carpedm20 / carpedm20/DCGAN-tensorflow
train model and test model also encounter the problem free(): invalid next size
- Dominant language
- JavaScript
- Stars
- 7.2k
- Forks
- 2.6k
- PR merge metrics
- No merged PRs in 30d
Description
Hi,
when I input `python main.py --dataset mnist --input_height=28 --output_height=28 --c_dim=1 --is_train`
it can run until epoch[24] and then it output:Error in python': free(): invalid next size (normal): 0x00000000011c5c10
when I input `python main.py --dataset mnist --input_height=28 --output_height=28 --c_dim=1`
it cannot run and output: Error in python': free(): invalid next size (normal): 0x00000000011c5c10
Could anyone help me?
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reproducing the reported failure with the two `python main.py` commands for MNIST, comparing training and test-mode behavior and the crash around epoch 24. Inspect `main.py` and the TensorFlow execution path to determine the source of the `free(): invalid next size` error; done means the commands run without the reported memory error and the relevant behavior is covered by a regression check.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, tensorflow
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100