Ilia Karmanov

When loading this model with Chainer and attempting to evaluate a batch of images it complains that the eps param in batch-norm is < 1e-5 `sym = caffe.CaffeFunction("DenseNet_121.caffemodel") ` Is...

yolo_grid_anchor_generator ->object has no len()

8

I was curious to give this a go and wasn't sure if the below error was due to this being python2 only or something else? ``` iliauk@ikobjtest:/data/models/research$ python object_detection/train.py --logtostderr...

The way that [TF](https://github.com/ilkarman/DeepLearningFrameworks/blob/mutligpuilia/notebooks/Tensorflow_MultiGPU.ipynb) does checkpointing with: `tf.estimator.train_and_evaluate(nn, train_spec, eval_spec)` Seems to result in a lot of IO lag where it saves the params to disk after every epoch, runs...

@mitmul Thank you for highlighting my typo in your PR request; I wanted to highlight two further issues I am facing [here](https://github.com/ilkarman/DeepLearningFrameworks/blob/mutligpuilia/notebooks/Chainer_MultiGPU.ipynb) 1. Toggling between single and muli-gpu (4x) improves...

Cannot replicate Kinetics-400 Results

4

Thank you very much for posting the codebase! However, I'm having difficulty replicating the 71.0% acc mentioned in the paper for 'bLVNet-TAM-8×2', I only get around 55% when validating each...

F.upsample(per_frame_logits)

1

I was wondering what the difference is between this and the tensorflow model that requires the output to be upsampled? As I understand the number of frames gets downsampled by...

Consider expanding this example to a working API?

Add multinomial logistic regression example to bridge gap between logit and NN