@rainley123 . So how did you solved this?

Just add a code to judge if the croped_xmin is equal to the croped_xmax, is they are the same, remove the label and box, because this object will not be in the picture after crop.
the code is like this:

if the object is not in the dist_box, just remove it

mask = tf.logical_not(tf.logical_or(tf.equal(croped_xmin, croped_xmax), tf.equal(croped_ymin, croped_ymax)))        
croped_xmin = tf.boolean_mask(croped_xmin, mask)
croped_ymin = tf.boolean_mask(croped_ymin, mask)
croped_xmax = tf.boolean_mask(croped_xmax, mask)
croped_ymax = tf.boolean_mask(croped_ymax, mask)
labels = tf.boolean_mask(labels, mask) 

from tensorflow-yolov3.

When I run the train.py,I also can‘t train my data.It's also the problem:

OutOfRangeError: End of sequence
[[{{node cond/IteratorGetNext_1}} = IteratorGetNextoutput_shapes=[[?,416,416,3], , , ], output_types=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

During handling of the above exception, another exception occurred。OutOfRangeError Traceback (most recent call last)
in ()
78 if (epoch+1)%1000 == 0: saver.save(sess, save_path="./checkpoint/yolov3.ckpt", global_step=epoch)

Do you know what's the problem?

from tensorflow-yolov3.

=> EPOCH: 341 loss_xy: 1.6257 loss_wh: 4.0940 loss_conf:4570.6030 loss_class:14.2002
=> EPOCH: 342 loss_xy: 1.5741 loss_wh: 2.6803 loss_conf:4656.8652 loss_class:11.8622
=> EPOCH: 343 loss_xy: 1.3638 loss_wh: 2.3212 loss_conf:4657.7090 loss_class:11.4552
2019-01-22 16:34:48.172989: W tensorflow/core/framework/op_kernel.cc:1261] Unknown: IndexError: index 13 is out of bounds for axis 0 with size 13
Traceback (most recent call last):

File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/script_ops.py", line 206, in call
ret = func(*args)

File "........../tensorflow-yolov3/core/dataset.py", line 105, in preprocess_true_boxes
y_true[l][j, i, k, 0:4] = gt_boxes[t, 0:4]

IndexError: index 13 is out of bounds for axis 0 with size 13

what's wrong

I also got this problems and have solved this problems. when you do data_augmentation. there are some problems in crop code. if one object is not in the distort_box, the croped_xmin and croped_xmax will be the same, in this way, you will get this problems

from tensorflow-yolov3.

@rainley123 . So how did you solved this?

from tensorflow-yolov3.

Thanks a lot, I gonna try it.

from tensorflow-yolov3.

UnknownError: IndexError: index 89 is out of bounds for axis 0 with size 88
Traceback (most recent call last):

File "D:\Users\madhu\Anaconda3\envs\yolo\lib\site-packages\tensorflow\python\ops\script_ops.py", line 206, in call
ret = func(*args)

File "C:\Users\madhu\Desktop\working\tensorflow-yolov3-master\core\dataset.py", line 180, in preprocess_true_boxes
y_true[l][j, i, k, 0:4] = gt_boxes[t, 0:4]

IndexError: index 89 is out of bounds for axis 0 with size 88

 [[{{node PyFunc}} = PyFunc[Tin=[DT_FLOAT], Tout=[DT_FLOAT, DT_FLOAT, DT_FLOAT], token="pyfunc_0"](stack)]]
 [[node cond/IteratorGetNext (defined at C:\Users\madhu\Desktop\working\tensorflow-yolov3-master\core\dataset.py:230)  = IteratorGetNext[output_shapes=[[?,704,1280,3], <unknown>, <unknown>, <unknown>], output_types=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](cond/IteratorGetNext/Switch:1)]]

for some reason i am also getting the same error. I have included the above code, still there is no change.

from tensorflow-yolov3.

UnknownError: IndexError: index 89 is out of bounds for axis 0 with size 88
Traceback (most recent call last):

File "D:\Users\madhu\Anaconda3\envs\yolo\lib\site-packages\tensorflow\python\ops\script_ops.py", line 206, in call
ret = func(*args)

File "C:\Users\madhu\Desktop\working\tensorflow-yolov3-master\core\dataset.py", line 180, in preprocess_true_boxes
y_true[l][j, i, k, 0:4] = gt_boxes[t, 0:4]

IndexError: index 89 is out of bounds for axis 0 with size 88

 [[{{node PyFunc}} = PyFunc[Tin=[DT_FLOAT], Tout=[DT_FLOAT, DT_FLOAT, DT_FLOAT], token="pyfunc_0"](stack)]]
 [[node cond/IteratorGetNext (defined at C:\Users\madhu\Desktop\working\tensorflow-yolov3-master\core\dataset.py:230)  = IteratorGetNext[output_shapes=[[?,704,1280,3], <unknown>, <unknown>, <unknown>], output_types=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](cond/IteratorGetNext/Switch:1)]]

for some reason i am also getting the same error. I have included the above code, still there is no change.

I was receiving this same error.If you have some classes like me, make sure your label class names start from index 0 and not 1.

from tensorflow-yolov3.

My class names are labeled from zero only. If you know any further info please let me know

from tensorflow-yolov3.

=> EPOCH: 341 loss_xy: 1.6257 loss_wh: 4.0940 loss_conf:4570.6030 loss_class:14.2002
=> EPOCH: 342 loss_xy: 1.5741 loss_wh: 2.6803 loss_conf:4656.8652 loss_class:11.8622
=> EPOCH: 343 loss_xy: 1.3638 loss_wh: 2.3212 loss_conf:4657.7090 loss_class:11.4552
2019-01-22 16:34:48.172989: W tensorflow/core/framework/op_kernel.cc:1261] Unknown: IndexError: index 13 is out of bounds for axis 0 with size 13
Traceback (most recent call last):

File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/script_ops.py", line 206, in call
ret = func(*args)

File "........../tensorflow-yolov3/core/dataset.py", line 105, in preprocess_true_boxes
y_true[l][j, i, k, 0:4] = gt_boxes[t, 0:4]

IndexError: index 13 is out of bounds for axis 0 with size 13

what's wrong

hello,i met the same problem with u,have u solved it?

from tensorflow-yolov3.

yes, i cropped my images and labels were not modified.
Still, Nan is not going away even with so many tweeks

from tensorflow-yolov3.

@rainley123 . So how did you solved this?

Just add a code to judge if the croped_xmin is equal to the croped_xmax, is they are the same, remove the label and box, because this object will not be in the picture after crop.
the code is like this:

if the object is not in the dist_box, just remove it

mask = tf.logical_not(tf.logical_or(tf.equal(croped_xmin, croped_xmax), tf.equal(croped_ymin, croped_ymax)))        
croped_xmin = tf.boolean_mask(croped_xmin, mask)
croped_ymin = tf.boolean_mask(croped_ymin, mask)
croped_xmax = tf.boolean_mask(croped_xmax, mask)
croped_ymax = tf.boolean_mask(croped_ymax, mask)
labels = tf.boolean_mask(labels, mask) 

请问这段代码添加在哪里

from tensorflow-yolov3.