ily666666
ily666666
if img is a gray img `image_pil = PIL.Image.open(filename)` it will fail to open img
 想问一下,这里我行色标注的尖括号是什么意思?这里公式(5)代表的意思是求相似度之后再相加还是相加之后再求相似度? 如果是求相似度之后再相加,下面我黄色标注的记号的R(i,j)就不再属于[-1,1]? 
PFENet++
#6 中提到并给出了训练日志,在训练阶段使用count=2000来进行评估,但是代码中训练阶段是5000,这是否对评估结果有影响?
没穿反光衣是否需要标注?
Hello, can you provide your circuit diagram data?
when I run section #overfit a sample# in train_model.ipynb, it appears. How can I solve it? OOM when allocating tensor with shape[1,1024,64,64] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc...