Grad-CAM.pytorch
Grad-CAM.pytorch copied to clipboard
yizt
pytorch实现Grad-CAM和Grad-CAM++,可以可视化任意分类网络的Class Activation Map (CAM)图,包括自定义的网络;同时也实现了目标检测faster r-cnn和retinanet两个网络的CAM图;欢迎试用、关注并反馈问题...
问题描述： 加载imagenet预训练权重跑没问题。但是当我尝试着加载自己训练好的模型权重时，出现以下错误： ``` size mismatch for fc.weight: copying a param with shape torch.Size([5, 2048]) from checkpoint, the shape in current model is torch.Size([1000, 2048]). size mismatch for fc.bias: copying a...
feature shape:torch.Size([1, 256, 100, 136]) feature shape:torch.Size([1, 256, 50, 68]) feature shape:torch.Size([1, 256, 25, 34]) feature shape:torch.Size([1, 256, 13, 17]) feature shape:torch.Size([1, 256, 7, 9]) Traceback (most recent call last):...
```python def gen_cam(image, mask): heatmap = cv2.applyColorMap(np.uint8(255 * mask), cv2.COLORMAP_JET) # heatmap = np.float32(heatmap) / 255 # little bug here heatmap = np.float32(heatmap) heatmap = heatmap[..., ::-1] # gbr to...
大佬您好 我是做图像复原的 请问热力图能应用到图像复原领域吗 如果可以的话，应该对谁进行反向传播呢 图像复原的结果是二维矩阵 并不是分类任务的一个值 求大佬指教
ValueError: operands could not be broadcast together with shapes (224,224,4) (3,) (224,224,4) 加载自己模型的报错，修改了get_net(net_name, weight_path=None)部分
嗨，我尝试运行RetinaNet示例代码。 该程序开始运行，但不久后失败。 那是最后几行： Hi, I tried to run the RetinaNet sample code. The program started to run, but failed shortly after. Those are the last few lines: ```python feature shape:torch.Size([1,...
@yizt Thanks for sharing your work . How can we use the current code to for segmentation models like deeplab . Can you share / suggest the modifications required Thanks...
Hi, Thanks for publishing this great repo! I am debugging an SSD network used for a 3-class object detection task. Can I use this repo for visualizing such a network...
