can't load the pre-trained model.
Opened this issue · 11 comments
always inform me of different tensor name not found error every time I press run. For example,
NotFoundError (see above for traceback): Tensor name "scale5/block3/c/scale5/block3/c/moving_variance/biased" not found in checkpoint files ./data/tensorflow-resnet-pretrained-20160509/ResNet-L50.ckpt
NotFoundError (see above for traceback): Tensor name "scale4/block6/b/scale4/block6/b/moving_mean/local_step" not found in checkpoint files ./data/tensorflow-resnet-pretrained-20160509/ResNet-L50.ckpt
this error drove me craze. how can i fix this?????????????????????????????????
this happened when I combine my own codes with the inference ry provided.
x = tf.placeholder(tf.float32, [None, None, 640, 3])
y_ = tf.placeholder(tf.float32, [None, 480, 640, 1],name="y_")
y_sm = tf.placeholder(tf.float32, [None, 480, 640, 1],name="y_sm")
y = inference(x, is_training=True)
I put some simple layers after the inference to suit my output. but the error has nothing to do with that.
@LvJC Did you successfully download the pretrained model by using the .torrent file? I can't download it because of no peers. Could you please provide an available url for me ? Thanks.
@LvJC have you solve it？I met the same problem. I think it is caused by the version of Tensorflow,but I have no idea which version it is
@daisysnow I use another bn function and changed the parameters' names
@LvJC Could you share the bn function and the checkpoint？ I just visited your homepage，is that what I can use directly？
@daisysnow I will fork it on my homepage in recent days
@daisysnow visit my fork, and I update the bn function.
@LvJC Hi, there is no seeds for torrent format file, can you send me the file named tensorflow-resnet-pretrained-20160509.tar.gz ? My email: 1598176867@qq.com. Thank you very much.
always inform me of different tensor name not found error every time I press
run. For example,
NotFoundError (see above for traceback): Tensor name "scale5/block3/c/scale5/block3/c/moving_variance/biased" not found in checkpoint files ./data/tensorflow-resnet-pretrained-20160509/ResNet-L50.ckpt
NotFoundError (see above for traceback): Tensor name "scale4/block6/b/scale4/block6/b/moving_mean/local_step" not found in checkpoint files ./data/tensorflow-resnet-pretrained-20160509/ResNet-L50.ckpt
always inform me of different tensor name not found error every time I press
run. For example,
NotFoundError (see above for traceback): Tensor name "scale5/block3/c/scale5/block3/c/moving_variance/biased" not found in checkpoint files ./data/tensorflow-resnet-pretrained-20160509/ResNet-L50.ckpt
NotFoundError (see above for traceback): Tensor name "scale4/block6/b/scale4/block6/b/moving_mean/local_step" not found in checkpoint files ./data/tensorflow-resnet-pretrained-20160509/ResNet-L50.ckpt
Because the structure in checkpoint is not equal to the inference() function
You can visualize the structure in checkpoint by tensorboard and compare it with the code in inference(), you will find this problem......