Something's wrong

[wangtianlong1994]

image 1/1 data/samples/Jujube_4501.bmp: Model Summary: 222 layers, 6.1556e+07 parameters, 6.1556e+07 gradients
Traceback (most recent call last):
  File "/home/zxzn/YOLOv3-GradCAM/gradcam/gradcam.py", line 178, in <module>
    cam = grad_cam.generate_cam(prep_img, target_class)
  File "/home/zxzn/YOLOv3-GradCAM/gradcam/gradcam.py", line 127, in generate_cam
    conv_output, model_output = self.extractor.forward_pass(input_image)
  File "/home/zxzn/YOLOv3-GradCAM/gradcam/gradcam.py", line 106, in forward_pass
    conv_output, x = self.forward_pass_on_convolutions(x)
  File "/home/zxzn/YOLOv3-GradCAM/gradcam/gradcam.py", line 91, in forward_pass_on_convolutions
    x = x + layer_outputs[int(mdef["from"])]
TypeError: int() argument must be a string, a bytes-like object or a number, not 'list'

Process finished with exit code 1

Why is that? I used the model trained by yolov3 of ultralytics and the corresponding CFG, but it couldn't work normally. In addition, I also took it out of the yolov3 file of ultralytics models.py , utils folder

This is my directory structure

(cam) zxzn@zxzn:~/YOLOv3-GradCAM/gradcam$ ls
cfg  data  detect.py  gradcam.py  misc_functions.py  models.py  __pycache__  test.py  train.py  utils  weights

Thank you for your help @pifalken

[pifalken]

I'll need to look into this further as something deeper is broken in the forward pass. For your specific error, you can replace:

int(mdef["from"])

with:

int(mdef["from"][0])

However, doing so will bring to light the other issues which I need to look into.

[wangtianlong1994]

我需要进一步研究这一点，因为前向传递中有更深层的问题。对于您的特定错误，您可以替换：

int（mdef [ “ from” ]）

与：

int（mdef [ “ from” ] [ 0 ]）

但是，这样做会发现我需要研究的其他问题。

I'll need to look into this further as something deeper is broken in the forward pass. For your specific error, you can replace:

int(mdef["from"])

with:

int(mdef["from"][0])

However, doing so will bring to light the other issues which I need to look into.

YES,When I do what you say, I will still display the type error

x = x + layer_outputs[int(mdef["from"][0])] TypeError: unsupported operand type(s) for +: 'Tensor' and 'list'

Looking forward to your solution

[praneet195]

Ok So on going through the code, Line #95 in gradcam.py should just be layer_outputs.append(x) This seems to work for me after taking into account the fix mentioned above. Now i'm running into the following error in misc_functions.py on the line: heatmap_on_image = Image.alpha_composite(heatmap_on_image, heatmap) saying images donot match. Trying to fix this but please let me know if you think the above fix is good enough?

[n-akram]

We are also trying this as well.

We were able to solve the issue @praneet195 has by adding the following line after line 91 in misc_functions.py.

https://github.com/pifalken/YOLOv3-GradCAM/blob/6a66a9eb469e43c0d42c7d1ce84eea9c16cff3da/gradcam/misc_functions.py#L91 heatmap_on_image = heatmap_on_image.resize(heatmap.size)

This is at least a temporary fix.

[wllkk]

image 1/1 data/samples/Jujube_4501.bmp: Model Summary: 222 layers, 6.1556e+07 parameters, 6.1556e+07 gradients
Traceback (most recent call last):
  File "/home/zxzn/YOLOv3-GradCAM/gradcam/gradcam.py", line 178, in <module>
    cam = grad_cam.generate_cam(prep_img, target_class)
  File "/home/zxzn/YOLOv3-GradCAM/gradcam/gradcam.py", line 127, in generate_cam
    conv_output, model_output = self.extractor.forward_pass(input_image)
  File "/home/zxzn/YOLOv3-GradCAM/gradcam/gradcam.py", line 106, in forward_pass
    conv_output, x = self.forward_pass_on_convolutions(x)
  File "/home/zxzn/YOLOv3-GradCAM/gradcam/gradcam.py", line 91, in forward_pass_on_convolutions
    x = x + layer_outputs[int(mdef["from"])]
TypeError: int() argument must be a string, a bytes-like object or a number, not 'list'

Process finished with exit code 1

这是为什么？我使用了由yolov3 of Ultralytics训练的模型和相应的CFG，但无法正常工作。此外，我还从utils文件夹ultralytics models.py的yolov3文件中删除了该文件

这是我的目录结构

(cam) zxzn@zxzn:~/YOLOv3-GradCAM/gradcam$ ls
cfg  data  detect.py  gradcam.py  misc_functions.py  models.py  __pycache__  test.py  train.py  utils  weights

谢谢您的帮助@pifalken

你好，我也遇到了这个问题，请问您解决了吗？

[wllkk]

好的， 所以在遍历代码时，gradcam.py中的第95行应该只是layer_outputs.append（x）。 考虑到上述修复后，这似乎对我有用。 现在，我在网上的misc_functions.py中遇到以下错误： heatmap_on_image = Image.alpha_composite(heatmap_on_image, heatmap) 说图像不匹配。 尝试解决此问题，但是如果您认为上述修复足够好，请告诉我。 excause me，How do you fix this bug? x = x + layer_outputs[int(mdef["from"])] TypeError: int() argument must be a string, a bytes-like object or a number, not 'list' please help me。looking forward to your reply。

[xielock]

请问这个问题解决了吗？？？？