# C5W1E2: Dinosaur Island Sample() Wrong Values **URL:** \ **Category:** Sequence Models\ **Tags:** coursera-platform\ **Created:** [September 12, 2023, 1:32am UTC](https://community.deeplearning.ai/t/c5w1e2-dinosaur-island-sample-wrong-values/442947 "2023-09-12T01:32:56Z")\ **Posts on this page:** 6\ **Page:** 1
**Author:** ![AlgorithmicAscension](https://avatars.discourse-cdn.com/v4/letter/a/e19adc/32.png) [@AlgorithmicAscension](https://community.deeplearning.ai/u/AlgorithmicAscension)\ **Post date:** [September 12, 2023, 1:32am UTC](https://community.deeplearning.ai/t/c5w1e2-dinosaur-island-sample-wrong-values/442947/1 "2023-09-12T01:32:56Z")
Step 1 is simple. Step 2, I’m sure I got the formulas correct because I got outputs with an acceptable shape. Step 4 is pretty straightforward. But at Step 3, I am given this: - Example of how to use `np.random.choice()`: ```auto np.random.seed(0) probs = np.array([0.1, 0.0, 0.7, 0.2]) idx = np.random.choice(range(len(probs)), p = probs) ``` - This means that you will pick the index (`idx`) according to the distribution: 𝑃(𝑖𝑛𝑑𝑒π‘₯=0)=0.1, 𝑃(𝑖𝑛𝑑𝑒π‘₯=1)=0.0, 𝑃(𝑖𝑛𝑑𝑒π‘₯=2)=0.7, 𝑃(𝑖𝑛𝑑𝑒π‘₯=3)=0.2 - Note that the value that’s set to `p` should be set to a 1D vector. - Also notice that 𝑦̂ βŸ¨π‘‘+1⟩, which is `y` in the code, is a 2D array. So y is the probability are the probabilities in a 2D array, but I need to input a 1D array in np.random.choice of the same size. I noticed that the probabilities of the same second index add up to 1. So I indexed into the counter at first, but it gave wrong values. ```auto Sampling: list of sampled indices: [23, 7, 15, 26, 25, 23, 21, 14, 23, 23, 7, 16, 26, 24, 18, 14, 10, 0] list of sampled characters: ['w', 'g', 'o', 'z', 'y', 'w', 'u', 'n', 'w', 'w', 'g', 'p', 'z', 'x', 'r', 'n', 'j', '\n'] --------------------------------------------------------------------------- AssertionError Traceback (most recent call last) in 19 print("\033[92mAll tests passed!") 20 ---> 21 sample_test(sample) in sample_test(target) 15 assert indices[-1] == char_to_ix['\n'], "All samples must end with \\n" 16 assert min(indices) >= 0 and max(indices) < len(char_to_ix), f"Sampled indexes must be between 0 and len(char_to_ix)={len(char_to_ix)}" ---> 17 assert np.allclose(indices[0:6], [23, 16, 26, 26, 24, 3]), "Wrong values" 18 19 print("\033[92mAll tests passed!") AssertionError: Wrong values ``` How are you supposed to aggregate a bunch of probability distributions into one probability distribution for the np.random.choice? ---
**Author:** ![balaji.ambresh](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/balaji.ambresh/32/128697_2.png) [@balaji.ambresh](https://community.deeplearning.ai/u/balaji.ambresh)\ **Post date:** [September 12, 2023, 3:06am UTC](https://community.deeplearning.ai/t/c5w1e2-dinosaur-island-sample-wrong-values/442947/2 "2023-09-12T03:06:45Z")
`probs` is logically a 1D array per our model architecture since we predict probability of next character based on the characters seen so far. To provide another hint, the shape of `probs` should be `(27, 1)` for each timestep. You can use ravel / squeeze to get rid of the dummy dimension since as you explained, numpy accepts a 1D array for `p` parameter. ---
**Author:** ![AlgorithmicAscension](https://avatars.discourse-cdn.com/v4/letter/a/e19adc/32.png) [@AlgorithmicAscension](https://community.deeplearning.ai/u/AlgorithmicAscension)\ **Post date:** [September 12, 2023, 3:28am UTC](https://community.deeplearning.ai/t/c5w1e2-dinosaur-island-sample-wrong-values/442947/3 "2023-09-12T03:28:49Z")
To be clear, I have a matrix of (27, 100) and which are 100 distributions of [a-z\n], each of which sum up to 1, and I need to turn it into (27,1) which should also sum up to 1. So should I take the average of the 100 distributions? I still don’t get it ---
**Author:** ![balaji.ambresh](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/balaji.ambresh/32/128697_2.png) [@balaji.ambresh](https://community.deeplearning.ai/u/balaji.ambresh)\ **Post date:** [September 12, 2023, 3:34am UTC](https://community.deeplearning.ai/t/c5w1e2-dinosaur-island-sample-wrong-values/442947/4 "2023-09-12T03:34:50Z")
In method `sample`, if `y.shape` is not `(27, 1)`, you’ve made a coding error. ---
**Author:** ![balaji.ambresh](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/balaji.ambresh/32/128697_2.png) [@balaji.ambresh](https://community.deeplearning.ai/u/balaji.ambresh)\ **Post date:** [September 12, 2023, 4:02am UTC](https://community.deeplearning.ai/t/c5w1e2-dinosaur-island-sample-wrong-values/442947/5 "2023-09-12T04:02:51Z")
Feedback on your code: The way you’ve initialized `x` and `a_prev` is incorrect. Always make tensors 2D to avoid surprises. For instance, if you want to initialize zeros for a vocabulary of 27 charcters, make zeros of shape `(27, 1)` and not `(27,)` ---
**Author:** ![AlgorithmicAscension](https://avatars.discourse-cdn.com/v4/letter/a/e19adc/32.png) [@AlgorithmicAscension](https://community.deeplearning.ai/u/AlgorithmicAscension)\ **Post date:** [September 12, 2023, 4:24am UTC](https://community.deeplearning.ai/t/c5w1e2-dinosaur-island-sample-wrong-values/442947/6 "2023-09-12T04:24:37Z")
I implemented your suggestion on all initializations. Thank you so much. I was going insane looking at this πŸ₯Ή