JFanL

Encountered the same problem, Audios_tf = tf.placeholder(tf.float32, shape=[batch_size, None], name='1_input') Preds_th, loss_th = sess.run((preds, loss), feed_dict={labels_tf: np.array(y_test), audios_tf: np.array(audios_np)}) Traceback (most recent call last): File "TRY.py", line 173, in audios_tf...

I solved it. In sess, the normalized place went wrong. mean, var = tf.nn.moments(m, axes=[2]) leads to tf.nn.batch_normalization(x=m, mean=mean, variance =var, offset=shift, scale=scale, variance_epsilon=0) The data does not correspond (the...

https://github.com/xingyizhou/CenterNet/issues/816#issue-703620592

> (centernet) C:\Users\QZW\CenterNet-windows\src\lib\models\networks\DCNv2>python setup.py build develop running build running build_ext D:\Users\QZW\Anaconda3\envs\centernet\lib\site-packages\torch\utils\cpp_extension.py:196: UserWarning: > > ``` > !! WARNING !! > ``` > > !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! Your compiler (cl 19.00.24210) may be...

> It needed to make install cocoAPI (Download from https://github.com/philferriere/cocoapi, and unzip cocoapi-master.zip to cocoapi-master. After that, cd to cocoapi-master/PythonAPI and make install ) and cd to CornerNet-Lite/core/models/py_utils/_cpools: python setup.py...

I disable the multi-thread dataloader by --not_prefetch_test to solve the problem.refer to https://github.com/xingyizhou/CenterNet/issues/126#issuecomment-499606727

I have the same problem. Have you solved it?

I solved it. In sess, the normalized place went wrong. mean, var = tf.nn.moments(m, axes=[2]) leads to tf.nn.batch_normalization(x=m, mean=mean, variance =var, offset=shift, scale=scale, variance_epsilon=0) The data does not correspond (the...

> It looks like the problem is with the .so being compiled for ubuntu but trying to be loaded into osx. Did you start the colab kernel from inside of...

@Naveenkhasyap The same error occurred. Can't solve the problem without modifying or reducing the environment? Is there any other way?