Something's wrong about yolov3-gradcam HOT 7 OPEN

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.

This is at least a temporary fix.

from yolov3-gradcam.

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.

from yolov3-gradcam.

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

from yolov3-gradcam.

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?

from yolov3-gradcam.

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？

from yolov3-gradcam.

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。

from yolov3-gradcam.

请问这个问题解决了吗？？？？

from yolov3-gradcam.