five-video-classification-methods

five-video-classification-methods copied to clipboard

Fix Asserting error for one hot encoding

1

This should resolve [issue76](https://github.com/harvitronix/five-video-classification-methods/issues/76) when running by train.py for 'lstm' model.

mertia-himanshu

ValueError: Input 0 is incompatible with layer model: expected shape=(None, 224, 224, 3), found shape=(None, 240, 320, 3)

1

Hello! I'm having this error while executing train.py. Although the target shape is correct i can't wrap my head around the expected shape. I'll leave the stack trace: [traceback.txt](https://github.com/harvitronix/five-video-classification-methods/files/6719861/traceback.txt)

JosephMartinelli

Train Problem

1

Thank your for your sharing. When I run train.py,I met a problem is ValueError: output of generator should be a tuple `(x, y, sample_weight)` or `(x, y)`. Found: None. Can...

jianghongsun

Getting error in extract_features.py

3

Hi, I ran the 1_move_files.py and 2_extract_files.py successfully. after that, I tried running the extract_features.py, it gives me the following error File "C:\Users\Preeti Gupta\Downloads\five-video-classification-methods-master\data.py", line 81, in get_classes if item[1]...

preetigupta010203

Training using own Dataset

1

Hello there, Thanks for the great work, I have tested it with 101 Dataset and all went good. Now I want to train a model using my dataset, I converted...

suheib-sherif

sunruina2

@harvitronix hello Harvey, thanks to your really good tutorial for video classification. I followed your instruction to train my own lrcn video classification model and it works well under tensorflow&keras....

Magsun

Training accuracy on own dataset

2

I have trained on my own four categories datasets, and the accuracy is very low. Does anyone know why?

zxj11838

Low accuracy of LRCN model

1

Hello, I'm trying to recreate the results you've mentioned in your medium blog post. I've split the dataset using your scripts, used the default hyper parameters- 1000 epochs lr =...

shashi438

notebook_tutorial for prediction with any video

2

This notebook shows how can you use this model to make prediction on any video [pipeline_v1.pdf](https://github.com/harvitronix/five-video-classification-methods/files/3122639/pipeline_v1.pdf)

saurabh241930