Open essxnce opened 5 years ago
I also have this problem. I modified the "N/16" to "int(N/16)", then it can work. May be you can try this way.
It is Python 2 code. Don't run it on Python 3.6.
@xuwang1988 Hello, have you run this program already?I have a problem with the. Mat data format .Can you give me some help?
I have a problem with the. Mat data format .I don't know how to convert ShapeNet data to .Mat data. Can you give me some help?
@LebronGG hellow,we met the same question i cover the m40 to .mat ,But the program reported error,so i read the train.py to see how to read the data and chage the format ,I tried many times but all failed .Can we solve the problem together?Exchange ideas
Hello, I'm so surprised your code simplicity. When I use and your codework, I just have a problem like this :
jinhyeok@yang:~/PointGrid/code$ python train.py /home/jinhyeok/anaconda3/lib/python3.6/site-packages/h5py/init.py:36: FutureWarning: Conversion of the second argument of issubdtype from
train()
File "train.py", line 128, in train
pred_cat, pred_seg = model.get_model(dequeue_pointgrid, is_training=is_training_ph)
File "/home/jinhyeok/PointGrid/code/network.py", line 194, in get_model
cat_features = tf.tile(tf.reshape(tf.concat([fc2, pred_cat], axis=1), [batch_size, 1, 1, 1, -1]), [1, N/16, N/16, N/16, 1])
File "/home/jinhyeok/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/gen_array_ops.py", line 8805, in tile
"Tile", input=input, multiples=multiples, name=name)
File "/home/jinhyeok/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 609, in _apply_op_helper
param_name=input_name)
File "/home/jinhyeok/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 60, in _SatisfiesTypeConstraint
", ".join(dtypes.as_dtype(x).name for x in allowed_list)))
TypeError: Value passed to parameter 'multiples' has DataType float32 not in list of allowed values: int32, int64
float
tonp.floating
is deprecated. In future, it will be treated asnp.float64 == np.dtype(float).type
. from ._conv import register_converters as _register_converters Batch Size: 32 Training using GPU: 1 Training epoch: 200 Traceback (most recent call last): File "train.py", line 206, inI don't know why this situation just happened...
Jinhyeok