Closed xiaoshuguo750 closed 6 years ago
I have resolved the problem
bboxes = tf.sparse_tensor_to_dense(features['bboxes']) maxval0 = tf.size(bboxes, out_type=tf.int32)/8 maxval1 = tf.to_int32(maxval0) r = 8*tf.random_uniform((1,), minval=0, maxval=maxval1, dtype=tf.int32)
Thank you very much!
Hi! When I run grasp_det.py for the training on pycharm, there were some errors,
/home/xiaoshuguo/anaconda3/bin/python /home/xiaoshuguo/PycharmProjects/untitled2/robot-grasp-detection/grasp_det.py validation inputs False False Traceback (most recent call last): File "/home/xiaoshuguo/PycharmProjects/untitled2/robot-grasp-detection/grasp_det.py", line 162, in
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
File "/home/xiaoshuguo/anaconda3/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "/home/xiaoshuguo/PycharmProjects/untitled2/robot-grasp-detection/grasp_det.py", line 115, in main
run_training()
File "/home/xiaoshuguo/PycharmProjects/untitled2/robot-grasp-detection/grasp_det.py", line 47, in run_training
images, bboxes = grasp_img_proc.inputs([datafiles])
File "/home/xiaoshuguo/PycharmProjects/untitled2/robot-grasp-detection/grasp_img_proc.py", line 158, in inputs
num_readers=1)
File "/home/xiaoshuguo/PycharmProjects/untitled2/robot-grasp-detection/grasp_img_proc.py", line 122, in batch_inputs
image_buffer, bbox = parse_example_proto(examples_serialized)
File "/home/xiaoshuguo/PycharmProjects/untitled2/robot-grasp-detection/grasp_img_proc.py", line 26, in parse_example_proto
r = 8*tf.random_uniform((1,), minval=0, maxval=tf.size(bboxes, out_type=tf.int32)/8, dtype=tf.int32)
File "/home/xiaoshuguo/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/random_ops.py", line 229, in random_uniform
maxval = ops.convert_to_tensor(maxval, dtype=dtype, name="max")
File "/home/xiaoshuguo/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 639, in convert_to_tensor
as_ref=False)
File "/home/xiaoshuguo/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 704, in internal_convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "/home/xiaoshuguo/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 577, in _TensorTensorConversionFunction
% (dtype.name, t.dtype.name, str(t)))
ValueError: Tensor conversion requested dtype int32 for Tensor with dtype float64: 'Tensor("truediv:0", shape=(), dtype=float64, device=/device:CPU:0)'
I don't know why it is? How can I resovle it? Thank you very much! #