yangxue0827 / FPN_Tensorflow

A Tensorflow implementation of FPN detection framework.
416 stars 150 forks source link

TypeError: cond() got an unexpected keyword argument 'true_fn', i am puzzled with this problem, do you meet this problem before, can you help me? #13

Closed chinapanda closed 6 years ago

chinapanda commented 6 years ago

I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcublas.so locally I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcudnn.so locally I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcufft.so locally I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcuda.so.1 locally I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcurand.so locally tfrecord path is --> /home/hley/software/FPN_Tensorflow/data/tfrecords/pascal_train Traceback (most recent call last): File "train.py", line 229, in train() File "train.py", line 34, in train is_training=True) File "../data/io/read_tfrecord.py", line 82, in next_batch is_training=is_training) File "../data/io/read_tfrecord.py", line 57, in read_and_prepocess_single_img target_shortside_len=shortside_len) File "../data/io/image_preprocess.py", line 26, in short_side_resize false_fn=lambda: (target_shortside_len h//w, target_shortside_len)) TypeError: cond() got an unexpected keyword argument 'true_fn'

yangxue0827 commented 6 years ago

I guess this function is changed between the different version of tensorflow

chinapanda commented 6 years ago

thanks! that is right, i have already corrected it, i want to know how much data to train these models just for plane. thanks!

niuniu111 commented 6 years ago

I also met this problem, what should I do ?

chinapanda commented 6 years ago

Change the version of tensorflow into 1.2. look this configure [ ubuntu(Encoding problems may occur on windows) + python2 + tensorflow1.2 + cv2 + cuda8.0 + GeForce GTX 1080 ]