# W3 | Planar Data Classification | Backprop wrong dW1 **URL:** \ **Category:** Neural Networks and Deep Learning\ **Tags:** coursera-platform\ **Created:** [September 26, 2022, 3:30pm UTC](https://community.deeplearning.ai/t/w3-planar-data-classification-backprop-wrong-dw1/210537 "2022-09-26T15:30:59Z")\ **Posts on this page:** 2\ **Page:** 1
**Author:** ![Matthew\_Brown](https://avatars.discourse-cdn.com/v4/letter/m/c5a1d2/32.png) [@Matthew\_Brown](https://community.deeplearning.ai/u/Matthew_Brown)\ **Post date:** [September 26, 2022, 3:31pm UTC](https://community.deeplearning.ai/t/w3-planar-data-classification-backprop-wrong-dw1/210537/1 "2022-09-26T15:31:00Z")
Hello, I get a very small variation from the expected output, namely: dW1[2,1], dW1[2,2] and db1[2,1] ## // Full error message AssertionError Traceback (most recent call last) in 7 print ("db2 = "+ str(grads[“db2”])) 8 ----\> 9 backward\_propagation\_test(backward\_propagation) ~/work/release/W3A1/public\_tests.py in backward\_propagation\_test(target) 187 assert output[“db2”].shape == expected\_output[“db2”].shape, f"Wrong shape for db2." 188 → 189 assert np.allclose(output[“dW1”], expected\_output[“dW1”]), “Wrong values for dW1” 190 assert np.allclose(output[“db1”], expected\_output[“db1”]), “Wrong values for db1” 191 assert np.allclose(output[“dW2”], expected\_output[“dW2”]), “Wrong values for dW2” AssertionError: Wrong values for dW1 //My output dW1 = [[0.00301023 -0.00747267] [0.00257967 -0.00641287] [-0.00156892 0.003893] [-0.00652037 0.01618243]] db1 = [[0.00176201] [0.00150994] [-0.00091736] [-0.00381422]] dW2 = [[0.00078841 0.01765429 -0.00084166 -0.01022527]] db2 = [[-0.16655712]] //Expected ```auto dW1 = [[0.00301023 -0.00747267] [0.00257968 -0.00641288] [-0.00156892 0.003893] [-0.00652037 0.01618243]] db1 = [[0.00176201] [0.00150995] [-0.00091736] [-0.00381422]] dW2 = [[0.00078841 0.01765429 -0.00084166 -0.01022527]] db2 = [[-0.16655712]] ``` _{Moderator’s Edit: Solution Code Removed}_ Thanks! ---
**Author:** ![Elemento](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/elemento/32/854_2.png) [@Elemento](https://community.deeplearning.ai/u/Elemento)\ **Post date:** [September 27, 2022, 9:49am UTC](https://community.deeplearning.ai/t/w3-planar-data-classification-backprop-wrong-dw1/210537/2 "2022-09-27T09:49:18Z")
Hey @Matthew_Brown, Welcome to the community. Please check the expression of `dZ1` carefully. When you are calculating `dZ1`, we are considering the expression dZ1 = da1 \* \frac{\partial{a1}}{\partial{Z1}} where \frac{\partial{a1}}{\partial{Z1}} is supposed to be `(1 - np.power(A1, 2))` as pointed out in the tips. Let me know if this helps. **P.S. - Posting code publicly is strictly against the community guidelines. Please refrain from doing so in the future. If a mentor needs to take a look at your code, (s)he will ask you to DM it.** Cheers, Elemento