wjnam / relative_attributing_propagation Goto Github PK

View Code? Open in Web Editor NEW

76.0 76.0 8.0 3.63 MB

Interpreting DNNs, Relative attributing propagation

Python 100.00%

explainable-ai interpretable-deep-learning

relative_attributing_propagation's People

Contributors

Stargazers

Watchers

Forkers

seohyunlee-ku justinmacp jaehyunnn niuwan1 zeta1999 youngeun1209 apcc-geoslegend n33lkanth

relative_attributing_propagation's Issues

Keras implementation

Hi,

in the paper you say:

We implement RAP with both Pytorch and Keras and visualize the explanation as a heatmap. For the evaluation, we utilized the Keras version to fairly compare with other explaining methods.

Would it be possible for you to share the Keras implementation as well?

RAP will generate weird heatmap on resnet

I find that RAP works correctly on vggnet, but generates weird heatmaps on resnet, even when the image is from your paper. The generated heatmaps for cat image(Figure 6 in your paper) on vggnet/resnet are as follows.
VGG16: Resnet50: result from your paper(on resnet-50):

Could you please give me some advice? @wjNam @shirgur

relprop function in resnet.py

First of all, thanks to open your codes.

I wonder how below codes are works at line 299 ~ 302 in resnet.py

R = self.layer4.relprop(R, alpha)
R = self.layer3.relprop(R, alpha)
R = self.layer2.relprop(R, alpha)
R = self.layer1.relprop(R, alpha)

For example, resnet18, each self.layer4 has 2 blocks (block(1) and block(2)).
((1) and (2) mean order of appended.)
In my understand, relevance scores are propagated from block(2) to block(1).

However, in your code, just call self.layer4.relprop(R, alpha), it looks relevance scores are propagated from block(1) to block(2).

Could you explain how these code work correctly?

thanks.

Evaluation Metric code share

Could you share the evaluation metric code for each attribute map for accurate comparison for new algorithms?

RAP for different output shape

Hi, while running the main.py for resnet50 with 365 output classes, I ran into the following error

torch.Size([1, 2048]) torch.Size([365, 2048]) torch.Size([1, 1000])

---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
<ipython-input-3-02abbf51b5f9> in <module>
      7 #    Res = model.relprop(R = output * T, alpha= 1).sum(dim=1, keepdim=True)
      8 #else:
----> 9 RAP = model.RAP_relprop(R=T)
     10 Res = (RAP).sum(dim=1, keepdim=True)
     11 # Check relevance value preserved

/home/SharedData3/ushasi/tub/gan/modules/resnet.py in RAP_relprop(self, R)
    324         return R
    325     def RAP_relprop(self, R):
--> 326         R = self.fc.RAP_relprop(R)
    327         R = R.reshape_as(self.avgpool.Y)
    328         R = self.avgpool.RAP_relprop(R)

/home/SharedData3/ushasi/tub/gan/modules/layers.py in RAP_relprop(self, R_p)
    372             pd = R_p
    373 
--> 374             Rp_tmp = first_prop(pd, px, nx, pw, nw)
    375             A =  redistribute(Rp_tmp)
    376 

/home/SharedData3/ushasi/tub/gan/modules/layers.py in first_prop(pd, px, nx, pw, nw)
    317             #print(px,pw)
    **318             print(px.shape,pw.shape,pd.shape)**
--> 319             Rpp = F.linear(px, pw) * pd
    320             Rpn = F.linear(px, nw) * pd
    321             Rnp = F.linear(nx, pw) * pd

RuntimeError: The size of tensor a (365) must match the size of tensor b (1000) at non-singleton dimension 1

The top 3 shapes are a result of the print statement I added (in bold).
If I change my T = (T[:, np.newaxis] == np.arange(1000)) * 1.0 to T = (T[:, np.newaxis] == np.arange(365)) * 1.0 in compute_pred function, then the error goes away.
I just wanted to confirm that this is indeed the right way to fix the error, I hope I am not doing something random to get rid of the error and in the process, giving the wrong output.

Error with ResNet18 and Resnet34 (BasicBlock in Resnet)

It appears there is a bug when attempting to use the attribution method for ResNet18/Resnet34 model. Resnet50 works fine. Perhaps, there is a bug in BasicBlock class. Could you please take a look? The error trace is below.

Traceback (most recent call last):
  File "main.py", line 119, in <module>
    RAP = model.RAP_relprop(R=T)
  File "Relative_Attributing_Propagation/modules/resnet.py", line 335, in RAP_relprop
    R = self.layer4.RAP_relprop(R)
  File "Relative_Attributing_Propagation/modules/layers.py", line 207, in RAP_relprop
    Rp = m.RAP_relprop(Rp)
  File "Relative_Attributing_Propagation/modules/resnet.py", line 113, in RAP_relprop
    return self.clone.RAP_relprop([x1, x2])
  File "Relative_Attributing_Propagation/modules/layers.py", line 154, in RAP_relprop
    Rp_tmp = backward(tmp_R_p[i])
  File "Relative_Attributing_Propagation/modules/layers.py", line 139, in backward
    for z, rp, rn in zip(Z, R_p):
ValueError: not enough values to unpack (expected 3, got 2)

wjnam / relative_attributing_propagation Goto Github PK

relative_attributing_propagation's People

Contributors

Stargazers

Watchers

Forkers

relative_attributing_propagation's Issues

Keras implementation

RAP will generate weird heatmap on resnet

relprop function in resnet.py

Evaluation Metric code share

RAP for different output shape

Error with ResNet18 and Resnet34 (BasicBlock in Resnet)

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent