Sudden drop in accuracy while training a deep neural net

I am using mxnet to train a 11-class image classifier. I am observing a weird behavior training accuracy was increasing slowly and went upto 39% and in next epoch it went down to 9% and then it...

Using im2rec in MXnet to create dataset with png images

I am trying to follow the example here and create my own dataset for training using MXnet. My data is organized as specified in the example: /data yes/ file1.png file2.png ...

How many output nodes should my Convolutional Neural Network have?

I am using the Passenger Screening Challenge from the Kaggle website for a class project. I've implemented an out-of-the-box Convolutional Neural Network from this tutorial:...

Sagemaker "Could not find model data" when trying to deploy my model

I have a training script in Sagemaker like, def train(current_host, hosts, num_cpus, num_gpus, channel_input_dirs, model_dir, hyperparameters, **kwargs): ... Train a network ... return...

Amazon Web Services: -bash: activate: No such file or directory

I'm trying to use Deep Learning AMI (Ubuntu) on Amazon Web Services (AWS). When you login, you get a message as follows (I'm showing part of it here): Please use one of the following commands to...

How to force tensorflow to use all available GPUs?

I have an 8 GPU cluster and when I run a piece of Tensorflow code from Kaggle (pasted below), it only utilizes a single GPU instead of all 8. I confirmed this using nvidia-smi. # Set some...

How to install CUDA in Google Colab GPU's

It seems that Google Colab GPU's doesn't come with CUDA Toolkit, how can I install CUDA in Google Colab GPU's. I am getting this error in installing mxnet in Google Colab. Installing collected...

AWS Deeplens with Keras and MXNet Model: ValueError for symbol 'data' not found

I have a CNN model that I made using Keras using MXNet as the backend. I am able to create, train, and export a model without a hitch. However, when I attempted to load this model to the DeepLens,...

MXNetError - dataset does not start with a valid magic number

I am trying to use amazon sagemaker linear-learner algorithm, it support content type of ‘application/x-recordio-protobuf’. In preprocessing phase, i used scikit-learn preprocessing to...

ERROR: You must give at least one requirement to install -- when running: pip install --upgrade --no-binary hdbscan

I am trying to install hdbscan in my PC which runs Windows 10 and has installed Python 3.6. My first attempt failed: (base) C:\WINDOWS\system32>pip install hdbscan --user Collecting hdbscan ...

Rasa NLU installation issue - Incompatible Version

I am trying to install rasa NLU using 'pip install rasa' command. The installation ends up with the compatibility error. Kindly some one into the issue and help me out in resolving the version...

How to use Conv1d with MXNet.jl or Flux in Julia?

I've tried to translate the Conv1d Python Keras example from: https://machinelearningmastery.com/cnn-models-for-human-activity-recognition-time-series-classification into Julia using mxnet.jl and...

error: Illegal instruction (core dumped) - tensorflow==2.1.0

I am importing tensorflow in my ubuntu (Lenovo 110-Ideapad laptop) python using following commands- (tfx-test) [email protected]:~/Chandni/TFX$ python Python 3.6.9 (default, Nov 7 2019, 10:44:02)...

How to fix:- libmxnet.so: cannot open shared object file: No such file or directory

I'm trying to install mxnet on Yocto (Rocko) for my 64-bit Armv8-A. I did pip3 install mxnet and it was successfully installed. It was installed in - /usr/lib/python3.5/site-packages I copied...

What are all the formats to save machine learning model in scikit-learn, keras, tensorflow and mxnet?

There are many ways to save a model and its weights. It is confusing when there are so many ways and not any source where we can read and compare their properties. Some of the formats I know...

mxnet-gluon on colab: cudaMalloc retry failed: out of memory

I'm trying to train a faster RCNN on google-colab using mxnet gluon and VOC dataset. After training the net, when I try to analyze a new image to test it, I get the error below. This problem comes...

How to export Scikit learn models for hosting in AWS Sagemaker (sklearn model artifacts, .pkl file or .tar.gz)

I am looking for a solution that allows me to host my trained Sklearn model (that I am satisfied with) on SageMaker without having to retrain it before deploying to an endpoint. On the one hand I...

why AssertionError having numpy.ndarray

My data frame is look like - can sbi bjf srt acc amb tata ...

Predicting locally with a model trained on Sagemaker

I have trained a model on AWS SageMaker by using the built-in algorithm Semantic Segmentation. This trained model named as model.tar.gz is stored on S3. So I want to download this file from S3 and...

How to install "mxnet" package in R 4.0.2

Good afternoon. Recently I have encountered the problem with installing "mxnet" package. I have tried several variants of code, but neither of their actually installs this package. cran <-...

Memory allocation error on worker 0: std::bad_alloc: CUDA error

DESCRIPTION I am just trying to gave a trainign and a test set for the model but I get the following errors 1st data package - train_data = xgboost.DMatrix(data=X_train, label=y_train) Up until I...

Telling metaflow to install package with pip using conda decorator

Running on AWS I would usually define a step: @batch(cpu=1, memory=5000) @conda(libraries={'pandas': '1'}) @step def hello(self): do stuff... However, I am working with deeplearning libraries...

how to solve numpy error while installing mxnet?

I was just running the default command to install mxnet on windows but this error popped up, I need to use mxnet in order to run insightface library, I was wondering what I did wrong What I've...

Mxnet, load data from csv file with pandas and feed to NN models

I'm having a problem in loading correctly a .csv file to use as input for a very simple dense NN model. The csv file contains all the input features and a 'target' column, to use as output for...

R: namespace load failed for ‘mxnet’: package ‘mxnet’ was installed before R 4.0.0: please re-install it

I am trying to install the R package "mxnet". However, this package does not seem to be available on CRAN. I found similar posts on stackoveflow where similar problems were...

Getting OSError: libnccl.so.2 while importing mxnet

My configurations are: gpu: Nvidia GeForce MX450 with 2GB Graphics Card Cuda version: 10.1 MxNet Version: mxnet-cu101: 1.8.0 While trying to mxnet using import mxnet I am getting the following...

Problem installing Mxnet using pip on Windows

I am trying to install mxnet on my windows but receiving below error which seems is related to numpy. I tried to manually uninstall numpy or install other versions of mxnet but it did not work. ...

ERROR: Cannot install gluonts, mxnet, numpy and pandas because these package versions have conflicting dependencies

I wanted to install certain packages: pip install gluonts==0.8.0 mxnet~=1.7 pathlib==1.0.1 numpy==1.17.2 pandas==1.0.5 ujson==4.0.2 torch~=1.6 pytorch-lightning~=1.1 But during installation, i...

How to install mxnet on google colab?

I'm trying to install mxnet with gpu on colab. I guess current colab has cuda 11.1 installed by default as !nvcc --version gives nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2020...

ModuleNotFoundError: No module named 'mxnet'

I have been looking for the solution for this error for a whole morning. I created an separate environment for python 3.6 and I still got this error. I am using anacondas. So i am so...