Roma Jain

The video I wanted to classify is say X seconds, frames broken at 1 fps rate. And the segment (1,16) , what does this implicate? And, when mode score is...

Model architecture ---> adam=keras.optimizers.Adam(lr=0.0001) early_stopping = keras.callbacks.ModelCheckpoint(filepath, monitor='val_acc', verbose=0, save_best_only=True, save_weights_only=False, mode='auto', period=10) input_text = Input(shape=(1,), dtype="string") embedding = Lambda(UniversalEmbedding, output_shape=(512, ))(input_text) dense = Dense(1024)(embedding) bnorm = BatchNormalization()(dense) acti =...

Original sentence gets transformed to other sentence on online testing

2

> 1 have a nice day 1 have a nice day ['1', 'have', 'a', 'nice', 'day'] 1 original: need to improve transfer: to a up Why does original give "need...

Converting npy files to TFRecords files

2

I have tried to convert .npy files to tfrecords using `tf.train.Feature(float_list=tf.train.FloatList(value=array))` But, on reading features and labels from these TFRecords, it says expected string but got float32