C3W1_Assignment UNQ_C1 combine_sample assert confusion

Course Q&A Generative Adversarial Networks (GANS) Apply Generative Adversarial Networks
1

The combine_sample code triggered the following assertion:

image
image1081×236 32.3 KB

I have implemented the combining as I did in the assignment C1W3_WGAN_GP:

  1. I created a tensor of booleans named epsilon by assigning the result of comparing a tensor of torch.rand (of real image size) to be less than the given probability of real images.
  2. I then assigned to target_images the sum of real images times epsilon and fake images times logical not epsilon

I think that the assert “# Make sure that no mixing happened” might mean that tensor target_images is the correct length but I don’t know what “mixing” means.

Please help me understand the assert message.

2

Hi Jswat!

What you have done is logically incorrect. It would be easier for me to explain this in paper → Please refer to the attachments!

DLAI2
DLAI2893×1280 46.2 KB

DLAI1
DLAI11280×937 50.8 KB

This is where you are wrong, kindly go through the instructions that are mapped to this cell once again to get a clear understanding and try again.

Regards,
Nithin

3

Thanks for the feedback.

1 Like
4

Dear All,

I am experiencing an error on the same task.

I used torch.multinomial to randomly select a proportion of uniform index indicators (1s). This produced an index at random positions of the correct proportions. I then used the index to select a subset from the sample. I did this for the real and fake indices. I concatenated the selected samples. I also concatenated the selected indices. I sorted the combined indices in ascending order and used these to select the concatenated samples.

I am however, not getting the order right and am incurring the following assert error:

 36 # Make sure that the order is maintained

—> 37 assert torch.abs(test_combination - test_reals).sum() < 1e-4

Thanks in advance,

Mark

5

Have you seen this thread? Please read from that post forward and let us know if that sheds any light or looks related to your issues.

6

It may be that I’m simply not understanding what you mean, but that all sounds a bit worrying. The point is to do things “in place” and also “row-wise”, not “element-wise”. You clone the “reals” and then replace some of those samples (in-place) with fakes.

I also did not see any reference to torch.multinomial in the instructions. They do discuss using torch.rand or torch.bernoulli. I used torch.rand FWIW …

7

I had a look at the other thread and it makes much more sense now. It did say there were multiple ways to sort this, but what I did was wrong. I randomly sampled from each of real and fake and concatenated them in a way that the indexing wouldn’t have worked either. The solution described on the thread that you linked works. It swaps elements nicely preserving the order. Thanks again for your help.

1 Like