search

hehefan / Unsupervised-Person-Re-identification-Clustering-and-Fine-tuning

219 stars 87 forks source link

ValueError: No such layer: avg_pool #17

Closed mod1998 closed 5 years ago

mod1998 commented 6 years ago

I run the train.py and get 0.ckpt,but when I use it to run unsupervised.py,I get the error: Traceback (most recent call last): File "unsupervised.py", line 97, in net = Model(input=previous_model.input, output=previous_model.get_layer('avg_pool').output) File "/home/zhangkun/anaconda3/envs/tensorflow/lib/python3.6/site-packages/keras/engine/network.py", line 364, in get_layer raise ValueError('No such layer: ' + name) ValueError: No such layer: avg_pool

mod1998 commented 6 years ago

but I use your duke.ckpt to run unsupervised,there is no error.

hehefan commented 5 years ago

I think it may be caused by the keras version. I use the version 2.0.4.　 You can also train a baseline model by yourself. It won't take too much time.