Environment: Ubuntu 21.10 TensorFlow: 2.8.0 NVIDIA-SMI 510.54 CUDA Version: 11.6 I am trying to reproduce C4-W2A1 in my own environment, and this happened: [Screenshot from 2022-04-05 11-25-04]

I removed all “assertion” tests after exercises in the notebook and succeed to reproduce model with accuracy >0.80 of several runs. [Screenshot from 2022-04-06 09-00-13] It seems Coursera environment always produce the same seed with np.random.seed(1) , and it isn’t the case for my local environm…

For the notebooks to work correctly, you have to be extremely careful that you’re using the same versions of all the tools that Coursera uses.

Do you get similar results if you run the notebook in Coursera’s environment?

I had all test passed in Coursera Environment

it seems to have something to do with reusing X1. Check this out. np.random.seed(1) X1 = np.ones((1,4,4,3)) * -1 X2 = np.ones((1,4,4,3)) * 1 X3 = np.ones((1,4,4,3)) * 3 X4 = np.concatenate((X1, X2, X3), axis=0).astype(np.float32) X5 = np.concatenate((X1, X2, X3), axis=0).astype(np.float32) X6 = …

I had both piece failed. I also tried: X1 = np.ones((1, 4, 4, 3)) * -1 X2 = np.ones((1, 4, 4, 3)) * 1 X3 = np.ones((1, 4, 4, 3)) * 3 X = np.concatenate((X1, X2, X3), axis = 0).astype(np.float32) y = Conv2D(filters = 2, kernel_size = 1, strides = (2,2), padding = 'valid')(X) z = Conv2D(filters = 2…

Strange. I pasted that code into a cell in my notebook and the assertion evaluated True. X1 = np.ones((1, 4, 4, 3)) * -1 X2 = np.ones((1, 4, 4, 3)) * 1 X3 = np.ones((1, 4, 4, 3)) * 3 X = np.concatenate((X1, X2, X3), axis = 0).astype(np.float32) y = tf.keras.layers.Conv2D(filters = 2, kernel_size …

[SOLVED] "convolutional_block" gives different output at each run in the local environment

Course Q&A Deep Learning Specialization Convolutional Neural Networks

Lingxiao_Gao April 5, 2022, 11:05pm 8

I removed all “assertion” tests after exercises in the notebook and succeed to reproduce model with accuracy >0.80 of several runs.

It seems Coursera environment always produce the same seed with np.random.seed(1) , and it isn’t the case for my local environment.

Topic		Replies	Views
Output is off by a really small margin Convolutional Neural Networks week-module-2 , coursera-platform	9	53	July 22, 2024
Week2 - Assignment 1 (Conv2D issue) Convolutional Neural Networks coursera-platform	2	596	August 3, 2022
AssertionError: Wrong values when training=False.in "onvolutional Block" Exercise Convolutional Neural Networks coursera-platform	3	595	July 13, 2022
C4W2 programing exercise：RES NETWORKS(the first one) Convolutional Neural Networks coursera-platform	4	666	August 4, 2022
Course 4 Week 2, Assigment 1- Exercise 2 - convolutional_block error Convolutional Neural Networks week-module-2 , coursera-platform	2	192	April 14, 2024

[SOLVED] "convolutional_block" gives different output at each run in the local environment

Related topics