Closed JumeLin closed 2 years ago
Hi, Sorry for the late reply. Can you please share more details, maybe some code, Maybe share the code snippet where you construct the CAM object ?
Thank you very much. forget that question which is a silly question. I have the other question when I use the grad-cam to realize the heatmap of YOLOV5 for object detection, but something wrong as follows:
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor 【1, 3, 20, 20, 12】], which is output 0 of SigmoidBackward, is at version 2; expected version 0 instead. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later. Good luck!
I don't know how to solute that question. the function "get_loss" in my code was wrong.
class GradCAM:
def __init__(self,
model,
target_layers,
reshape_transform=None,
use_cuda=False):
self.model = model.eval()
self.target_layers = target_layers
self.reshape_transform = reshape_transform
self.cuda = use_cuda
if self.cuda:
self.model = model.cuda()
self.activations_and_grads = ActivationsAndGradients(self.model, target_layers, reshape_transform)
""" Get a vector of weights for every channel in the target layer.
Methods that return weights channels,
will typically need to only implement this function. """
@staticmethod
def get_cam_weights(grads):
return np.mean(grads, axis=(2, 3), keepdims=True)
@staticmethod
def get_loss(output, target_category):
loss = 0
# print(target_category)
for i in range(len(target_category)):
output = output[i]
# print(output.size())
loss = loss + output(:, 5+target_category[i])
return loss
def get_cam_image(self, activations, grads):
weights = self.get_cam_weights(grads)
weighted_activations = weights * activations
cam = weighted_activations.sum(axis=1)
return cam
@staticmethod
def get_target_width_height(input_tensor):
width, height = input_tensor.size(-1), input_tensor.size(-2)
return width, height
def compute_cam_per_layer(self, input_tensor):
activations_list = [a.cpu().data.numpy()
for a in self.activations_and_grads.activations]
grads_list = [g.cpu().data.numpy()
for g in self.activations_and_grads.gradients]
target_size = self.get_target_width_height(input_tensor)
cam_per_target_layer = []
# Loop over the saliency image from every layer
for layer_activations, layer_grads in zip(activations_list, grads_list):
cam = self.get_cam_image(layer_activations, layer_grads)
cam[cam < 0] = 0 # works like mute the min-max scale in the function of scale_cam_image
scaled = self.scale_cam_image(cam, target_size)
cam_per_target_layer.append(scaled[:, None, :])
return cam_per_target_layer
def aggregate_multi_layers(self, cam_per_target_layer):
cam_per_target_layer = np.concatenate(cam_per_target_layer, axis=1)
cam_per_target_layer = np.maximum(cam_per_target_layer, 0)
result = np.mean(cam_per_target_layer, axis=1)
return self.scale_cam_image(result)
@staticmethod
def scale_cam_image(cam, target_size=None):
result = []
for img in cam:
img = img - np.min(img)
img = img / (1e-7 + np.max(img))
if target_size is not None:
img = cv2.resize(img, target_size)
result.append(img)
result = np.float32(result)
return result
def __call__(self, input_tensor, target_category=None):
if self.cuda:
input_tensor = input_tensor.cuda()
# 正向传播得到网络输出logits(未经过softmax)
# 这里output = self.activation_and_grads(input_tensor)是将输入进行正向传播并注册正向传播hook函数和方向hook函数,
# 得到activation和反向的grad
output = self.activations_and_grads(input_tensor)[0]
# debug
# 由Yolov5的predict函数可知预测输出为 pred=model(img, augment=augment, visualize=visualize)[0],and the size of pred
# is (bs, num_box, xywh+obj_conf+obj_classes)
# 判断target_category是否为int类型
if isinstance(target_category, int):
# 如果是,再将target_category乘上一个batch维度的信息
target_category = [target_category] * input_tensor.size(0)
if target_category is None:
# 如果指定的target_category为None,则预测得分最高的类
target_category = np.argmax(output.cpu().data.numpy(), axis=-1)
print(f"category id: {target_category}")
else:
assert (len(target_category) == input_tensor.size(0))
self.model.zero_grad()
loss = self.get_loss(output, target_category)
loss.backward(retain_graph=True)
cam_per_layer = self.compute_cam_per_layer(input_tensor)
return self.aggregate_multi_layers(cam_per_layer)
def __del__(self):
self.activations_and_grads.release()
def __enter__(self):
return self
def __exit__(self, exc_type, exc_value, exc_tb):
self.activations_and_grads.release()
if isinstance(exc_value, IndexError):
# Handle IndexError here...
print(
f"An exception occurred in CAM with block: {exc_type}. Message: {exc_value}")
return True
Hi, Sorry for the late reply. Can you please share more details, maybe some code, Maybe share the code snippet where you construct the CAM object ?
The get_loss function seems strange.
output = output[i]
What is the intention in this line?
Closing this issue, please re-open if relevant.
File "H:/codefile/personal/yolov5/pytorch-grad-cam-master/my_cam.py", line 144, in
reshape_transform=None)
TypeError: EigenCAM() takes no arguments
I found that the 'fasterrcnn_reshape_transform' was just defined but didn't use it when I try to implement the faster-rcnn. Then the error came out.