BHUSHAN MUTHIYAN

Hello Johnson, Thank you for the nice tutorial. I was able to change the code in cnn-benchmarks.lua to run it for multi-GPU system(8 GPU). It gave me a speed-up of...

Error while installng vpp while running the command "./install.sh vpp"

2

Hello, I am new to c++14 and I am trying to install vpp by executing the command "./install.sh vpp" But it gives me following error. tests/CMakeFiles/fill.dir/build.make:62: recipe for target 'tests/CMakeFiles/fill.dir/fill.cc.o'...

Keras word2vec is much more faster than tensorflow word2vec ?

1

Thanks for your work. I had a question about word2vec. I ran both of your codes of word2vec viz Keras_word2vec.py and tf_word2vec.py !! Keras word2vec with Tensorflow backend seems faster...

How is #iterations, step_size and number of epochs related ?

1

Hello, Thank you for this wonderful tutorial !! From the Tensorflow word2vec tutorial and code in Github for tf_word2vec.py, I am not able to understand how are "#iterations", "step_size" and...

ValueError: bad marshal data (unknown type code)

2

I converted the jupyter notebook "Embedding_Space_Visualisation.ipynb" to the python script and I was running using the Python3 environment with Cuda-10.1 installed on my laptop. I am getting a **ValueError: bad...

Final model checkpoint is not saved even after running for many hours.

5

Hello, I am trying to run the model for 100000 steps. The model checkpoint saved has 3 files. 1) model.ckpt-99999.data-00000-of-00001 2) model.ckpt-99999.index 3) model.ckpt-99999.meta But the final checkpoint value is...

Error using image dataset of 640x360 for training using SqueezeDet.

7

Hello, I changed the image size in src/config/kitty_squeezeDet_config.py file from to 640x360 for 96 classes and also added class names in the config.py file, keeping all other parameters same. I...

Are this models for Tensorflow backend ot=r Theano backend?

1

I want to save the weights and load the weights in Keras with Tensorflow backend. When I import ResNet50 model with Tensorflow backend I get errors ValueError: Cannot feed value...

Hello, I was unable to run the original github code because the downloaded code somehow had indentation issues. Below code works perfectly for Hand written recognition. 

Does the training script need images only of size 224x224 ?

2

Hello @vonclites, I want to know if this script needs only image size of 224x224 while creating a tfrecord file? Or will it work for any size image? Please, let...