A problem I meet in spatial_cnn and spatial_dataloader

[inkplatform]

Dear jeffreyyihuang:

Base your code,I don't clear how to make Spatial input data -> rgb frames, and how to make ture below load_ucf_image function

` def load_ucf_image(self,video_name, index):
if video_name.split('')[0] == 'HandstandPushups':
n,g = video_name.split('',1)
name = 'HandStandPushups_'+g
path = self.root_dir + 'HandstandPushups'+'/separated_images/v_'+name+'/v_'+name+''
else:
path = self.root_dir + video_name.split('')[0]+'/separated_images/v_'+video_name+'/v_'+video_name+'_'

    img = Image.open(path +str(index)+'.jpg')
    transformed_img = self.transform(img)
    img.close()

    return transformed_img`

I want to ask how to get Spatial input data -> rgb frames dataset. Thank you very much.
Chen Fei