hexin6688
hexin6688
loss is descending,but the val loss=nan,anybody have face this problem?
我训练自己的数据集的时候,按照训练Market1501的方法,把图片都按照ID放在不同的文件夹之后。训练的时候,train-loss正常下降,val-loss从第一个epoch开始不变,到后面一直上升。 训练集: ID:19658 train_all:72824 images train:65624 images val:7200 images (when train this model on my own dataset,the train-loss decrease correctly,but the val-loss increase from the first epoch)
Traceback (most recent call last): File "G:/数据集/tensorflow-yolov3-master/image_demo.py", line 43, in np.reshape(pred_lbbox, (-1, 5 + num_classes))], axis=0) File "G:\anaconda\lib\site-packages\numpy\core\fromnumeric.py", line 292, in reshape return _wrapfunc(a, 'reshape', newshape, order=order) File "G:\anaconda\lib\site-packages\numpy\core\fromnumeric.py", line...
why insset the non-local attention in this way?
Traceback (most recent call last): File "G:\darknet_to_tensorflow\DW2TF-1.2\util\reader.py", line 84, in get_block line = next(line_getter) StopIteration The above exception was the direct cause of the following exception: Traceback (most recent call...