dl-backtrace 0.0.16__tar.gz → 0.0.17__tar.gz

{dl_backtrace-0.0.16 → dl_backtrace-0.0.17}/.github/scripts/release.py

@@ -41,7 +41,7 @@ def create_new_patch_release():
         new_version_number = bump_patch_number(last_version_number)
 
     subprocess.run(
-        ["gh", "release", "create", "--generate-notes", "0.0.16"],
+        ["gh", "release", "create", "--generate-notes", "0.0.17"],
         check=True,
     )
 

dl_backtrace-0.0.17/PKG-INFO

@@ -0,0 +1,164 @@
+Metadata-Version: 2.1
+Name: dl_backtrace
+Version: 0.0.17
+Summary: A python SDK for Deep Learning Backtrace
+Home-page: https://xai.arya.ai/docs/introduction
+License: MIT
+Keywords: aryaxai deep learning backtrace,ML observability
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.0
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: tensorflow==2.14.0
+
+# AryaXai-Backtrace
+Backtrace module for Generating Explainability on Deep learning models using TensorFlow / Pytorch
+
+# Backtrace Module
+[![License](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
+
+## Overview
+
+The Backtrace Module is a powerful and patent-pending algorithm developed by AryaXAI for enhancing the explainability of AI models, particularly in the context of complex techniques like deep learning.
+
+## Features
+
+- **Explainability:** Gain deep insights into your AI models by using the Backtrace algorithm, providing multiple explanations for their decisions.
+
+- **Consistency:** Ensure consistent and accurate explanations across different scenarios and use cases.
+
+- **Mission-Critical Support:** Tailored for mission-critical AI use cases where transparency is paramount.
+
+## Installation
+
+To integrate the Backtrace Module into your project, follow these simple steps:
+
+```bash
+pip install dl-backtrace
+```
+
+## Usage 
+
+### Tensoflow-Keras based models
+
+```python
+from dl_backtrace.tf_backtrace import Backtrace as B
+```
+
+### Pytorch based models
+
+```python
+from dl_backtrace.pytorch_backtrace import Backtrace as B
+```
+
+### Evalauting using Backtrace:
+
+1. Step - 1: Initialize a Backtrace Object using your Model
+```python
+backtrace = B(model=model)
+```
+
+2. Step - 2: Calculate layer-wise output using a data instance
+
+```python
+layer_outputs = backtrace.predict(test_data[0])
+```
+
+3. Step - 3: Calculate layer-wise Relevance using Evaluation 
+```python
+relevance = backtrace.eval(layer_outputs,mode='default',scaler=1,thresholding=0.5,task="binary-classification")
+```
+
+#### Depending on Task we have several attributes for Relevance Calculation in Evalaution:
+
+| Attribute    | Description | Values |
+|--------------|-------------|--------|
+| mode         | evaluation mode of algorithm | { default, contrastive}|
+| scaler       | Total / Starting Relevance at the Last Layer | Integer ( Default: None, Preferred: 1)|
+| thresholding | Thresholding Model Prediction in Segemntation Task to select Pixels predicting the actual class. (Only works in Segmentation Tasks) |  Default:0.5      |
+| task         | The task of the Model | { binary-classification, multi-class classification, bbox-regression, binary-segmentation} |
+
+## Example Notebooks : 
+
+### Tensorflow-Keras : 
+
+| Name        | Task        | Link                          |
+|-------------|-------------|-------------------------------|
+| Backtrace Loan Classification Tabular Dataset | Binary Classification | [Colab Link](https://colab.research.google.com/drive/1H5jaryVPEAQuqk9XPP71UIL4cemli98K?usp=sharing) |
+| Backtrace Image FMNIST Dataset | Multi-Class Classification | [Colab Link](https://colab.research.google.com/drive/1BZsdo7IWYGhdy0Pg_m8r7c3COczuW_tG?usp=sharing)  |
+| Backtrace CUB Bounding Box Regression Image Dataset | Single Object Detection | [Colab Link](https://colab.research.google.com/drive/15mmJ2aGt-_Ho7RdPWjNEEoFXE9mu9HLV?usp=sharing) |
+| Backtrace Next Word Generation Textual Dataset | Next Word Generation | [Colab Link](https://colab.research.google.com/drive/1iRMMcEm4iMVuk236vDtEB6rKsirny8cB?usp=sharing) |
+| Backtrace ImDB Sentiment Classification Textual Dataset | Sentiment Classification | [Colab Link](https://colab.research.google.com/drive/1L5nEMO6H8pbGo1Opd9S4mbYPMmq5Vl-M?usp=sharing)|
+| Backtrace Binary Classification Textual Dataset | Binary Classification | [Colab Link](https://colab.research.google.com/drive/1PxFY4hEhcIr4nTVyfwLE_29CzQTCD3dA?usp=sharing) |
+| Backtrace Multi-Class NewsGroup20 Classification Textual Dataset | Multi-Class Classification | [Colab Link](https://colab.research.google.com/drive/1u3B18TZwfTdYJeYBGcHQ0T3fzfM2USGT?usp=sharing) |
+| Backtrace CVC-ClinicDB Colonoscopy Binary Segmentation | Organ Segmentation | [Colab Link](https://colab.research.google.com/drive/1cUNUao7fahDgndVI-cpn2iSByTiWaB4j?usp=sharing) | 
+| Backtrace CamVid Road Car Binary Segmentation | Binary Segmentation | [Colab Link](https://colab.research.google.com/drive/1OAY7aAraKq_ucyVt5AYPBD8LkQOIuy1C?usp=sharing) |
+
+### Pytorch : 
+| Name        | Task        | Link                          |
+|-------------|-------------|-------------------------------|
+| Backtrace Tabular Dataset | Binary Classification | [Colab Link](https://colab.research.google.com/drive/1_r-IS7aIuATSvGNRLk8VDVVLkDSaKCpD?usp=sharing)|
+| Backtrace Image Dataset | Multi-Class Classification | [Colab Link](https://colab.research.google.com/drive/1v2XajWtIbf7Vt31Z1fnKnAjyiDzPxwnU?usp=sharing) |
+
+For more detailed examples and use cases, check out our documentation.
+
+## Supported Layers and Future Work :
+
+### Tensorflow-Keras:
+
+- [x] Dense (Fully Connected) Layer
+- [x] Convolutional Layer (Conv2D,Conv1D)
+- [x] Transpose Convolutional Layer (Conv2DTranspose,Conv1DTranspose)
+- [x] Reshape Layer
+- [x] Flatten Layer
+- [x] Global Max Pooling (2D & 1D) Layer
+- [x] Global Average Pooling (2D & 1D) Layer
+- [x] Max Pooling (2D & 1D) Layer
+- [x] Average Pooling (2D & 1D) Layer
+- [x] Concatenate Layer
+- [x] Add Layer
+- [x] Long Short-Term Memory (LSTM) Layer
+- [x] Dropout Layer
+- [x] Embedding Layer
+- [x] TextVectorization Layer
+- [ ] Other Custom Layers 
+
+### Pytorch :
+
+(Note: Currently we only Support Binary and Multi-Class Classification in Pytorch, Segmentation and Single Object Detection will be supported in the next release.)
+
+- [x] Linear (Fully Connected) Layer
+- [x] Convolutional Layer (Conv2D)
+- [x] Reshape Layer
+- [x] Flatten Layer
+- [x] Global Average Pooling 2D Layer (AdaptiveAvgPool2d)
+- [x] Max Pooling 2D Layer (MaxPool2d)
+- [x] Average Pooling 2D Layer (AvgPool2d)
+- [x] Concatenate Layer
+- [x] Add Layer
+- [x] Long Short-Term Memory (LSTM) Layer
+- [ ] Dropout Layer
+- [ ] Embedding Layer
+- [ ] EmbeddingBag Layer
+- [ ] 1d Convolution Layer (Conv1d)
+- [ ] 1d Pooling Layers (AvgPool1d,MaxPool1d,AdaptiveAvgPool1d,AdaptiveMaxPool1d)
+- [ ] Transpose Convolution Layers (ConvTranspose2d,ConvTranspose1d)
+- [ ] Global Max Pooling 2D Layer (AdaptiveMaxPool2d)
+- [ ] Other Custom Layers
+
+
+## Getting Started
+If you are new to Backtrace, head over to our Getting Started Guide to quickly set up and use the module in your projects.
+
+## Contributing
+We welcome contributions from the community. To contribute, please follow our Contribution Guidelines.
+
+## License
+This project is licensed under the MIT License - see the LICENSE file for details.
+
+## Contact
+For any inquiries or support, please contact AryaXAI Support.

dl_backtrace-0.0.17/README.md

@@ -0,0 +1,147 @@
+# AryaXai-Backtrace
+Backtrace module for Generating Explainability on Deep learning models using TensorFlow / Pytorch
+
+# Backtrace Module
+[![License](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
+
+## Overview
+
+The Backtrace Module is a powerful and patent-pending algorithm developed by AryaXAI for enhancing the explainability of AI models, particularly in the context of complex techniques like deep learning.
+
+## Features
+
+- **Explainability:** Gain deep insights into your AI models by using the Backtrace algorithm, providing multiple explanations for their decisions.
+
+- **Consistency:** Ensure consistent and accurate explanations across different scenarios and use cases.
+
+- **Mission-Critical Support:** Tailored for mission-critical AI use cases where transparency is paramount.
+
+## Installation
+
+To integrate the Backtrace Module into your project, follow these simple steps:
+
+```bash
+pip install dl-backtrace
+```
+
+## Usage 
+
+### Tensoflow-Keras based models
+
+```python
+from dl_backtrace.tf_backtrace import Backtrace as B
+```
+
+### Pytorch based models
+
+```python
+from dl_backtrace.pytorch_backtrace import Backtrace as B
+```
+
+### Evalauting using Backtrace:
+
+1. Step - 1: Initialize a Backtrace Object using your Model
+```python
+backtrace = B(model=model)
+```
+
+2. Step - 2: Calculate layer-wise output using a data instance
+
+```python
+layer_outputs = backtrace.predict(test_data[0])
+```
+
+3. Step - 3: Calculate layer-wise Relevance using Evaluation 
+```python
+relevance = backtrace.eval(layer_outputs,mode='default',scaler=1,thresholding=0.5,task="binary-classification")
+```
+
+#### Depending on Task we have several attributes for Relevance Calculation in Evalaution:
+
+| Attribute    | Description | Values |
+|--------------|-------------|--------|
+| mode         | evaluation mode of algorithm | { default, contrastive}|
+| scaler       | Total / Starting Relevance at the Last Layer | Integer ( Default: None, Preferred: 1)|
+| thresholding | Thresholding Model Prediction in Segemntation Task to select Pixels predicting the actual class. (Only works in Segmentation Tasks) |  Default:0.5      |
+| task         | The task of the Model | { binary-classification, multi-class classification, bbox-regression, binary-segmentation} |
+
+## Example Notebooks : 
+
+### Tensorflow-Keras : 
+
+| Name        | Task        | Link                          |
+|-------------|-------------|-------------------------------|
+| Backtrace Loan Classification Tabular Dataset | Binary Classification | [Colab Link](https://colab.research.google.com/drive/1H5jaryVPEAQuqk9XPP71UIL4cemli98K?usp=sharing) |
+| Backtrace Image FMNIST Dataset | Multi-Class Classification | [Colab Link](https://colab.research.google.com/drive/1BZsdo7IWYGhdy0Pg_m8r7c3COczuW_tG?usp=sharing)  |
+| Backtrace CUB Bounding Box Regression Image Dataset | Single Object Detection | [Colab Link](https://colab.research.google.com/drive/15mmJ2aGt-_Ho7RdPWjNEEoFXE9mu9HLV?usp=sharing) |
+| Backtrace Next Word Generation Textual Dataset | Next Word Generation | [Colab Link](https://colab.research.google.com/drive/1iRMMcEm4iMVuk236vDtEB6rKsirny8cB?usp=sharing) |
+| Backtrace ImDB Sentiment Classification Textual Dataset | Sentiment Classification | [Colab Link](https://colab.research.google.com/drive/1L5nEMO6H8pbGo1Opd9S4mbYPMmq5Vl-M?usp=sharing)|
+| Backtrace Binary Classification Textual Dataset | Binary Classification | [Colab Link](https://colab.research.google.com/drive/1PxFY4hEhcIr4nTVyfwLE_29CzQTCD3dA?usp=sharing) |
+| Backtrace Multi-Class NewsGroup20 Classification Textual Dataset | Multi-Class Classification | [Colab Link](https://colab.research.google.com/drive/1u3B18TZwfTdYJeYBGcHQ0T3fzfM2USGT?usp=sharing) |
+| Backtrace CVC-ClinicDB Colonoscopy Binary Segmentation | Organ Segmentation | [Colab Link](https://colab.research.google.com/drive/1cUNUao7fahDgndVI-cpn2iSByTiWaB4j?usp=sharing) | 
+| Backtrace CamVid Road Car Binary Segmentation | Binary Segmentation | [Colab Link](https://colab.research.google.com/drive/1OAY7aAraKq_ucyVt5AYPBD8LkQOIuy1C?usp=sharing) |
+
+### Pytorch : 
+| Name        | Task        | Link                          |
+|-------------|-------------|-------------------------------|
+| Backtrace Tabular Dataset | Binary Classification | [Colab Link](https://colab.research.google.com/drive/1_r-IS7aIuATSvGNRLk8VDVVLkDSaKCpD?usp=sharing)|
+| Backtrace Image Dataset | Multi-Class Classification | [Colab Link](https://colab.research.google.com/drive/1v2XajWtIbf7Vt31Z1fnKnAjyiDzPxwnU?usp=sharing) |
+
+For more detailed examples and use cases, check out our documentation.
+
+## Supported Layers and Future Work :
+
+### Tensorflow-Keras:
+
+- [x] Dense (Fully Connected) Layer
+- [x] Convolutional Layer (Conv2D,Conv1D)
+- [x] Transpose Convolutional Layer (Conv2DTranspose,Conv1DTranspose)
+- [x] Reshape Layer
+- [x] Flatten Layer
+- [x] Global Max Pooling (2D & 1D) Layer
+- [x] Global Average Pooling (2D & 1D) Layer
+- [x] Max Pooling (2D & 1D) Layer
+- [x] Average Pooling (2D & 1D) Layer
+- [x] Concatenate Layer
+- [x] Add Layer
+- [x] Long Short-Term Memory (LSTM) Layer
+- [x] Dropout Layer
+- [x] Embedding Layer
+- [x] TextVectorization Layer
+- [ ] Other Custom Layers 
+
+### Pytorch :
+
+(Note: Currently we only Support Binary and Multi-Class Classification in Pytorch, Segmentation and Single Object Detection will be supported in the next release.)
+
+- [x] Linear (Fully Connected) Layer
+- [x] Convolutional Layer (Conv2D)
+- [x] Reshape Layer
+- [x] Flatten Layer
+- [x] Global Average Pooling 2D Layer (AdaptiveAvgPool2d)
+- [x] Max Pooling 2D Layer (MaxPool2d)
+- [x] Average Pooling 2D Layer (AvgPool2d)
+- [x] Concatenate Layer
+- [x] Add Layer
+- [x] Long Short-Term Memory (LSTM) Layer
+- [ ] Dropout Layer
+- [ ] Embedding Layer
+- [ ] EmbeddingBag Layer
+- [ ] 1d Convolution Layer (Conv1d)
+- [ ] 1d Pooling Layers (AvgPool1d,MaxPool1d,AdaptiveAvgPool1d,AdaptiveMaxPool1d)
+- [ ] Transpose Convolution Layers (ConvTranspose2d,ConvTranspose1d)
+- [ ] Global Max Pooling 2D Layer (AdaptiveMaxPool2d)
+- [ ] Other Custom Layers
+
+
+## Getting Started
+If you are new to Backtrace, head over to our Getting Started Guide to quickly set up and use the module in your projects.
+
+## Contributing
+We welcome contributions from the community. To contribute, please follow our Contribution Guidelines.
+
+## License
+This project is licensed under the MIT License - see the LICENSE file for details.
+
+## Contact
+For any inquiries or support, please contact AryaXAI Support.

dl_backtrace-0.0.17/dl_backtrace/old_backtrace/__init__.py

@@ -0,0 +1 @@
+

{dl_backtrace-0.0.16 → dl_backtrace-0.0.17}/dl_backtrace/tf_backtrace/backtrace/backtrace.py

@@ -51,6 +51,7 @@ class Backtrace(object):
             self.model_weights = EN.extract_encoder_weights(model)
             # # calculate the output of each submodule of the encoder model
             # self.all_out_model = EN.create_encoder_output(model)
+            self.activation_dict = None
         elif model_type == 'encoder_decoder':
             # create a tree-like structure and layer_stack for encoder-decoder model
             self.model_resource, self.layer_stack = ED.build_enc_dec_tree(model)
@@ -58,6 +59,7 @@ class Backtrace(object):
             self.model_weights = ED.extract_encoder_decoder_weights(model)
             # # calculate the output of each submodule of the encoder-decoder model
             # self.all_out_model = ED.calculate_encoder_decoder_output(model)
+            self.activation_dict = None 
         
         else:
             self.create_tree(model.layers)
@@ -227,7 +229,7 @@ class Backtrace(object):
         all_wt = {}
         if len(start_wt) == 0:
             if self.model_type == 'encoder':
-                start_wt = UP.calculate_start_wt_UP(all_out[out_layer])
+                start_wt = UP.calculate_start_wt(all_out[out_layer])
                 all_wt[out_layer] = start_wt * multiplier
                 layer_stack = self.layer_stack
                 all_wts = self.model_weights
@@ -439,7 +441,7 @@ class Backtrace(object):
                     all_wt[child_nodes[0]] = all_wt[child_nodes[0]] + temp_wt.sum()
                 elif model_resource["graph"][start_layer]["class"] == "Self_Attention":
                     weights = all_wts[start_layer]
-                    self_attention_weights = HP.rename_attention_keys(weights)
+                    self_attention_weights = HP.rename_self_attention_keys(weights)
                     temp_wt = UP.calculate_wt_self_attention(
                         all_wt[start_layer],
                         all_out[child_nodes[0]][0],
@@ -447,7 +449,7 @@ class Backtrace(object):
                     )
                     all_wt[child_nodes[0]] += temp_wt
                 elif model_resource["graph"][start_layer]["class"] == 'Residual':
-                    temp_wt = UP.calculate_wt_add(
+                    temp_wt = UP.calculate_wt_residual(
                         all_wt[start_layer],
                         [all_out[ch] for ch in child_nodes],
                     )

{dl_backtrace-0.0.16 → dl_backtrace-0.0.17}/dl_backtrace/tf_backtrace/backtrace/utils/utils_prop.py

@@ -1108,6 +1108,59 @@ def stabilize(matrix, epsilon=1e-6):
     return matrix + epsilon * np.sign(matrix)
 
 
+def calculate_wt_residual(wts, inp=None):
+    if isinstance(wts, tf.Tensor):
+        wts = wts.numpy()
+    inp = [i.numpy() if isinstance(i, tf.Tensor) else i for i in inp]
+
+    wt_mat = []
+    inp_list = []
+    expanded_wts = as_strided(
+        wts,
+        shape=(np.prod(wts.shape),),
+        strides=(wts.strides[-1],),
+        writeable=False,  # totally use this to avoid writing to memory in weird places
+    )
+
+    for x in inp:
+        expanded_input = as_strided(
+            x,
+            shape=(np.prod(x.shape),),
+            strides=(x.strides[-1],),
+            writeable=False,  # totally use this to avoid writing to memory in weird places
+        )
+        inp_list.append(expanded_input)
+        wt_mat.append(np.zeros_like(expanded_input))
+
+    wt_mat = np.array(wt_mat)
+    inp_list = np.array(inp_list)
+
+    for i in range(wt_mat.shape[1]):
+        wt_ind1 = wt_mat[:, i]
+        wt = expanded_wts[i]
+        l1_ind1 = inp_list[:, i]
+        p_ind = l1_ind1 > 0
+        n_ind = l1_ind1 < 0
+        p_sum = np.sum(l1_ind1[p_ind])
+        n_sum = np.sum(l1_ind1[n_ind]) * -1
+        t_sum = p_sum - n_sum
+        p_agg_wt = 0
+        n_agg_wt = 0
+        if p_sum + n_sum > 0:
+            p_agg_wt = p_sum / (p_sum + n_sum)
+            n_agg_wt = n_sum / (p_sum + n_sum)
+        if p_sum == 0:
+            p_sum = 1
+        if n_sum == 0:
+            n_sum = 1
+        wt_ind1[p_ind] = (l1_ind1[p_ind] / p_sum) * wt * p_agg_wt
+        wt_ind1[n_ind] = (l1_ind1[n_ind] / n_sum) * wt * n_agg_wt * -1.0
+        wt_mat[:, i] = wt_ind1
+
+    wt_mat = [i.reshape(wts.shape) for i in list(wt_mat)]
+    return wt_mat
+
+
 def calculate_relevance_V(wts, value_output):
     # Initialize wt_mat with zeros
     wt_mat_V = np.zeros((wts.shape[0], wts.shape[1], *value_output.shape))

{dl_backtrace-0.0.16 → dl_backtrace-0.0.17}/dl_backtrace/version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.0.16'
-__version_tuple__ = version_tuple = (0, 0, 16)
+__version__ = version = '0.0.17'
+__version_tuple__ = version_tuple = (0, 0, 17)

dl_backtrace-0.0.17/dl_backtrace.egg-info/PKG-INFO

@@ -0,0 +1,164 @@
+Metadata-Version: 2.1
+Name: dl_backtrace
+Version: 0.0.17
+Summary: A python SDK for Deep Learning Backtrace
+Home-page: https://xai.arya.ai/docs/introduction
+License: MIT
+Keywords: aryaxai deep learning backtrace,ML observability
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.0
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: tensorflow==2.14.0
+
+# AryaXai-Backtrace
+Backtrace module for Generating Explainability on Deep learning models using TensorFlow / Pytorch
+
+# Backtrace Module
+[![License](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
+
+## Overview
+
+The Backtrace Module is a powerful and patent-pending algorithm developed by AryaXAI for enhancing the explainability of AI models, particularly in the context of complex techniques like deep learning.
+
+## Features
+
+- **Explainability:** Gain deep insights into your AI models by using the Backtrace algorithm, providing multiple explanations for their decisions.
+
+- **Consistency:** Ensure consistent and accurate explanations across different scenarios and use cases.
+
+- **Mission-Critical Support:** Tailored for mission-critical AI use cases where transparency is paramount.
+
+## Installation
+
+To integrate the Backtrace Module into your project, follow these simple steps:
+
+```bash
+pip install dl-backtrace
+```
+
+## Usage 
+
+### Tensoflow-Keras based models
+
+```python
+from dl_backtrace.tf_backtrace import Backtrace as B
+```
+
+### Pytorch based models
+
+```python
+from dl_backtrace.pytorch_backtrace import Backtrace as B
+```
+
+### Evalauting using Backtrace:
+
+1. Step - 1: Initialize a Backtrace Object using your Model
+```python
+backtrace = B(model=model)
+```
+
+2. Step - 2: Calculate layer-wise output using a data instance
+
+```python
+layer_outputs = backtrace.predict(test_data[0])
+```
+
+3. Step - 3: Calculate layer-wise Relevance using Evaluation 
+```python
+relevance = backtrace.eval(layer_outputs,mode='default',scaler=1,thresholding=0.5,task="binary-classification")
+```
+
+#### Depending on Task we have several attributes for Relevance Calculation in Evalaution:
+
+| Attribute    | Description | Values |
+|--------------|-------------|--------|
+| mode         | evaluation mode of algorithm | { default, contrastive}|
+| scaler       | Total / Starting Relevance at the Last Layer | Integer ( Default: None, Preferred: 1)|
+| thresholding | Thresholding Model Prediction in Segemntation Task to select Pixels predicting the actual class. (Only works in Segmentation Tasks) |  Default:0.5      |
+| task         | The task of the Model | { binary-classification, multi-class classification, bbox-regression, binary-segmentation} |
+
+## Example Notebooks : 
+
+### Tensorflow-Keras : 
+
+| Name        | Task        | Link                          |
+|-------------|-------------|-------------------------------|
+| Backtrace Loan Classification Tabular Dataset | Binary Classification | [Colab Link](https://colab.research.google.com/drive/1H5jaryVPEAQuqk9XPP71UIL4cemli98K?usp=sharing) |
+| Backtrace Image FMNIST Dataset | Multi-Class Classification | [Colab Link](https://colab.research.google.com/drive/1BZsdo7IWYGhdy0Pg_m8r7c3COczuW_tG?usp=sharing)  |
+| Backtrace CUB Bounding Box Regression Image Dataset | Single Object Detection | [Colab Link](https://colab.research.google.com/drive/15mmJ2aGt-_Ho7RdPWjNEEoFXE9mu9HLV?usp=sharing) |
+| Backtrace Next Word Generation Textual Dataset | Next Word Generation | [Colab Link](https://colab.research.google.com/drive/1iRMMcEm4iMVuk236vDtEB6rKsirny8cB?usp=sharing) |
+| Backtrace ImDB Sentiment Classification Textual Dataset | Sentiment Classification | [Colab Link](https://colab.research.google.com/drive/1L5nEMO6H8pbGo1Opd9S4mbYPMmq5Vl-M?usp=sharing)|
+| Backtrace Binary Classification Textual Dataset | Binary Classification | [Colab Link](https://colab.research.google.com/drive/1PxFY4hEhcIr4nTVyfwLE_29CzQTCD3dA?usp=sharing) |
+| Backtrace Multi-Class NewsGroup20 Classification Textual Dataset | Multi-Class Classification | [Colab Link](https://colab.research.google.com/drive/1u3B18TZwfTdYJeYBGcHQ0T3fzfM2USGT?usp=sharing) |
+| Backtrace CVC-ClinicDB Colonoscopy Binary Segmentation | Organ Segmentation | [Colab Link](https://colab.research.google.com/drive/1cUNUao7fahDgndVI-cpn2iSByTiWaB4j?usp=sharing) | 
+| Backtrace CamVid Road Car Binary Segmentation | Binary Segmentation | [Colab Link](https://colab.research.google.com/drive/1OAY7aAraKq_ucyVt5AYPBD8LkQOIuy1C?usp=sharing) |
+
+### Pytorch : 
+| Name        | Task        | Link                          |
+|-------------|-------------|-------------------------------|
+| Backtrace Tabular Dataset | Binary Classification | [Colab Link](https://colab.research.google.com/drive/1_r-IS7aIuATSvGNRLk8VDVVLkDSaKCpD?usp=sharing)|
+| Backtrace Image Dataset | Multi-Class Classification | [Colab Link](https://colab.research.google.com/drive/1v2XajWtIbf7Vt31Z1fnKnAjyiDzPxwnU?usp=sharing) |
+
+For more detailed examples and use cases, check out our documentation.
+
+## Supported Layers and Future Work :
+
+### Tensorflow-Keras:
+
+- [x] Dense (Fully Connected) Layer
+- [x] Convolutional Layer (Conv2D,Conv1D)
+- [x] Transpose Convolutional Layer (Conv2DTranspose,Conv1DTranspose)
+- [x] Reshape Layer
+- [x] Flatten Layer
+- [x] Global Max Pooling (2D & 1D) Layer
+- [x] Global Average Pooling (2D & 1D) Layer
+- [x] Max Pooling (2D & 1D) Layer
+- [x] Average Pooling (2D & 1D) Layer
+- [x] Concatenate Layer
+- [x] Add Layer
+- [x] Long Short-Term Memory (LSTM) Layer
+- [x] Dropout Layer
+- [x] Embedding Layer
+- [x] TextVectorization Layer
+- [ ] Other Custom Layers 
+
+### Pytorch :
+
+(Note: Currently we only Support Binary and Multi-Class Classification in Pytorch, Segmentation and Single Object Detection will be supported in the next release.)
+
+- [x] Linear (Fully Connected) Layer
+- [x] Convolutional Layer (Conv2D)
+- [x] Reshape Layer
+- [x] Flatten Layer
+- [x] Global Average Pooling 2D Layer (AdaptiveAvgPool2d)
+- [x] Max Pooling 2D Layer (MaxPool2d)
+- [x] Average Pooling 2D Layer (AvgPool2d)
+- [x] Concatenate Layer
+- [x] Add Layer
+- [x] Long Short-Term Memory (LSTM) Layer
+- [ ] Dropout Layer
+- [ ] Embedding Layer
+- [ ] EmbeddingBag Layer
+- [ ] 1d Convolution Layer (Conv1d)
+- [ ] 1d Pooling Layers (AvgPool1d,MaxPool1d,AdaptiveAvgPool1d,AdaptiveMaxPool1d)
+- [ ] Transpose Convolution Layers (ConvTranspose2d,ConvTranspose1d)
+- [ ] Global Max Pooling 2D Layer (AdaptiveMaxPool2d)
+- [ ] Other Custom Layers
+
+
+## Getting Started
+If you are new to Backtrace, head over to our Getting Started Guide to quickly set up and use the module in your projects.
+
+## Contributing
+We welcome contributions from the community. To contribute, please follow our Contribution Guidelines.
+
+## License
+This project is licensed under the MIT License - see the LICENSE file for details.
+
+## Contact
+For any inquiries or support, please contact AryaXAI Support.

{dl_backtrace-0.0.16 → dl_backtrace-0.0.17}/dl_backtrace.egg-info/SOURCES.txt

@@ -15,6 +15,7 @@ dl_backtrace.egg-info/SOURCES.txt
 dl_backtrace.egg-info/dependency_links.txt
 dl_backtrace.egg-info/requires.txt
 dl_backtrace.egg-info/top_level.txt
+dl_backtrace/old_backtrace/__init__.py
 dl_backtrace/old_backtrace/pytorch_backtrace/__init__.py
 dl_backtrace/old_backtrace/pytorch_backtrace/backtrace/__init__.py
 dl_backtrace/old_backtrace/pytorch_backtrace/backtrace/backtrace.py

dl_backtrace-0.0.16/PKG-INFO

@@ -1,102 +0,0 @@
-Metadata-Version: 2.1
-Name: dl_backtrace
-Version: 0.0.16
-Summary: A python SDK for Deep Learning Backtrace
-Home-page: https://xai.arya.ai/docs/introduction
-License: MIT
-Keywords: aryaxai deep learning backtrace,ML observability
-Classifier: Intended Audience :: Developers
-Classifier: Intended Audience :: Science/Research
-Classifier: Programming Language :: Python :: 3
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Requires-Python: >=3.0
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: tensorflow==2.14.0
-
-# AryaXai-Backtrace
-Backtrace module for Generating Explainability on Deep learning models using TensorFlow / Pytorch
-
-# Backtrace Module
-[![License](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
-
-## Overview
-
-The Backtrace Module is a powerful and patent-pending algorithm developed by AryaXAI for enhancing the explainability of AI models, particularly in the context of complex techniques like deep learning.
-
-## Features
-
-- **Explainability:** Gain deep insights into your AI models by using the Backtrace algorithm, providing multiple explanations for their decisions.
-
-- **Consistency:** Ensure consistent and accurate explanations across different scenarios and use cases.
-
-- **Mission-Critical Support:** Tailored for mission-critical AI use cases where transparency is paramount.
-
-## Installation
-
-To integrate the Backtrace Module into your project, follow these simple steps:
-
-```bash
-pip install dl-backtrace
-```
-
-usage for Tensoflow based models
-
-```python
-from dl_backtrace.tf_backtrace import Backtrace as B
-from dl_backtrace.tf_backtrace import contrast as UC
-from dl_backtrace.tf_backtrace import prop as UP
-from dl_backtrace.tf_backtrace import activation_master
-```
-
-usage for Pytorch based models
-
-```python
-from dl_backtrace.pytorch_backtrace import Backtrace as B
-from dl_backtrace.pytorch_backtrace import contrast as UC
-from dl_backtrace.pytorch_backtrace import prop as UP
-from dl_backtrace.pytorch_backtrace import activation_master
-```
-
-## Example Notebooks
-
-| Name        | Link                          |
-|-------------|-------------------------------|
-| Tensorflow Backtrace Tabular Dataset | [Colab Link](https://colab.research.google.com/drive/1A4J-wgShD7M_pUmsqbnI8BD3hE43dT8o?usp=sharing)  |
-| Tensorflow Backtrace Textual Dataset | [Colab Link](https://colab.research.google.com/drive/1zT_K8mHdzyfQe_LG576qwiBqw8o6LRQH?usp=sharing)  |
-| Tensorflow Backtrace Image Dataset | [Colab Link](https://colab.research.google.com/drive/1KbLtcjYDrPQvG6oJj1wmHdiWxRrtKNrV?usp=sharing)  |
-| Pytorch Backtrace Tabular Dataset | [Colab Link](https://colab.research.google.com/drive/1Z4UJNFd83dwXBMM0cmiNYEjh6xhRtQA_?usp=sharing) |
-| Pytorch Backtrace Image Dataset | [Colab Link](https://colab.research.google.com/drive/14XKwCsS9IZep2AlDDYfavnVRNz8_b-jM?usp=sharing) |
-
-
-For more detailed examples and use cases, check out our documentation.
-
-## Supported Layers and Future Work
-- [x] Dense (Fully Connected) Layer
-- [x] Convolutional Layer (Conv2D)
-- [x] Reshape Layer
-- [x] Flatten Layer
-- [x] Global Average Pooling 2D Layer
-- [x] Max Pooling 2D Layer
-- [x] Average Pooling 2D Layer
-- [x] Concatenate Layer
-- [x] Add Layer
-- [x] Long Short-Term Memory (LSTM) Layer
-- [x] Batch Normalisation Layer
-- [x] Dropout Layer
-- [ ] Embedding Layer
-- [ ] Other Custom Layers
-
-
-## Getting Started
-If you are new to Backtrace, head over to our Getting Started Guide to quickly set up and use the module in your projects.
-
-## Contributing
-We welcome contributions from the community. To contribute, please follow our Contribution Guidelines.
-
-## License
-This project is licensed under the MIT License - see the LICENSE file for details.
-
-## Contact
-For any inquiries or support, please contact AryaXAI Support.

dl_backtrace-0.0.16/README.md

@@ -1,85 +0,0 @@
-# AryaXai-Backtrace
-Backtrace module for Generating Explainability on Deep learning models using TensorFlow / Pytorch
-
-# Backtrace Module
-[![License](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
-
-## Overview
-
-The Backtrace Module is a powerful and patent-pending algorithm developed by AryaXAI for enhancing the explainability of AI models, particularly in the context of complex techniques like deep learning.
-
-## Features
-
-- **Explainability:** Gain deep insights into your AI models by using the Backtrace algorithm, providing multiple explanations for their decisions.
-
-- **Consistency:** Ensure consistent and accurate explanations across different scenarios and use cases.
-
-- **Mission-Critical Support:** Tailored for mission-critical AI use cases where transparency is paramount.
-
-## Installation
-
-To integrate the Backtrace Module into your project, follow these simple steps:
-
-```bash
-pip install dl-backtrace
-```
-
-usage for Tensoflow based models
-
-```python
-from dl_backtrace.tf_backtrace import Backtrace as B
-from dl_backtrace.tf_backtrace import contrast as UC
-from dl_backtrace.tf_backtrace import prop as UP
-from dl_backtrace.tf_backtrace import activation_master
-```
-
-usage for Pytorch based models
-
-```python
-from dl_backtrace.pytorch_backtrace import Backtrace as B
-from dl_backtrace.pytorch_backtrace import contrast as UC
-from dl_backtrace.pytorch_backtrace import prop as UP
-from dl_backtrace.pytorch_backtrace import activation_master
-```
-
-## Example Notebooks
-
-| Name        | Link                          |
-|-------------|-------------------------------|
-| Tensorflow Backtrace Tabular Dataset | [Colab Link](https://colab.research.google.com/drive/1A4J-wgShD7M_pUmsqbnI8BD3hE43dT8o?usp=sharing)  |
-| Tensorflow Backtrace Textual Dataset | [Colab Link](https://colab.research.google.com/drive/1zT_K8mHdzyfQe_LG576qwiBqw8o6LRQH?usp=sharing)  |
-| Tensorflow Backtrace Image Dataset | [Colab Link](https://colab.research.google.com/drive/1KbLtcjYDrPQvG6oJj1wmHdiWxRrtKNrV?usp=sharing)  |
-| Pytorch Backtrace Tabular Dataset | [Colab Link](https://colab.research.google.com/drive/1Z4UJNFd83dwXBMM0cmiNYEjh6xhRtQA_?usp=sharing) |
-| Pytorch Backtrace Image Dataset | [Colab Link](https://colab.research.google.com/drive/14XKwCsS9IZep2AlDDYfavnVRNz8_b-jM?usp=sharing) |
-
-
-For more detailed examples and use cases, check out our documentation.
-
-## Supported Layers and Future Work
-- [x] Dense (Fully Connected) Layer
-- [x] Convolutional Layer (Conv2D)
-- [x] Reshape Layer
-- [x] Flatten Layer
-- [x] Global Average Pooling 2D Layer
-- [x] Max Pooling 2D Layer
-- [x] Average Pooling 2D Layer
-- [x] Concatenate Layer
-- [x] Add Layer
-- [x] Long Short-Term Memory (LSTM) Layer
-- [x] Batch Normalisation Layer
-- [x] Dropout Layer
-- [ ] Embedding Layer
-- [ ] Other Custom Layers
-
-
-## Getting Started
-If you are new to Backtrace, head over to our Getting Started Guide to quickly set up and use the module in your projects.
-
-## Contributing
-We welcome contributions from the community. To contribute, please follow our Contribution Guidelines.
-
-## License
-This project is licensed under the MIT License - see the LICENSE file for details.
-
-## Contact
-For any inquiries or support, please contact AryaXAI Support.

dl_backtrace-0.0.16/dl_backtrace.egg-info/PKG-INFO

@@ -1,102 +0,0 @@
-Metadata-Version: 2.1
-Name: dl_backtrace
-Version: 0.0.16
-Summary: A python SDK for Deep Learning Backtrace
-Home-page: https://xai.arya.ai/docs/introduction
-License: MIT
-Keywords: aryaxai deep learning backtrace,ML observability
-Classifier: Intended Audience :: Developers
-Classifier: Intended Audience :: Science/Research
-Classifier: Programming Language :: Python :: 3
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Requires-Python: >=3.0
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: tensorflow==2.14.0
-
-# AryaXai-Backtrace
-Backtrace module for Generating Explainability on Deep learning models using TensorFlow / Pytorch
-
-# Backtrace Module
-[![License](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
-
-## Overview
-
-The Backtrace Module is a powerful and patent-pending algorithm developed by AryaXAI for enhancing the explainability of AI models, particularly in the context of complex techniques like deep learning.
-
-## Features
-
-- **Explainability:** Gain deep insights into your AI models by using the Backtrace algorithm, providing multiple explanations for their decisions.
-
-- **Consistency:** Ensure consistent and accurate explanations across different scenarios and use cases.
-
-- **Mission-Critical Support:** Tailored for mission-critical AI use cases where transparency is paramount.
-
-## Installation
-
-To integrate the Backtrace Module into your project, follow these simple steps:
-
-```bash
-pip install dl-backtrace
-```
-
-usage for Tensoflow based models
-
-```python
-from dl_backtrace.tf_backtrace import Backtrace as B
-from dl_backtrace.tf_backtrace import contrast as UC
-from dl_backtrace.tf_backtrace import prop as UP
-from dl_backtrace.tf_backtrace import activation_master
-```
-
-usage for Pytorch based models
-
-```python
-from dl_backtrace.pytorch_backtrace import Backtrace as B
-from dl_backtrace.pytorch_backtrace import contrast as UC
-from dl_backtrace.pytorch_backtrace import prop as UP
-from dl_backtrace.pytorch_backtrace import activation_master
-```
-
-## Example Notebooks
-
-| Name        | Link                          |
-|-------------|-------------------------------|
-| Tensorflow Backtrace Tabular Dataset | [Colab Link](https://colab.research.google.com/drive/1A4J-wgShD7M_pUmsqbnI8BD3hE43dT8o?usp=sharing)  |
-| Tensorflow Backtrace Textual Dataset | [Colab Link](https://colab.research.google.com/drive/1zT_K8mHdzyfQe_LG576qwiBqw8o6LRQH?usp=sharing)  |
-| Tensorflow Backtrace Image Dataset | [Colab Link](https://colab.research.google.com/drive/1KbLtcjYDrPQvG6oJj1wmHdiWxRrtKNrV?usp=sharing)  |
-| Pytorch Backtrace Tabular Dataset | [Colab Link](https://colab.research.google.com/drive/1Z4UJNFd83dwXBMM0cmiNYEjh6xhRtQA_?usp=sharing) |
-| Pytorch Backtrace Image Dataset | [Colab Link](https://colab.research.google.com/drive/14XKwCsS9IZep2AlDDYfavnVRNz8_b-jM?usp=sharing) |
-
-
-For more detailed examples and use cases, check out our documentation.
-
-## Supported Layers and Future Work
-- [x] Dense (Fully Connected) Layer
-- [x] Convolutional Layer (Conv2D)
-- [x] Reshape Layer
-- [x] Flatten Layer
-- [x] Global Average Pooling 2D Layer
-- [x] Max Pooling 2D Layer
-- [x] Average Pooling 2D Layer
-- [x] Concatenate Layer
-- [x] Add Layer
-- [x] Long Short-Term Memory (LSTM) Layer
-- [x] Batch Normalisation Layer
-- [x] Dropout Layer
-- [ ] Embedding Layer
-- [ ] Other Custom Layers
-
-
-## Getting Started
-If you are new to Backtrace, head over to our Getting Started Guide to quickly set up and use the module in your projects.
-
-## Contributing
-We welcome contributions from the community. To contribute, please follow our Contribution Guidelines.
-
-## License
-This project is licensed under the MIT License - see the LICENSE file for details.
-
-## Contact
-For any inquiries or support, please contact AryaXAI Support.