YOLO
YOLO
冻结训练的问题
你好，我在train里面已经将Freeze_Train设置为False，为什么开始训练的时候，下面还是显示1/50？最开始的loss达到了1000 （Faster-RCNN里面也是这个情况）   
Hello, I think Criss-Cross Attention & Axial Attention are also the commonly used attention mechanisms.
May I ask if you have solved the problem“'numpy.ndarray' object has no attribute 'add_patch'”？I have the same problem
Hi I notice that the derivation of axial-attention in the code is as follows： But in the original version of axial attention it would look like this： I don't fully...
Hi~I have some questions about Axial-attention Why [there](https://github.com/AngeLouCN/CaraNet/blob/2664929e03e1fa8a0763de149b002a573027d547/lib/self_attention.py#L37) is no premute operation before view in mode h? ``` # for mode h projected_query = self.query_conv(x).premute(0, 1, 3, 2).view(*view).permute(0, 2, 1)...
Hello! I have some questions about cv2.canny module. What is the function of "cv2. Canny"module in the figure? This step is not in the MSRF-Net, and I don't see a...
Hello, I have a doubt about Sensitivity Specificity loss function's implementation. So I think that the correct way to translate this Sensitivity into **prediction ** and **ground_truth ** terms for...
Thank you for the great code～I have a theoretical question to ask. What is the significance of averaging the prediction results for T forward propagation? This is a classification problem...
尝试复现了一下，发现有几个问题(不确定)，如遇到相同问题，欢迎讨论。 ### **1.class JsonReader** 对于build_vocab.py中的class JsonReader,在构建vocab的时候是没有问题的，但在dataset.py中，self.caption[image_name]，image_name已经是图像名称，而不需要像build_vocab.py中用key[序号]来取。 所以我认为在运行trainer.py->dataset.py的时候class JsonReader应该改为如下。实验结束也表明修改之后的 JsonReader才会构造出不是空的target。 ``` class JsonReader(object): def __init__(self, json_file): self.data = self.__read_json(json_file) def __read_json(self, filename): with open(filename, 'r') as f: data = json.load(f) return...
In the gloria_model.py/def get_local_similarities(130), row_sim is computed by "max" ``` row_sim, max_row_idx = torch.max(row_sim, dim=1, keepdim=True) # [48, 1] ``` and, in the gloria_loss.py / def local_loss(120), row_sim is computed...