Open kunfei1 opened 6 years ago
i just found make a mistake ,but it also only 80map...
Load segmentation weights Push Model to GPU Main Begins Exception in thread prefetch_loop: Traceback (most recent call last): File "/home/lvv/anaconda2/lib/python2.7/threading.py", line 801, in __bootstrap_inner self.run() File "/home/lvv/anaconda2/lib/python2.7/threading.py", line 754, in run self.target(*self.args, **self.__kwargs) File "/home/lvv/anaconda2/lib/python2.7/site-packages/chainer/iterators/multiprocess_iterator.py", line 336, in _run alive = self._task() File "/home/lvv/anaconda2/lib/python2.7/site-packages/chainer/iterators/multiprocess_iterator.py", line 355, in _task data_all = future.get(_response_time) File "/home/lvv/anaconda2/lib/python2.7/multiprocessing/pool.py", line 572, in get raise self._value AttributeError: 'NoneType' object has no attribute 'shape' Have you ever come across this problem?thank you very much
yes,you can see the first issue, Replacing x = self.pool(x) with x = self.pool.apply((x,))[0] will solve the problem
thank you .I'll try
this code have you ever run over?could you send your runned code to me ?i have try your method, but not solve this problem
hellow I have trained market datasets with the market and duke pretrained model. And test with python, but get a bad result mAP 0.16. I think although the pretrained is important, the result is too bad. did some important points need to attention? By the way , I use the imagename's persion id like '-1_c1s1_001376_05.jpg', using '-1'. and misunderstand that the code's 'market_gallery.txt' , it contain like 'market/bounding_box_test/-1_c1s1_000401_03.jpg 0',but i could not understand the meaning of '0', it seems all the .jpg follows '0'.
i just found make a mistake ,but it also only 80map...
Hi, I run this code for 20000 iterations, but the mAP is only 0.4445. I didn't pretrain it on 10 reid datasets. I only train it on Market-1501 for 20000 iterations. How do you train it to get 0.80 mAP? Thanks!
hellow I have trained market datasets with the market and duke pretrained model. And test with python, but get a bad result mAP 0.16. I think although the pretrained is important, the result is too bad. did some important points need to attention? By the way , I use the imagename's persion id like '-1_c1s1_001376_05.jpg', using '-1'. and misunderstand that the code's 'market_gallery.txt' , it contain like 'market/bounding_box_test/-1_c1s1_000401_03.jpg 0',but i could not understand the meaning of '0', it seems all the .jpg follows '0'.
i just found make a mistake ,but it also only 80map...
Hi, I run this code for 20000 iterations, but the mAP is only 0.4445. I didn't pretrain it on 10 reid datasets. I only train it on Market-1501 for 20000 iterations. How do you train it to get 0.80 mAP? Thanks!
I just pretrain it on Market1501+Duke....
Hello, Do you know how to compute the rank1 and mAP? could you give me the code which compute the rank1 and mAP, My mail is pku1401210454@163.com, Thank you very much! @kunfei1
hellow I have trained market datasets with the market and duke pretrained model. And test with python, but get a bad result mAP 0.16. I think although the pretrained is important, the result is too bad. did some important points need to attention? By the way , I use the imagename's persion id like '-1_c1s1_001376_05.jpg', using '-1'. and misunderstand that the code's 'market_gallery.txt' , it contain like 'market/bounding_box_test/-1_c1s1_000401_03.jpg 0',but i could not understand the meaning of '0', it seems all the .jpg follows '0'.