# C5W4 Assignment Exercise 5 - Encoder **URL:** \ **Category:** Sequence Models\ **Tags:** week-module-4, coursera-platform\ **Created:** [March 4, 2025, 8:15pm UTC](https://community.deeplearning.ai/t/c5w4-assignment-exercise-5-encoder/780258 "2025-03-04T20:15:51Z")\ **Posts on this page:** 2\ **Page:** 1
**Author:** ![zaine\_111](https://avatars.discourse-cdn.com/v4/letter/z/82dd89/32.png) [@zaine\_111](https://community.deeplearning.ai/u/zaine_111)\ **Post date:** [March 4, 2025, 8:15pm UTC](https://community.deeplearning.ai/t/c5w4-assignment-exercise-5-encoder/780258/1 "2025-03-04T20:15:51Z")
I’m getting the Assertion error below. I completed the following steps: 1. pass x through the embedding layer using self.embedding(x) 2. Scale x by using \*= tf.math.sqrt() (using tf.cast() on self.embedding\_dim 3. Add the PE as directed in the instructions 4. For the dropout layer I used self.dropout() with training=training 5. In the for … loop I called self.enc\_layers[i] But I’m getting this error: AssertionError Traceback (most recent call last) in 1 # UNIT TEST ----\> 2 Encoder\_test(Encoder) ~/work/W4A1/public\_tests.py in Encoder\_test(target) 116 encoderq\_output = encoderq(x, True, None) 117 → 118 assert tf.is\_tensor(encoderq\_output), “Wrong type. Output must be a tensor” 119 assert tuple(tf.shape(encoderq\_output).numpy()) == (x.shape[0], x.shape[1], embedding\_dim), f"Wrong shape. We expected ({x.shape[0]}, {x.shape[1]}, {embedding\_dim})" 120 assert np.allclose(encoderq\_output.numpy(), AssertionError: Wrong type. Output must be a tensor ---
**Author:** ![TMosh](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/tmosh/32/9321_2.png) [@TMosh](https://community.deeplearning.ai/u/TMosh)\ **Post date:** [March 4, 2025, 8:54pm UTC](https://community.deeplearning.ai/t/c5w4-assignment-exercise-5-encoder/780258/2 "2025-03-04T20:54:22Z")
Note that the error could be in either your Encoder() class, or in your EncoderLayer() class. The EncoderLayer\_test() does not catch all possible issues. If you open the public\_tests.py file, you can find the Encoder\_test() function. This will help you identify the conditions where your code does not work correctly.