keras-video-classifier

keras-video-classifier copied to clipboard

patool error

10

I have created an environment and executing as instructed in Github. ubuntu:18.04 python 3.6 On executing this command I am getting the following error: python vgg16_bidirectional_lstm_train.py Using TensorFlow backend. unzipping...

janvib27

Hi, the `K.set_image_dim_ordering('tf')` isn't a part of keras.backend anymore. Solutions on stackoverflow and other forums suggest replacing it with the following: `K.set_image_data_format('channels_first')`

akshitadixit

1. What is MAX_NB_CLASSES = 4 in frame_extractors file? 2. What is MAX_NB_CLASSES = 20 in vgg16 feature extractor file? 3. Where to change dataset name to train own dataset?...

farhadmath

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...

sayakpaul

Error during prediction

1

Hi, I'm getting the the error "ValueError: Object arrays cannot be loaded when allow_pickle=False" while I run "vgg16_bidirectional_lstm_predict.py" after the model training. I'm requesting your help to solve it.

farhadmath

Which gpu you used for the training on UCF-101 and how much time it took? Also, why are you taking only one frame from every second?

gurjeet8197

I've trained 3 classes : "bye" , "hello" and "what's up" and every classe contains 50 videos. In the end of training after extracting frames I get this : max...

siryne

`pyplot` will output `tkinter.TclError: no display name and no $DISPLAY environment variable` on headless server. Changing the import part of plot_utils.py from `from matplotlib import pyplot as plt` to ```...

qysnn

I am trying to apply this code to a custom dataset and find out that it will hang at vgg16_feature_extractor.py line 44 forever. After doing some search, I think the...

qysnn

For patool to work unrar/unzip should be present.

jibinmathew69