCAM++`. + +#### Saliency Map + +<img src='https://github.com/keisen/tf-keras-vis/raw/master/docs/examples/images/smoothgrad.png' width='600px' /> + +The images above are generated by `SmoothGrad`. + +<!-- ./sec.3 --> + +## Usage + +### ActivationMaximization (Visualizing Convolutional Filter) + +<!-- ActivationMaximization --> + +```python +import tensorflow as tf +from tensorflow.keras.applications import VGG16 +from matplotlib import pyplot as plt +from tf_keras_vis.activation_maximization import ActivationMaximization +from tf_keras_vis.activation_maximization.callbacks import Progress +from tf_keras_vis.activation_maximization.input_modifiers import Jitter, Rotate2D +from tf_keras_vis.activation_maximization.regularizers import TotalVariation2D, Norm +from tf_keras_vis.utils.model_modifiers import ExtractIntermediateLayer, ReplaceToLinear +from tf_keras_vis.utils.scores import CategoricalScore + +# Create the visualization instance. +# All visualization classes accept a model and model-modifier, which, for example, +# replaces the activation of last layer to linear function so on, in constructor. +activation_maximization = \ + ActivationMaximization(VGG16(), + model_modifier=[ExtractIntermediateLayer('block5_conv3'), + ReplaceToLinear()], + clone=False) + +# You can use Score class to specify visualizing target you want. +# And add regularizers or input-modifiers as needed. +activations = \ + activation_maximization(CategoricalScore(FILTER_INDEX), + steps=200, + input_modifiers=[Jitter(jitter=16), Rotate2D(degree=1)], + regularizers=[TotalVariation2D(weight=1.0), + Norm(weight=0.3, p=1)], + optimizer=tf.keras.optimizers.RMSprop(1.0, 0.999), + callbacks=[Progress()]) + +## Since v0.6.0, calling `astype()` is NOT necessary. +# activations = activations[0].astype(np.uint8) + +# Render +plt.imshow(activations[0]) +``` + +<!-- ./ActivationMaximization --> + +### Gradcam++ + +<!-- Gradcam++ --> + +```python +import numpy as np +from matplotlib import pyplot as plt +from matplotlib import cm +from tf_keras_vis.gradcam_plus_plus import GradcamPlusPlus +from tf_keras_vis.utils.model_modifiers import ReplaceToLinear +from tf_keras_vis.utils.scores import CategoricalScore + +# Create GradCAM++ object +gradcam = GradcamPlusPlus(YOUR_MODEL_INSTANCE, + model_modifier=ReplaceToLinear(), + clone=True) + +# Generate cam with GradCAM++ +cam = gradcam(CategoricalScore(CATEGORICAL_INDEX), + SEED_INPUT) + +## Since v0.6.0, calling `normalize()` is NOT necessary. +# cam = normalize(cam) + +plt.imshow(SEED_INPUT_IMAGE) +heatmap = np.uint8(cm.jet(cam[0])[..., :3] * 255) +plt.imshow(heatmap, cmap='jet', alpha=0.5) # overlay +``` + +<!-- ./Gradcam++ --> + +Please see the guides below for more details: + +### Getting Started Guides + +<!-- examples --> + +* [Saliency and CAMs](https://keisen.github.io/tf-keras-vis-docs/examples/attentions.html) +* [Visualize Dense Layer](https://keisen.github.io/tf-keras-vis-docs/examples/visualize_dense_layer.html) +* [Visualize Convolutional Filer](https://keisen.github.io/tf-keras-vis-docs/examples/visualize_conv_filters.html) + +<!-- ./examples --> + +**[NOTES]** +If you have ever used [keras-vis](https://github.com/raghakot/keras-vis), you may feel that tf-keras-vis is similar with keras-vis. +Actually tf-keras-vis derived from keras-vis, and both provided visualization methods are almost the same. +But please notice that tf-keras-vis APIs does NOT have compatibility with keras-vis. + + +## Requirements + +<!-- sec.5 --> + +* Python 3.7+ +* Tensorflow 2.0+ + + +<!-- ./sec.5 --> + +## Installation + +<!-- sec.6 --> + +* PyPI + +```bash +$ pip install tf-keras-vis tensorflow +``` + +* Source (for development) + +```bash +$ git clone https://github.com/keisen/tf-keras-vis.git +$ cd tf-keras-vis +$ pip install -e .[develop] tensorflow +``` + +<!-- ./sec.6 --> + +## Use Cases + +<!-- sec.7 --> + +* [chitra](https://github.com/aniketmaurya/chitra) + * A Deep Learning Computer Vision library for easy data loading, model building and model interpretation with GradCAM/GradCAM++. + + +## Known Issues + +* With InceptionV3, ActivationMaximization doesn't work well, that's, it might generate meaninglessly blur image. +* With cascading model, Gradcam and Gradcam++ don't work well, that's, it might occur some error. So we recommend to use FasterScoreCAM in this case. +* `channels-first` models and data is unsupported. + + +## ToDo + +* Guides + * Visualizing multiple attention or activation images at once utilizing batch-system of model + * Define various score functions + * Visualizing attentions with multiple inputs models + * Visualizing attentions with multiple outputs models + * Advanced score functions + * Tuning Activation Maximization + * Visualizing attentions for N-dim image inputs +* We're going to add some methods such as below + - Deep Dream + - Style transfer + + +%package -n python3-tf-keras-vis +Summary: Neural network visualization toolkit for tf.keras +Provides: python-tf-keras-vis +BuildRequires: python3-devel +BuildRequires: python3-setuptools +BuildRequires: python3-pip +%description -n python3-tf-keras-vis +# [tf-keras-vis](https://keisen.github.io/tf-keras-vis-docs/) + +<!-- sec.0 --> + +[](https://pepy.tech/project/tf-keras-vis) +[](https://badge.fury.io/py/tf-keras-vis) +[](https://badge.fury.io/py/tf-keras-vis) +[](https://github.com/keisen/tf-keras-vis/actions/workflows/python-package.yml) +[](https://opensource.org/licenses/MIT) +[](https://keisen.github.io/tf-keras-vis-docs/) + +<!-- ./sec.0 --> + + <!-- sec.1 --> + +<!-- ./sec.1 --> + +## Web documents + +https://keisen.github.io/tf-keras-vis-docs/ + + +## Overview + +<!-- sec.2 --> + +tf-keras-vis is a visualization toolkit for debugging `tf.keras.Model` in Tensorflow2.0+. +Currently supported methods for visualization include: + +* Feature Visualization + - ActivationMaximization ([web](https://distill.pub/2017/feature-visualization/), [github](https://github.com/raghakot/keras-vis)) +* Class Activation Maps + - GradCAM ([paper](https://arxiv.org/pdf/1610.02391v1.pdf)) + - GradCAM++ ([paper](https://arxiv.org/pdf/1710.11063.pdf)) + - ScoreCAM ([paper](https://arxiv.org/pdf/1910.01279.pdf), [github](https://github.com/haofanwang/Score-CAM)) + - Faster-ScoreCAM ([github](https://github.com/tabayashi0117/Score-CAM/blob/master/README.md#faster-score-cam)) + - LayerCAM ([paper](http://mftp.mmcheng.net/Papers/21TIP_LayerCAM.pdf), [github](https://github.com/PengtaoJiang/LayerCAM)) :new::zap: +* Saliency Maps + - Vanilla Saliency ([paper](https://arxiv.org/pdf/1312.6034.pdf)) + - SmoothGrad ([paper](https://arxiv.org/pdf/1706.03825.pdf)) + +tf-keras-vis is designed to be light-weight, flexible and ease of use. +All visualizations have the features as follows: + +* Support **N-dim image inputs**, that's, not only support pictures but also such as 3D images. +* Support **batch wise** processing, so, be able to efficiently process multiple input images. +* Support the model that have either **multiple inputs** or **multiple outputs**, or both. +* Support the **mixed-precision** model. + +And in ActivationMaximization, + +* Support Optimizers that are built to tf.keras. + +<!-- ./sec.2 --> + +### Visualizations + +<!-- sec.3 --> + +#### Dense Unit + +<img src='https://github.com/keisen/tf-keras-vis/raw/master/docs/examples/images/visualize-dense-layer.png' width='600px' /> + +#### Convolutional Filter + +<img src='https://github.com/keisen/tf-keras-vis/raw/master/docs/examples/images/visualize-filters.png' width='600px' /> + +#### Class Activation Map + +<img src='https://github.com/keisen/tf-keras-vis/raw/master/docs/examples/images/gradcam_plus_plus.png' width='600px' /> + +The images above are generated by `GradCAM++`. + +#### Saliency Map + +<img src='https://github.com/keisen/tf-keras-vis/raw/master/docs/examples/images/smoothgrad.png' width='600px' /> + +The images above are generated by `SmoothGrad`. + +<!-- ./sec.3 --> + +## Usage + +### ActivationMaximization (Visualizing Convolutional Filter) + +<!-- ActivationMaximization --> + +```python +import tensorflow as tf +from tensorflow.keras.applications import VGG16 +from matplotlib import pyplot as plt +from tf_keras_vis.activation_maximization import ActivationMaximization +from tf_keras_vis.activation_maximization.callbacks import Progress +from tf_keras_vis.activation_maximization.input_modifiers import Jitter, Rotate2D +from tf_keras_vis.activation_maximization.regularizers import TotalVariation2D, Norm +from tf_keras_vis.utils.model_modifiers import ExtractIntermediateLayer, ReplaceToLinear +from tf_keras_vis.utils.scores import CategoricalScore + +# Create the visualization instance. +# All visualization classes accept a model and model-modifier, which, for example, +# replaces the activation of last layer to linear function so on, in constructor. +activation_maximization = \ + ActivationMaximization(VGG16(), + model_modifier=[ExtractIntermediateLayer('block5_conv3'), + ReplaceToLinear()], + clone=False) + +# You can use Score class to specify visualizing target you want. +# And add regularizers or input-modifiers as needed. +activations = \ + activation_maximization(CategoricalScore(FILTER_INDEX), + steps=200, + input_modifiers=[Jitter(jitter=16), Rotate2D(degree=1)], + regularizers=[TotalVariation2D(weight=1.0), + Norm(weight=0.3, p=1)], + optimizer=tf.keras.optimizers.RMSprop(1.0, 0.999), + callbacks=[Progress()]) + +## Since v0.6.0, calling `astype()` is NOT necessary. +# activations = activations[0].astype(np.uint8) + +# Render +plt.imshow(activations[0]) +``` + +<!-- ./ActivationMaximization --> + +### Gradcam++ + +<!-- Gradcam++ --> + +```python +import numpy as np +from matplotlib import pyplot as plt +from matplotlib import cm +from tf_keras_vis.gradcam_plus_plus import GradcamPlusPlus +from tf_keras_vis.utils.model_modifiers import ReplaceToLinear +from tf_keras_vis.utils.scores import CategoricalScore + +# Create GradCAM++ object +gradcam = GradcamPlusPlus(YOUR_MODEL_INSTANCE, + model_modifier=ReplaceToLinear(), + clone=True) + +# Generate cam with GradCAM++ +cam = gradcam(CategoricalScore(CATEGORICAL_INDEX), + SEED_INPUT) + +## Since v0.6.0, calling `normalize()` is NOT necessary. +# cam = normalize(cam) + +plt.imshow(SEED_INPUT_IMAGE) +heatmap = np.uint8(cm.jet(cam[0])[..., :3] * 255) +plt.imshow(heatmap, cmap='jet', alpha=0.5) # overlay +``` + +<!-- ./Gradcam++ --> + +Please see the guides below for more details: + +### Getting Started Guides + +<!-- examples --> + +* [Saliency and CAMs](https://keisen.github.io/tf-keras-vis-docs/examples/attentions.html) +* [Visualize Dense Layer](https://keisen.github.io/tf-keras-vis-docs/examples/visualize_dense_layer.html) +* [Visualize Convolutional Filer](https://keisen.github.io/tf-keras-vis-docs/examples/visualize_conv_filters.html) + +<!-- ./examples --> + +**[NOTES]** +If you have ever used [keras-vis](https://github.com/raghakot/keras-vis), you may feel that tf-keras-vis is similar with keras-vis. +Actually tf-keras-vis derived from keras-vis, and both provided visualization methods are almost the same. +But please notice that tf-keras-vis APIs does NOT have compatibility with keras-vis. + + +## Requirements + +<!-- sec.5 --> + +* Python 3.7+ +* Tensorflow 2.0+ + + +<!-- ./sec.5 --> + +## Installation + +<!-- sec.6 --> + +* PyPI + +```bash +$ pip install tf-keras-vis tensorflow +``` + +* Source (for development) + +```bash +$ git clone https://github.com/keisen/tf-keras-vis.git +$ cd tf-keras-vis +$ pip install -e .[develop] tensorflow +``` + +<!-- ./sec.6 --> + +## Use Cases + +<!-- sec.7 --> + +* [chitra](https://github.com/aniketmaurya/chitra) + * A Deep Learning Computer Vision library for easy data loading, model building and model interpretation with GradCAM/GradCAM++. + + +## Known Issues + +* With InceptionV3, ActivationMaximization doesn't work well, that's, it might generate meaninglessly blur image. +* With cascading model, Gradcam and Gradcam++ don't work well, that's, it might occur some error. So we recommend to use FasterScoreCAM in this case. +* `channels-first` models and data is unsupported. + + +## ToDo + +* Guides + * Visualizing multiple attention or activation images at once utilizing batch-system of model + * Define various score functions + * Visualizing attentions with multiple inputs models + * Visualizing attentions with multiple outputs models + * Advanced score functions + * Tuning Activation Maximization + * Visualizing attentions for N-dim image inputs +* We're going to add some methods such as below + - Deep Dream + - Style transfer + + +%package help +Summary: Development documents and examples for tf-keras-vis +Provides: python3-tf-keras-vis-doc +%description help +# [tf-keras-vis](https://keisen.github.io/tf-keras-vis-docs/) + +<!-- sec.0 --> + +[](https://pepy.tech/project/tf-keras-vis) +[](https://badge.fury.io/py/tf-keras-vis) +[](https://badge.fury.io/py/tf-keras-vis) +[](https://github.com/keisen/tf-keras-vis/actions/workflows/python-package.yml) +[](https://opensource.org/licenses/MIT) +[](https://keisen.github.io/tf-keras-vis-docs/) + +<!-- ./sec.0 --> + + <!-- sec.1 --> + +<!-- ./sec.1 --> + +## Web documents + +https://keisen.github.io/tf-keras-vis-docs/ + + +## Overview + +<!-- sec.2 --> + +tf-keras-vis is a visualization toolkit for debugging `tf.keras.Model` in Tensorflow2.0+. +Currently supported methods for visualization include: + +* Feature Visualization + - ActivationMaximization ([web](https://distill.pub/2017/feature-visualization/), [github](https://github.com/raghakot/keras-vis)) +* Class Activation Maps + - GradCAM ([paper](https://arxiv.org/pdf/1610.02391v1.pdf)) + - GradCAM++ ([paper](https://arxiv.org/pdf/1710.11063.pdf)) + - ScoreCAM ([paper](https://arxiv.org/pdf/1910.01279.pdf), [github](https://github.com/haofanwang/Score-CAM)) + - Faster-ScoreCAM ([github](https://github.com/tabayashi0117/Score-CAM/blob/master/README.md#faster-score-cam)) + - LayerCAM ([paper](http://mftp.mmcheng.net/Papers/21TIP_LayerCAM.pdf), [github](https://github.com/PengtaoJiang/LayerCAM)) :new::zap: +* Saliency Maps + - Vanilla Saliency ([paper](https://arxiv.org/pdf/1312.6034.pdf)) + - SmoothGrad ([paper](https://arxiv.org/pdf/1706.03825.pdf)) + +tf-keras-vis is designed to be light-weight, flexible and ease of use. +All visualizations have the features as follows: + +* Support **N-dim image inputs**, that's, not only support pictures but also such as 3D images. +* Support **batch wise** processing, so, be able to efficiently process multiple input images. +* Support the model that have either **multiple inputs** or **multiple outputs**, or both. +* Support the **mixed-precision** model. + +And in ActivationMaximization, + +* Support Optimizers that are built to tf.keras. + +<!-- ./sec.2 --> + +### Visualizations + +<!-- sec.3 --> + +#### Dense Unit + +<img src='https://github.com/keisen/tf-keras-vis/raw/master/docs/examples/images/visualize-dense-layer.png' width='600px' /> + +#### Convolutional Filter + +<img src='https://github.com/keisen/tf-keras-vis/raw/master/docs/examples/images/visualize-filters.png' width='600px' /> + +#### Class Activation Map + +<img src='https://github.com/keisen/tf-keras-vis/raw/master/docs/examples/images/gradcam_plus_plus.png' width='600px' /> + +The images above are generated by `GradCAM++`. + +#### Saliency Map + +<img src='https://github.com/keisen/tf-keras-vis/raw/master/docs/examples/images/smoothgrad.png' width='600px' /> + +The images above are generated by `SmoothGrad`. + +<!-- ./sec.3 --> + +## Usage + +### ActivationMaximization (Visualizing Convolutional Filter) + +<!-- ActivationMaximization --> + +```python +import tensorflow as tf +from tensorflow.keras.applications import VGG16 +from matplotlib import pyplot as plt +from tf_keras_vis.activation_maximization import ActivationMaximization +from tf_keras_vis.activation_maximization.callbacks import Progress +from tf_keras_vis.activation_maximization.input_modifiers import Jitter, Rotate2D +from tf_keras_vis.activation_maximization.regularizers import TotalVariation2D, Norm +from tf_keras_vis.utils.model_modifiers import ExtractIntermediateLayer, ReplaceToLinear +from tf_keras_vis.utils.scores import CategoricalScore + +# Create the visualization instance. +# All visualization classes accept a model and model-modifier, which, for example, +# replaces the activation of last layer to linear function so on, in constructor. +activation_maximization = \ + ActivationMaximization(VGG16(), + model_modifier=[ExtractIntermediateLayer('block5_conv3'), + ReplaceToLinear()], + clone=False) + +# You can use Score class to specify visualizing target you want. +# And add regularizers or input-modifiers as needed. +activations = \ + activation_maximization(CategoricalScore(FILTER_INDEX), + steps=200, + input_modifiers=[Jitter(jitter=16), Rotate2D(degree=1)], + regularizers=[TotalVariation2D(weight=1.0), + Norm(weight=0.3, p=1)], + optimizer=tf.keras.optimizers.RMSprop(1.0, 0.999), + callbacks=[Progress()]) + +## Since v0.6.0, calling `astype()` is NOT necessary. +# activations = activations[0].astype(np.uint8) + +# Render +plt.imshow(activations[0]) +``` + +<!-- ./ActivationMaximization --> + +### Gradcam++ + +<!-- Gradcam++ --> + +```python +import numpy as np +from matplotlib import pyplot as plt +from matplotlib import cm +from tf_keras_vis.gradcam_plus_plus import GradcamPlusPlus +from tf_keras_vis.utils.model_modifiers import ReplaceToLinear +from tf_keras_vis.utils.scores import CategoricalScore + +# Create GradCAM++ object +gradcam = GradcamPlusPlus(YOUR_MODEL_INSTANCE, + model_modifier=ReplaceToLinear(), + clone=True) + +# Generate cam with GradCAM++ +cam = gradcam(CategoricalScore(CATEGORICAL_INDEX), + SEED_INPUT) + +## Since v0.6.0, calling `normalize()` is NOT necessary. +# cam = normalize(cam) + +plt.imshow(SEED_INPUT_IMAGE) +heatmap = np.uint8(cm.jet(cam[0])[..., :3] * 255) +plt.imshow(heatmap, cmap='jet', alpha=0.5) # overlay +``` + +<!-- ./Gradcam++ --> + +Please see the guides below for more details: + +### Getting Started Guides + +<!-- examples --> + +* [Saliency and CAMs](https://keisen.github.io/tf-keras-vis-docs/examples/attentions.html) +* [Visualize Dense Layer](https://keisen.github.io/tf-keras-vis-docs/examples/visualize_dense_layer.html) +* [Visualize Convolutional Filer](https://keisen.github.io/tf-keras-vis-docs/examples/visualize_conv_filters.html) + +<!-- ./examples --> + +**[NOTES]** +If you have ever used [keras-vis](https://github.com/raghakot/keras-vis), you may feel that tf-keras-vis is similar with keras-vis. +Actually tf-keras-vis derived from keras-vis, and both provided visualization methods are almost the same. +But please notice that tf-keras-vis APIs does NOT have compatibility with keras-vis. + + +## Requirements + +<!-- sec.5 --> + +* Python 3.7+ +* Tensorflow 2.0+ + + +<!-- ./sec.5 --> + +## Installation + +<!-- sec.6 --> + +* PyPI + +```bash +$ pip install tf-keras-vis tensorflow +``` + +* Source (for development) + +```bash +$ git clone https://github.com/keisen/tf-keras-vis.git +$ cd tf-keras-vis +$ pip install -e .[develop] tensorflow +``` + +<!-- ./sec.6 --> + +## Use Cases + +<!-- sec.7 --> + +* [chitra](https://github.com/aniketmaurya/chitra) + * A Deep Learning Computer Vision library for easy data loading, model building and model interpretation with GradCAM/GradCAM++. + + +## Known Issues + +* With InceptionV3, ActivationMaximization doesn't work well, that's, it might generate meaninglessly blur image. +* With cascading model, Gradcam and Gradcam++ don't work well, that's, it might occur some error. So we recommend to use FasterScoreCAM in this case. +* `channels-first` models and data is unsupported. + + +## ToDo + +* Guides + * Visualizing multiple attention or activation images at once utilizing batch-system of model + * Define various score functions + * Visualizing attentions with multiple inputs models + * Visualizing attentions with multiple outputs models + * Advanced score functions + * Tuning Activation Maximization + * Visualizing attentions for N-dim image inputs +* We're going to add some methods such as below + - Deep Dream + - Style transfer + + +%prep +%autosetup -n tf-keras-vis-0.8.5 + +%build +%py3_build + +%install +%py3_install +install -d -m755 %{buildroot}/%{_pkgdocdir} +if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi +if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi +if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi +if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi +pushd %{buildroot} +if [ -d usr/lib ]; then + find usr/lib -type f -printf "\"/%h/%f\"\n" >> filelist.lst +fi +if [ -d usr/lib64 ]; then + find usr/lib64 -type f -printf "\"/%h/%f\"\n" >> filelist.lst +fi +if [ -d usr/bin ]; then + find usr/bin -type f -printf "\"/%h/%f\"\n" >> filelist.lst +fi +if [ -d usr/sbin ]; then + find usr/sbin -type f -printf "\"/%h/%f\"\n" >> filelist.lst +fi +touch doclist.lst +if [ -d usr/share/man ]; then + find usr/share/man -type f -printf "\"/%h/%f.gz\"\n" >> doclist.lst +fi +popd +mv %{buildroot}/filelist.lst . +mv %{buildroot}/doclist.lst . + +%files -n python3-tf-keras-vis -f filelist.lst +%dir %{python3_sitelib}/* + +%files help -f doclist.lst +%{_docdir}/* + +%changelog +* Fri Jun 09 2023 Python_Bot <Python_Bot@openeuler.org> - 0.8.5-1 +- Package Spec generated @@ -0,0 +1 @@ +364ee6f2a55bb844bc62f7c62aceb551 tf-keras-vis-0.8.5.tar.gz |