profile
viewpoint
Sayak Paul sayakpaul PyImageSearch Kolkata, India sayak.dev Trying to learn how machines learn.

brohrer/academic_advisory 413

Collected opinions and advice for academic programs focused on data science skills.

sayakpaul/Benchmarking-and-MLI-experiments-on-the-Adult-dataset 30

Contains benchmarking and interpretability experiments on the Adult dataset using several libraries

ariG23498/Vigyanam 7

Code base for Vigyanam

sayakpaul/A-B-testing-with-Machine-Learning 6

Implemented an A/B Testing solution with the help of machine learning

sayakpaul/Analytics-Vidhya-Game-of-Deep-Learning-Hackathon 6

Contains my experiments for the Game of Deep Learning Hackathon conducted by Analytics Vidhya

sayakpaul/Breast-Cancer-Detection-using-Deep-Learning 6

Experiments to show the usage of deep learning to detect breast cancer from breast histopathology images

sayakpaul/Applied-Data-Science-w-Python-Specialization 5

Contains my assignments, guiding notebooks (provided as the course materials) and the datasets.

PacktPublishing/Hands-On-Python-Deep-Learning-for-Web 4

Hands-On Python Deep Learning for Web,Published by Packt

sayakpaul/Age-Detection-of-Indian-Actors 4

The repository contains my experiments for a Hackathon problem by Analytics Vidhya

sayakpaul/Age-Detector-API 3

A simple REST API based on this repository:

startedtiangolo/fastapi

started time in 2 hours

pull request commenttensorflow/docs

Tutoruial on activation heatmaps with tf.keras

@Mbah-Javis when could you start working on it?

Mbah-Javis

comment created time in 17 hours

issue commenttensorflow/tensorflow

Could not load dynamic library 'libnvinfer_plugin.so.6'

I got the same error as well. When I downgraded to TensorFlow 2.0.0 (with pip install tensorflow-gpu==2.0.0) it solved the issue.

mjlbach

comment created time in 2 days

startedinsilicomedicine/GENTRL

started time in 2 days

pull request commenttensorflow/docs

Tutoruial on activation heatmaps with tf.keras

Hi @lamberta. @Mbah-Javis participated in this year's GCI and I was one of the mentors there. He did a pretty decent job on this one hence I suggested this might be a good fit here.

Mbah-Javis

comment created time in 4 days

create barnchsayakpaul/sayakpaul.github.io

branch : master

created branch time in 5 days

created repositorysayakpaul/sayakpaul.github.io

Sayak Paul

created time in 5 days

push eventsayakpaul/sayakpaul.github.io

Sayak Paul

commit sha bbbe92a284ef4e769da7796b06688f3ef113a38e

Update _config.yml

view details

push time in 5 days

push eventsayakpaul/sayakpaul.github.io

Sayak Paul

commit sha a99d069f7369f9dc5401c8e4f7305fd7a057a0ee

Update _config.yml

view details

push time in 5 days

push eventsayakpaul/sayakpaul.github.io

Sayak Paul

commit sha 9308cb1f1ce34eb909478d3f9e42659c53161f4e

Update _config.yml

view details

push time in 5 days

create barnchsayakpaul/sayakpaul.github.io

branch : master

created branch time in 5 days

created repositorysayakpaul/sayakpaul.github.io

Sayak's portfolio site

created time in 5 days

startedfloydhub/Screenshot-to-code-backup

started time in 6 days

startedhuggingface/tokenizers

started time in 9 days

pull request commentopencv/opencv

CUDA backend for the DNN module

@adamhrv could you pass along a Python script by which the FPS could be confirmed? Would be very helpful.

YashasSamaga

comment created time in 10 days

push eventsayakpaul/TF-2.0-Hacks

Sayak Paul

commit sha b55f59890956e0af79bd95fe583fe7ce22d26b69

Add files via upload

view details

push time in 15 days

push eventsayakpaul/TF-2.0-Hacks

Sayak Paul

commit sha 353e3361351aa7bd06b36010e4567f0a32e0b9b5

Update train.py

view details

push time in 15 days

push eventsayakpaul/TF-2.0-Hacks

Sayak Paul

commit sha 952d94cbb847b352bde310f8da952ff8a2a36571

Add files via upload

view details

push time in 15 days

startedhouqp/sqlvet

started time in 15 days

push eventsayakpaul/TF-2.0-Hacks

Sayak Paul

commit sha 499e0c96face3f453b627b999ebf7269f0e803a6

Comments added

view details

push time in 16 days

startedabhiTronix/vidgear

started time in 16 days

push eventsayakpaul/TalksGiven

Sayak Paul

commit sha 38526c1c5a34a3a19b90781564cbc9f1d8e09f32

Update README.md

view details

push time in 17 days

push eventsayakpaul/TF-2.0-Hacks

Sayak Paul

commit sha ccac728c0a0408a2b0d9ddbfebfba329684e1faa

Added Bayesian Search notebook

view details

push time in 17 days

pull request commenttensorflow/docs

New Chapter Request for Kolkata, India

@soonson yeah, but this one was raised days back. Anyway thanks!

sayakpaul

comment created time in 17 days

push eventsayakpaul/awesome-machine-learning-interpretability

Sayak Paul

commit sha eeb63d74f900a01ab807d30ac8d7673028acae89

Added Google's course on Testing and Debugging in ML

view details

push time in 18 days

push eventsayakpaul/TF-2.0-Hacks

Sayak Paul

commit sha aa632e2981cbef743264abc2ad5d821ced628b62

Removed an unnecessary README

view details

push time in 18 days

push eventsayakpaul/TalksGiven

Sayak Paul

commit sha 62032544154be50c54381e5e1ff0542d2a08831d

Add files via upload

view details

push time in 19 days

startedlibindic/indic-trans

started time in 21 days

startedshakti365/nes

started time in 22 days

startedmayeaux/nodetube

started time in 22 days

pull request commentalirezadir/Production-Level-Deep-Learning

Adding resources

@alirezadir a gentle ping here to check in :)

sayakpaul

comment created time in 24 days

PR opened tensorflow/docs

Reviewers
New Chapter Request for Kolkata, India

Request to start a new TFUG chapter in India.

+1 -0

0 comment

1 changed file

pr created time in 24 days

push eventsayakpaul/docs

Sayak Paul

commit sha 027cd37e8337f197d7128fca3eca08b80db2eb26

New Chapter Request for Kolkata, India

view details

push time in 24 days

fork sayakpaul/docs

TensorFlow documentation

https://www.tensorflow.org

fork in 24 days

issue closedlmoroney/dlaicourse

tfjs@latest:2 Uncaught (in promise) Error: Argument 'b' passed to 'mul' must be a Tensor or TensorLike, but got 'null'

I am currently taking the Browser-based Models with TensorFlow.js course. I am only stuck in the Week 1 exercise.

Here's the code:

<html>
<head></head>
    <script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs@latest"></script>
    <script lang="js">
        async function run(){
            const trainingUrl = 'wdbc-train.csv';
            const trainingData = tf.data.csv(trainingUrl, {
                columnConfigs: {
                    diagnosis: {
                        isLabel: true
                    }
                }
            });

            const convertedTrainingData = 
                trainingData.map(({xs, ys}) => {
                      // console.log(trainingData);
                      return{ xs: Object.values(xs), ys: Object.values(ys)};
                  }).batch(10);
                  
            // const testingUrl = 'wdbc-test.csv';
            
            // const testingData = tf.data.csv(testingUrl, {
            //     columnConfigs: {
            //         diagnosis: {
            //             isLabel: true
            //         }
            //     }
                
            // });

            // const convertedTestingData = 
            //     testingData.map(({xs, ys}) => {
            //           return{ xs: Object.values(xs), ys: Object.values(ys)};
            //       }).batch(10);
            
            const numOfFeatures = 30;
            // console.log(numOfFeatures);
            
            const model = tf.sequential();
            model.add(tf.layers.dense({inputShape: [numOfFeatures], activation: "relu", units: 20}))
            model.add(tf.layers.dense({activation: "relu", units: 20}))
            model.add(tf.layers.dense({activation: "relu", units: 10}))
            model.add(tf.layers.dense({activation: "relu", units: 5}))
            model.add(tf.layers.dense({activation: "sigmoid", units: 1}));
            
            model.compile({loss: "binaryCrossentropy", optimizer: tf.train.rmsprop(), metrics: ["accuracy"]});

            model.summary();

            //console.log(convertedTrainingData);

            await model.fitDataset(convertedTrainingData, 
                             {epochs:100,
                              callbacks:{
                                  onEpochEnd: async(epoch, logs) =>{
                                      console.log("Epoch: " + epoch + " Loss: " + logs.loss);
                                  }
                              }});
            
            // await model.fitDataset(convertedTrainingData, 
            //                  {epochs:100,
            //                   validationData: convertedTestingData,
            //                   callbacks:{
            //                       onEpochEnd: async(epoch, logs) =>{
            //                           console.log("Epoch: " + epoch + " Loss: " + logs.loss + " Accuracy: " + logs.acc);
            //                       }
            //                   }});
            // await model.save('downloads://my_model');
            
            
        }
        run();
    </script>
<body>
</body>
</html>

And here's the console log:

tfjs@latest:2 _________________________________________________________________
tfjs@latest:2 Layer (type)                 Output shape              Param #   
tfjs@latest:2 =================================================================
tfjs@latest:2 dense_Dense1 (Dense)         [null,20]                 620       
tfjs@latest:2 _________________________________________________________________
tfjs@latest:2 dense_Dense2 (Dense)         [null,20]                 420       
tfjs@latest:2 _________________________________________________________________
tfjs@latest:2 dense_Dense3 (Dense)         [null,10]                 210       
tfjs@latest:2 _________________________________________________________________
tfjs@latest:2 dense_Dense4 (Dense)         [null,5]                  55        
tfjs@latest:2 _________________________________________________________________
tfjs@latest:2 dense_Dense5 (Dense)         [null,1]                  6         
tfjs@latest:2 =================================================================
tfjs@latest:2 Total params: 1311
tfjs@latest:2 Trainable params: 1311
tfjs@latest:2 Non-trainable params: 0
tfjs@latest:2 _________________________________________________________________
tfjs@latest:2 Uncaught (in promise) Error: Argument 'b' passed to 'mul' must be a Tensor or TensorLike, but got 'null'
    at Ke (tfjs@latest:2)
    at mul_ (tfjs@latest:2)
    at Object.mul (tfjs@latest:2)
    at t.mul (tfjs@latest:2)
    at tfjs@latest:2
    at tfjs@latest:2
    at t.scopedRun (tfjs@latest:2)
    at t.tidy (tfjs@latest:2)
    at We (tfjs@latest:2)
    at tfjs@latest:2
Ke @ tfjs@latest:2
mul_ @ tfjs@latest:2
mul @ tfjs@latest:2
t.mul @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
t.scopedRun @ tfjs@latest:2
t.tidy @ tfjs@latest:2
We @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
e.applyGradients @ tfjs@latest:2
e.minimize @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
o @ tfjs@latest:2
async function (async)
run @ wdbc_exercise.html:53
(anonymous) @ wdbc_exercise.html:73

I am absolutely running out of options here to debug this. Help would be appreciated. Thanks!

closed time in 25 days

sayakpaul

issue closedtensorflow/tfjs

tfjs@latest:2 Uncaught (in promise) Error: Argument 'b' passed to 'mul' must be a Tensor or TensorLike, but got 'null'

To get help from the community, we encourage using Stack Overflow and the tensorflow.js tag.

TensorFlow.js version

https://cdn.jsdelivr.net/npm/@tensorflow/tfjs@latest

Browser version

Version 79.0.3945.88 (Official Build) (64-bit)

Describe the problem or feature request

I am currently taking the Browser-based Models with TensorFlow.js course (by Coursera). I am only stuck in the Week 1 exercise.

Code to reproduce the bug / link to feature request

<head></head>
    <script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs@latest"></script>
    <script lang="js">
        async function run(){
            const trainingUrl = 'wdbc-train.csv';
            const trainingData = tf.data.csv(trainingUrl, {
                columnConfigs: {
                    diagnosis: {
                        isLabel: true
                    }
                }
            });

            const convertedTrainingData = 
                trainingData.map(({xs, ys}) => {
                      // console.log(trainingData);
                      return{ xs: Object.values(xs), ys: Object.values(ys)};
                  }).batch(10);
                  
            // const testingUrl = 'wdbc-test.csv';
            
            // const testingData = tf.data.csv(testingUrl, {
            //     columnConfigs: {
            //         diagnosis: {
            //             isLabel: true
            //         }
            //     }
                
            // });

            // const convertedTestingData = 
            //     testingData.map(({xs, ys}) => {
            //           return{ xs: Object.values(xs), ys: Object.values(ys)};
            //       }).batch(10);
            
            const numOfFeatures = 30;
            // console.log(numOfFeatures);
            
            const model = tf.sequential();
            model.add(tf.layers.dense({inputShape: [numOfFeatures], activation: "relu", units: 20}))
            model.add(tf.layers.dense({activation: "relu", units: 20}))
            model.add(tf.layers.dense({activation: "relu", units: 10}))
            model.add(tf.layers.dense({activation: "relu", units: 5}))
            model.add(tf.layers.dense({activation: "sigmoid", units: 1}));
            
            model.compile({loss: "binaryCrossentropy", optimizer: tf.train.rmsprop(), metrics: ["accuracy"]});

            model.summary();

            //console.log(convertedTrainingData);

            await model.fitDataset(convertedTrainingData, 
                             {epochs:100,
                              callbacks:{
                                  onEpochEnd: async(epoch, logs) =>{
                                      console.log("Epoch: " + epoch + " Loss: " + logs.loss);
                                  }
                              }});
            
            // await model.fitDataset(convertedTrainingData, 
            //                  {epochs:100,
            //                   validationData: convertedTestingData,
            //                   callbacks:{
            //                       onEpochEnd: async(epoch, logs) =>{
            //                           console.log("Epoch: " + epoch + " Loss: " + logs.loss + " Accuracy: " + logs.acc);
            //                       }
            //                   }});
            // await model.save('downloads://my_model');
            
            
        }
        run();
    </script>
<body>
</body>
</html>

Full error trace:

tfjs@latest:2 _________________________________________________________________
tfjs@latest:2 Layer (type)                 Output shape              Param #   
tfjs@latest:2 =================================================================
tfjs@latest:2 dense_Dense1 (Dense)         [null,20]                 620       
tfjs@latest:2 _________________________________________________________________
tfjs@latest:2 dense_Dense2 (Dense)         [null,20]                 420       
tfjs@latest:2 _________________________________________________________________
tfjs@latest:2 dense_Dense3 (Dense)         [null,10]                 210       
tfjs@latest:2 _________________________________________________________________
tfjs@latest:2 dense_Dense4 (Dense)         [null,5]                  55        
tfjs@latest:2 _________________________________________________________________
tfjs@latest:2 dense_Dense5 (Dense)         [null,1]                  6         
tfjs@latest:2 =================================================================
tfjs@latest:2 Total params: 1311
tfjs@latest:2 Trainable params: 1311
tfjs@latest:2 Non-trainable params: 0
tfjs@latest:2 _________________________________________________________________
tfjs@latest:2 Uncaught (in promise) Error: Argument 'b' passed to 'mul' must be a Tensor or TensorLike, but got 'null'
    at Ke (tfjs@latest:2)
    at mul_ (tfjs@latest:2)
    at Object.mul (tfjs@latest:2)
    at t.mul (tfjs@latest:2)
    at tfjs@latest:2
    at tfjs@latest:2
    at t.scopedRun (tfjs@latest:2)
    at t.tidy (tfjs@latest:2)
    at We (tfjs@latest:2)
    at tfjs@latest:2
Ke @ tfjs@latest:2
mul_ @ tfjs@latest:2
mul @ tfjs@latest:2
t.mul @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
t.scopedRun @ tfjs@latest:2
t.tidy @ tfjs@latest:2
We @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
e.applyGradients @ tfjs@latest:2
e.minimize @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
o @ tfjs@latest:2
async function (async)
run @ wdbc_exercise.html:53
(anonymous) @ wdbc_exercise.html:73

Here's the dataset I am using: https://github.com/lmoroney/dlaicourse/blob/master/TensorFlow%20Deployment/Course%201%20-%20TensorFlow-JS/Week%201/Exercise/wdbc-train.csv.

closed time in 25 days

sayakpaul

issue openedtensorflow/tfjs

tfjs@latest:2 Uncaught (in promise) Error: Argument 'b' passed to 'mul' must be a Tensor or TensorLike, but got 'null'

To get help from the community, we encourage using Stack Overflow and the tensorflow.js tag.

TensorFlow.js version

https://cdn.jsdelivr.net/npm/@tensorflow/tfjs@latest

Browser version

Version 79.0.3945.88 (Official Build) (64-bit)

Describe the problem or feature request

I am currently taking the Browser-based Models with TensorFlow.js course (by Coursera). I am only stuck in the Week 1 exercise.

Code to reproduce the bug / link to feature request

<head></head>
    <script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs@latest"></script>
    <script lang="js">
        async function run(){
            const trainingUrl = 'wdbc-train.csv';
            const trainingData = tf.data.csv(trainingUrl, {
                columnConfigs: {
                    diagnosis: {
                        isLabel: true
                    }
                }
            });

            const convertedTrainingData = 
                trainingData.map(({xs, ys}) => {
                      // console.log(trainingData);
                      return{ xs: Object.values(xs), ys: Object.values(ys)};
                  }).batch(10);
                  
            // const testingUrl = 'wdbc-test.csv';
            
            // const testingData = tf.data.csv(testingUrl, {
            //     columnConfigs: {
            //         diagnosis: {
            //             isLabel: true
            //         }
            //     }
                
            // });

            // const convertedTestingData = 
            //     testingData.map(({xs, ys}) => {
            //           return{ xs: Object.values(xs), ys: Object.values(ys)};
            //       }).batch(10);
            
            const numOfFeatures = 30;
            // console.log(numOfFeatures);
            
            const model = tf.sequential();
            model.add(tf.layers.dense({inputShape: [numOfFeatures], activation: "relu", units: 20}))
            model.add(tf.layers.dense({activation: "relu", units: 20}))
            model.add(tf.layers.dense({activation: "relu", units: 10}))
            model.add(tf.layers.dense({activation: "relu", units: 5}))
            model.add(tf.layers.dense({activation: "sigmoid", units: 1}));
            
            model.compile({loss: "binaryCrossentropy", optimizer: tf.train.rmsprop(), metrics: ["accuracy"]});

            model.summary();

            //console.log(convertedTrainingData);

            await model.fitDataset(convertedTrainingData, 
                             {epochs:100,
                              callbacks:{
                                  onEpochEnd: async(epoch, logs) =>{
                                      console.log("Epoch: " + epoch + " Loss: " + logs.loss);
                                  }
                              }});
            
            // await model.fitDataset(convertedTrainingData, 
            //                  {epochs:100,
            //                   validationData: convertedTestingData,
            //                   callbacks:{
            //                       onEpochEnd: async(epoch, logs) =>{
            //                           console.log("Epoch: " + epoch + " Loss: " + logs.loss + " Accuracy: " + logs.acc);
            //                       }
            //                   }});
            // await model.save('downloads://my_model');
            
            
        }
        run();
    </script>
<body>
</body>
</html>

Full error trace:

tfjs@latest:2 _________________________________________________________________
tfjs@latest:2 Layer (type)                 Output shape              Param #   
tfjs@latest:2 =================================================================
tfjs@latest:2 dense_Dense1 (Dense)         [null,20]                 620       
tfjs@latest:2 _________________________________________________________________
tfjs@latest:2 dense_Dense2 (Dense)         [null,20]                 420       
tfjs@latest:2 _________________________________________________________________
tfjs@latest:2 dense_Dense3 (Dense)         [null,10]                 210       
tfjs@latest:2 _________________________________________________________________
tfjs@latest:2 dense_Dense4 (Dense)         [null,5]                  55        
tfjs@latest:2 _________________________________________________________________
tfjs@latest:2 dense_Dense5 (Dense)         [null,1]                  6         
tfjs@latest:2 =================================================================
tfjs@latest:2 Total params: 1311
tfjs@latest:2 Trainable params: 1311
tfjs@latest:2 Non-trainable params: 0
tfjs@latest:2 _________________________________________________________________
tfjs@latest:2 Uncaught (in promise) Error: Argument 'b' passed to 'mul' must be a Tensor or TensorLike, but got 'null'
    at Ke (tfjs@latest:2)
    at mul_ (tfjs@latest:2)
    at Object.mul (tfjs@latest:2)
    at t.mul (tfjs@latest:2)
    at tfjs@latest:2
    at tfjs@latest:2
    at t.scopedRun (tfjs@latest:2)
    at t.tidy (tfjs@latest:2)
    at We (tfjs@latest:2)
    at tfjs@latest:2
Ke @ tfjs@latest:2
mul_ @ tfjs@latest:2
mul @ tfjs@latest:2
t.mul @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
t.scopedRun @ tfjs@latest:2
t.tidy @ tfjs@latest:2
We @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
e.applyGradients @ tfjs@latest:2
e.minimize @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
o @ tfjs@latest:2
async function (async)
run @ wdbc_exercise.html:53
(anonymous) @ wdbc_exercise.html:73

Here's the dataset I am using: https://github.com/lmoroney/dlaicourse/blob/master/TensorFlow%20Deployment/Course%201%20-%20TensorFlow-JS/Week%201/Exercise/wdbc-train.csv.

created time in 25 days

issue openedlmoroney/dlaicourse

tfjs@latest:2 Uncaught (in promise) Error: Argument 'b' passed to 'mul' must be a Tensor or TensorLike, but got 'null'

I am currently taking the Browser-based Models with TensorFlow.js course. I am only stuck in the Week 1 exercise.

Here's the code:

<html>
<head></head>
    <script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs@latest"></script>
    <script lang="js">
        async function run(){
            const trainingUrl = 'wdbc-train.csv';
            const trainingData = tf.data.csv(trainingUrl, {
                columnConfigs: {
                    diagnosis: {
                        isLabel: true
                    }
                }
            });

            const convertedTrainingData = 
                trainingData.map(({xs, ys}) => {
                      // console.log(trainingData);
                      return{ xs: Object.values(xs), ys: Object.values(ys)};
                  }).batch(10);
                  
            // const testingUrl = 'wdbc-test.csv';
            
            // const testingData = tf.data.csv(testingUrl, {
            //     columnConfigs: {
            //         diagnosis: {
            //             isLabel: true
            //         }
            //     }
                
            // });

            // const convertedTestingData = 
            //     testingData.map(({xs, ys}) => {
            //           return{ xs: Object.values(xs), ys: Object.values(ys)};
            //       }).batch(10);
            
            const numOfFeatures = 30;
            // console.log(numOfFeatures);
            
            const model = tf.sequential();
            model.add(tf.layers.dense({inputShape: [numOfFeatures], activation: "relu", units: 20}))
            model.add(tf.layers.dense({activation: "relu", units: 20}))
            model.add(tf.layers.dense({activation: "relu", units: 10}))
            model.add(tf.layers.dense({activation: "relu", units: 5}))
            model.add(tf.layers.dense({activation: "sigmoid", units: 1}));
            
            model.compile({loss: "binaryCrossentropy", optimizer: tf.train.rmsprop(), metrics: ["accuracy"]});

            model.summary();

            //console.log(convertedTrainingData);

            await model.fitDataset(convertedTrainingData, 
                             {epochs:100,
                              callbacks:{
                                  onEpochEnd: async(epoch, logs) =>{
                                      console.log("Epoch: " + epoch + " Loss: " + logs.loss);
                                  }
                              }});
            
            // await model.fitDataset(convertedTrainingData, 
            //                  {epochs:100,
            //                   validationData: convertedTestingData,
            //                   callbacks:{
            //                       onEpochEnd: async(epoch, logs) =>{
            //                           console.log("Epoch: " + epoch + " Loss: " + logs.loss + " Accuracy: " + logs.acc);
            //                       }
            //                   }});
            // await model.save('downloads://my_model');
            
            
        }
        run();
    </script>
<body>
</body>
</html>

And here's the console log:

tfjs@latest:2 _________________________________________________________________
tfjs@latest:2 Layer (type)                 Output shape              Param #   
tfjs@latest:2 =================================================================
tfjs@latest:2 dense_Dense1 (Dense)         [null,20]                 620       
tfjs@latest:2 _________________________________________________________________
tfjs@latest:2 dense_Dense2 (Dense)         [null,20]                 420       
tfjs@latest:2 _________________________________________________________________
tfjs@latest:2 dense_Dense3 (Dense)         [null,10]                 210       
tfjs@latest:2 _________________________________________________________________
tfjs@latest:2 dense_Dense4 (Dense)         [null,5]                  55        
tfjs@latest:2 _________________________________________________________________
tfjs@latest:2 dense_Dense5 (Dense)         [null,1]                  6         
tfjs@latest:2 =================================================================
tfjs@latest:2 Total params: 1311
tfjs@latest:2 Trainable params: 1311
tfjs@latest:2 Non-trainable params: 0
tfjs@latest:2 _________________________________________________________________
tfjs@latest:2 Uncaught (in promise) Error: Argument 'b' passed to 'mul' must be a Tensor or TensorLike, but got 'null'
    at Ke (tfjs@latest:2)
    at mul_ (tfjs@latest:2)
    at Object.mul (tfjs@latest:2)
    at t.mul (tfjs@latest:2)
    at tfjs@latest:2
    at tfjs@latest:2
    at t.scopedRun (tfjs@latest:2)
    at t.tidy (tfjs@latest:2)
    at We (tfjs@latest:2)
    at tfjs@latest:2
Ke @ tfjs@latest:2
mul_ @ tfjs@latest:2
mul @ tfjs@latest:2
t.mul @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
t.scopedRun @ tfjs@latest:2
t.tidy @ tfjs@latest:2
We @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
e.applyGradients @ tfjs@latest:2
e.minimize @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
(anonymous) @ tfjs@latest:2
o @ tfjs@latest:2
async function (async)
run @ wdbc_exercise.html:53
(anonymous) @ wdbc_exercise.html:73

I am absolutely running out of options here to debug this. Help would be appreciated. Thanks!

created time in 25 days

startedlmoroney/dlaicourse

started time in a month

push eventsayakpaul/TF-2.0-Hacks

Sayak Paul

commit sha c3642defc3363b6161891a5e829ff028ff525b75

Added custom df generator

view details

push time in a month

issue openedharvitronix/five-video-classification-methods

Suggestions on reshaping the input data for action recognition

First of all, thank you very much for your hard work. I am trying to build myself an activity recognition model on the subset of UCF101 dataset (I am using the top 20 activity labels).

So far, I have used a pre-trained VGG16 network to extract the features out of the individual frames extracted from the videos. The final shape I got from the VGG16 network is (20501, 7, 7, 512) (for the train set). I now want to pass these extracted features to an LSTM-based network and I am a bit confused as to how I should reshape it?

How many time steps should I pass in and also how many features in one time-step?

created time in a month

issue openedchen0040/keras-video-classifier

Regarding reshaping the input data for action recognition

Hi. Thank you for your great work.

I am working on Human Action Recognition and I am using the UCF101 dataset. To simply the work a bit, I am using the top-20 actions of the dataset. So far, I have used a pre-trained VGG16 network to extract the features out of the individual frames extracted from the videos. The final shape I got from the VGG16 network is (20501, 7, 7, 512) (for the train set). I now want to pass these extracted features to an LSTM-based network and I am a bit confused as to how I should reshape it?

How many time steps should I pass in and also how many features in one time-step?

Thank you in advance for your help and time :)

created time in a month

push eventsayakpaul/TalksGiven

Sayak Paul

commit sha f5c58f0b79a6f000abaf83603449b265461e8d80

Add files via upload

view details

push time in a month

push eventsayakpaul/TF-2.0-Hacks

Sayak Paul

commit sha 8a5daba37ab20886a0fcfdf59a91868b5f765863

Adding custom experiments with WnB

view details

push time in a month

issue closedsayakpaul/TF-2.0-Hacks

Additional link - Applications of Deep Learning

Hi, thanks for sharing those resources about TF 2.

I'd like to share the Applications of Deep Learning. This is a semester complete course by Jeff Heaton in video and notebooks. Very well organized and get updates all semester.

https://github.com/jeffheaton/t81_558_deep_learning

closed time in a month

renatoviolin

issue commentsayakpaul/TF-2.0-Hacks

Additional link - Applications of Deep Learning

Thanks for mentioining. I will add this.

renatoviolin

comment created time in a month

pull request commenttensorflow/docs

Removing redundant use of np.array & unnecessary spaces

Ah no problem @MarkDaoust :)

sayakpaul

comment created time in a month

startedchen0040/keras-video-classifier

started time in a month

startedharvitronix/five-video-classification-methods

started time in a month

push eventsayakpaul/TF-2.0-Hacks

Sayak Paul

commit sha 022dadfa1b10a13c54c9f75aa9069ffe0c6cabef

Update README.md

view details

push time in a month

push eventsayakpaul/TF-2.0-Hacks

Sayak Paul

commit sha 4276d7bb566234ae5d72d6ddca8c98a0dc6cd22e

Update README.md

view details

push time in a month

push eventsayakpaul/Mixed-Precision-Training-in-tf.keras-2.0

Sayak Paul

commit sha fac624b35fe9fc64cc823f8a265358a1b85d86c9

Update README.md

view details

push time in a month

startedtorchgan/torchgan

started time in a month

push eventsayakpaul/TalksGiven

Sayak Paul

commit sha a4b1a7dc9b8680728b6d0de1e5ae2d9f541b70ed

Add files via upload

view details

push time in a month

push eventsayakpaul/TalksGiven

Sayak Paul

commit sha c21b3c392c1104bb0a5f80a1fe26379e99298886

Update README.md

view details

push time in a month

issue commenttensorflow/tensorrt

Jupyter Notebook kernel dies automatically

Yeah, it might be the case. Worth propagating to the Colab team, I guess.

WeiFoo

comment created time in a month

push eventsayakpaul/ML-Bootcamp-Launchpad

Sayak

commit sha 00093556ff015676b206b4ae91782e476b66aeee

Fixed a link

view details

Sayak

commit sha 5276596acc3ddcec50bc9ccf6ddf5bc0504e76e2

Rectified

view details

push time in a month

startedscikit-multiflow/scikit-multiflow

started time in a month

starteddocker-slim/docker-slim

started time in a month

push eventsayakpaul/ML-Bootcamp-Launchpad

Sayak Paul

commit sha a1716f8f61d6e62a89b948f85ddcc0f62298b34e

Update GCP_Stuff.txt

view details

push time in a month

PublicEvent

startedkarpathy/pytorch-normalizing-flows

started time in a month

push eventsayakpaul/ML-Bootcamp-Launchpad

Sayak Paul

commit sha 93198bcff28bf9b7b614d5e423c5d285337fb146

Update README.md

view details

push time in a month

push eventsayakpaul/ML-Bootcamp-Launchpad

Sayak Paul

commit sha 3b2e7457271bd7762db1588c4911a27041e056e5

Update README.md

view details

push time in a month

push eventsayakpaul/ML-Bootcamp-Launchpad

Sayak Paul

commit sha ad7c54524bf381fd38dbb51acd47e86865bd51fe

Update README.md

view details

push time in a month

startedAgaMiko/data-augmentation-review

started time in 2 months

startedtobegit3hub/advisor

started time in 2 months

push eventsayakpaul/TalksGiven

Sayak Paul

commit sha 21bd5d122dbec7ec162060ca05c08c8c73f66845

Update README.md

view details

push time in 2 months

push eventsayakpaul/TalksGiven

Sayak Paul

commit sha ec25f813d010448ad09e1ffa5bbe9551e7563528

Add files via upload

view details

push time in 2 months

push eventsayakpaul/TalksGiven

Sayak Paul

commit sha 7f2e6166ac7b94d400476d543a099f4f54f06cce

Update README.md

view details

push time in 2 months

startedargman/EAST

started time in 2 months

startedfastai/nbdev

started time in 2 months

starteduber-research/PPLM

started time in 2 months

startedkurapan/EAST

started time in 2 months

startedpydata/xarray

started time in 2 months

issue commentalirezadir/Production-Level-Deep-Learning

Suggestion regarding tools and platforms

Thanks for the suggestion. And it is done - https://github.com/alirezadir/Production-Level-Deep-Learning/pull/10.

sayakpaul

comment created time in 2 months

push eventsayakpaul/Production-Level-Deep-Learning

Sayak Paul

commit sha 38ccde6893b6bdd30c29060555c8735582d9d79a

Adding resources As discussed in [7](https://github.com/alirezadir/Production-Level-Deep-Learning/issues/7)

view details

push time in 2 months

fork sayakpaul/Production-Level-Deep-Learning

A guideline for building practical production-level deep learning systems to be deployed in real world applications.

fork in 2 months

startedmicrosoft/nlp-recipes

started time in 2 months

push eventsayakpaul/Mixed-Precision-Training-in-tf.keras-2.0

Sayak

commit sha 655c97f95aa456be707dcc4ea8c5ac2a53fcdfd6

Adding updated scripts

view details

push time in 2 months

push eventsayakpaul/Mixed-Precision-Training-in-tf.keras-2.0

Sayak Paul

commit sha 3995fc79af1e0d7cb99ece4a7d4032d31cd2e1c2

Update README.md

view details

push time in 2 months

startedDataTurks/DataTurks

started time in 2 months

push eventsayakpaul/awesome-machine-learning-interpretability

Sayak Paul

commit sha 0b0024e14b05b9d6ab367f2f23d47685f1a60557

Adding deep learning model debugging resources With respect to the discussion as per [24](https://github.com/jphall663/awesome-machine-learning-interpretability/issues/24).

view details

push time in 2 months

issue commentjphall663/awesome-machine-learning-interpretability

Where to include articles/materials related debugging Deep Neural Nets?

@jphall663 understood. To your point, I would just add Andrej Karpathy's article A Recipe for Training Neural Nets. I will go ahead and close this issue and will submit a PR.

I will also keep looking for good stuff around model debugging and will communicate them to you :)

sayakpaul

comment created time in 2 months

push eventsayakpaul/TalksGiven

Sayak Paul

commit sha fe5fefa2a3c87cff166c39c7ccf00a380661c53e

Add files via upload

view details

push time in 2 months

push eventsayakpaul/TalksGiven

Sayak Paul

commit sha 44a7669c208d0bbcf16b14a832781e456d4eb307

Update README.md

view details

push time in 2 months

issue commenttensorflow/tensorrt

Jupyter Notebook kernel dies automatically

I am also experiencing the same. Any pointers @pooyadavoodi?

WeiFoo

comment created time in 2 months

issue openedalirezadir/Production-Level-Deep-Learning

Suggestion regarding tools and platforms

Hi @alirezadir. Firstly, thank you very much for putting this together. Really awesome! In this issue, I would like to take the opportunity of suggesting a few tools/platforms with which I have worked and I believe it could be beneficial:

  • For Data Storage, Google Cloud Storage.
  • For Data Versioning, FloydHub Datasets.
  • For Data Processing, GCP Dataflow.
  • Under the Software engineering for Cloud Providers, you could also mention the specific services offered by the cloud providers. For example, Compute Engine and Notebooks (GCP Notebooks does not require any configuration and can increase the productivity) for GCP, EC2 for AWS and so on.
  • You could mention ML Engine which eases out the process of distributed training (under Distributed Training section).
  • For the Troubleshooting section, this Twitter thread by Chip could be very useful.
  • For the Web Development section (and for general model serving purpose), BentoML could be useful.
  • For Monitoring, Stackdriver could be useful.

Thank you for reading!

created time in 2 months

startedalirezadir/Production-Level-Deep-Learning

started time in 2 months

startedOlafenwaMoses/ImageAI

started time in 2 months

startedchiphuyen/machine-learning-systems-design

started time in 2 months

push eventsayakpaul/Phishing-Websites-Detection

Sayak Paul

commit sha 622bbf64f9e27687a037f0aba897dc39487fb7fc

Add files via upload

view details

push time in 2 months

more