Skip to main content
Share Your Experience: Take the 2024 Developer Survey
mLstudent33's user avatar
mLstudent33's user avatar
mLstudent33's user avatar
mLstudent33
  • Member for 5 years, 2 months
  • Last seen more than a week ago
12 votes
1 answer
15k views

what is the first input to the decoder in a transformer model?

5 votes
2 answers
781 views

Feeding 3 consecutive video frames to a CNN to track a tennis ball

2 votes
2 answers
424 views

Calculating derivative of error at point x with respects to weight w_j

2 votes
1 answer
6k views

PPO, A2C for continuous action spaces, math and code

2 votes
1 answer
2k views

bert-as-service maximum sequence length

1 vote
2 answers
2k views

computer vision transformers: ViT does not have a decoder?

1 vote
1 answer
172 views

Partial derviative of prediction (sigmoid applied) with respect to weight

1 vote
1 answer
880 views

How Tensorflow text prediction predicts without softmax activation

1 vote
2 answers
2k views

What are features for state-action pairs in RL?

1 vote
1 answer
314 views

What are some ways to train, test and render an RL autonomous drone in a simulator?

1 vote
1 answer
501 views

multipying negated gradients by actions for the loss in actor nn of DDPG

1 vote
1 answer
519 views

K.gradients gives type error where both arguments are tensors

1 vote
0 answers
553 views

matterport mask-r-cnn transfer learning on own dataset using VGG annotator ver.1

1 vote
1 answer
1k views

A2C Continuous for Pendulum-v0 working implementation, negation for loss and entropy calculation

1 vote
1 answer
688 views

np.shape[::-1] reversal of dims and np.moveaxis splitting array

1 vote
1 answer
94 views

Is there a python version of Mitchell's face pose recognition code?

1 vote
2 answers
50 views

Calculating cyclic values in a toroidal world

0 votes
1 answer
299 views

Memorization in deep neural networks, random vs. properly labelled datasets

0 votes
1 answer
3k views

Keras reuse trained weights on CNN with different number of channels

0 votes
1 answer
244 views

RL Sutton book, initial estimate of q*(a) for 10 arm testbed

0 votes
1 answer
780 views

Face detection for different poses more robust than MTCNN?

0 votes
1 answer
483 views

What is .numpy()?