六百万迭代加六万素材十六灵石

onion2u

買來試一下

twmsn

遮罩是取自哪個的呢?

啊啊啊打

哈哈哈，没零食啊啊啊啊

Hunbbbb

666 就是灵石不够

谢博为

8bz为啥开了学习率和gan0.1之后就开始报错,我是3070，4bz的话可以开学习率和gan0.1

yangfanxt

谢博为 发表于 2023-2-5 17:27
8bz为啥开了学习率和gan0.1之后就开始报错,我是3070，4bz的话可以开学习率和gan0.1 ...

其他参数呢，我笔记本2070，只有你性能的百分之60都能正常跑呢

Michun

值得，买了试试

jdd9

学习学习学习学习学习学习学习学习

谢博为

yangfanxt 发表于 2023-2-5 18:42
其他参数呢，我笔记本2070，只有你性能的百分之60都能正常跑呢

我可以看看你的参数吗我不是很会设置，我按照这个参数是跑不起来，把学习率和gan0.1都关了可以跑，或者4bz也可以跑
[0] 目标迭代次数
Target iteration :
0
[n] 随机翻转 SRC 面部
Flip SRC faces randomly ( y/n 输入 ? 获取帮助信息 ) :
n
[n] 随机翻转 DST 面部
Flip DST faces randomly ( y/n 输入 ? 获取帮助信息 ) :
n
[4] 批量大小
Batch_size ( 输入 ? 获取帮助信息 ) : 8
8
[y] 遮罩训练
Masked training ( y/n 输入 ? 获取帮助信息 ) :
y
[y] 眼嘴优先
Eyes and mouth priority ( y/n 输入 ? 获取帮助信息 ) :
y
[y] 侧脸优化
Uniform yaw distribution of samples ( y/n 输入 ? 获取帮助信息 ) :
y
[n] 遮罩外围模糊
Blur out mask ( y/n 输入 ? 获取帮助信息 ) :
n
[y] 模型和优化器运行在GPU上
Place models and optimizer on GPU ( y/n 输入 ? 获取帮助信息 ) :
y
[y] 启用 AdaBelief 优化器?
Use AdaBelief optimizer? ( y/n 输入 ? 获取帮助信息 ) :
y
[y] 启用学习率下降
Use learning rate dropout ( n/y/cpu 输入 ? 获取帮助信息 ) :
y
[n] 启用样本随机扭曲
Enable random warp of samples ( y/n 输入 ? 获取帮助信息 ) :
n
[0.0] 随机色调/饱和度/光照强度
Random hue/saturation/light intensity ( 0.0 .. 0.3 输入 ? 获取帮助信息 ) :
0.0
[0.1] GAN 强度
GAN power ( 0.0 .. 5.0 输入 ? 获取帮助信息 ) :
0.1
[32] GAN 补丁大小
GAN patch size ( 3-640 输入 ? 获取帮助信息 ) :
32
[16] GAN 维度
GAN dimensions ( 4-512 输入 ? 获取帮助信息 ) :
16
[0.01] 真脸强度
'True face' power. ( 0.0000 .. 1.0 输入 ? 获取帮助信息 ) :
0.01
[0.0] 面部风格强度
Face style power ( 0.0..100.0 输入 ? 获取帮助信息 ) :
0.0
[0.0] 背景风格强度
Background style power ( 0.0..100.0 输入 ? 获取帮助信息 ) :
0.0
[rct] SRC 色彩转换模式
Color transfer for src faceset ( none/rct/lct/mkl/idt/sot 输入 ? 获取帮助信息 ) :
rct
[y] 启用梯度剪裁
Enable gradient clipping ( y/n 输入 ? 获取帮助信息 ) :
y
[n] 启用预训练
Enable pretraining mode ( y/n 输入 ? 获取帮助信息 ) :

谢博为

yangfanxt 发表于 2023-2-5 18:42
其他参数呢，我笔记本2070，只有你性能的百分之60都能正常跑呢

这是报错的内容
Error: 2 root error(s) found.
  (0) Resource exhausted: failed to allocate memory
         [[node Square_15 (defined at C:\DFL_RTX3000_series_1120\_internal\DFL\core\leras\ops\__init__.py:304) ]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.

         [[concat_12/concat/_1617]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.

  (1) Resource exhausted: failed to allocate memory
         [[node Square_15 (defined at C:\DFL_RTX3000_series_1120\_internal\DFL\core\leras\ops\__init__.py:304) ]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.

0 successful operations.
0 derived errors ignored.

Errors may have originated from an input operation.
Input Source operations connected to node Square_15:
mul_10 (defined at C:\DFL_RTX3000_series_1120\_internal\DFL\models\Model_SAEHD\Model.py:456)

Input Source operations connected to node Square_15:
mul_10 (defined at C:\DFL_RTX3000_series_1120\_internal\DFL\models\Model_SAEHD\Model.py:456)

Original stack trace for 'Square_15':
  File "threading.py", line 884, in _bootstrap
  File "threading.py", line 916, in _bootstrap_inner
  File "threading.py", line 864, in run
  File "C:\DFL_RTX3000_series_1120\_internal\DFL\mainscripts\Trainer.py", line 58, in trainerThread
    debug=debug)
  File "C:\DFL_RTX3000_series_1120\_internal\DFL\models\ModelBase.py", line 193, in __init__
    self.on_initialize()
  File "C:\DFL_RTX3000_series_1120\_internal\DFL\models\Model_SAEHD\Model.py", line 485, in on_initialize
    gpu_dst_loss = tf.reduce_mean ( 5*nn.dssim(gpu_target_dst_masked_opt, gpu_pred_dst_dst_masked_opt, max_val=1.0, filter_size=int(resolution/11.6) ), axis=[1])
  File "C:\DFL_RTX3000_series_1120\_internal\DFL\core\leras\ops\__init__.py", line 304, in dssim
    den1 = reducer(tf.square(img1) + tf.square(img2))
  File "C:\DFL_RTX3000_series_1120\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\gen_math_ops.py", line 10438, in square
    "Square", x=x, name=name)
  File "C:\DFL_RTX3000_series_1120\_internal\python-3.6.8\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 750, in _apply_op_helper
    attrs=attr_protos, op_def=op_def)
  File "C:\DFL_RTX3000_series_1120\_internal\python-3.6.8\lib\site-packages\tensorflow\python\framework\ops.py", line 3569, in _create_op_internal
    op_def=op_def)
  File "C:\DFL_RTX3000_series_1120\_internal\python-3.6.8\lib\site-packages\tensorflow\python\framework\ops.py", line 2045, in __init__
    self._traceback = tf_stack.extract_stack_for_node(self._c_op)

Traceback (most recent call last):
  File "C:\DFL_RTX3000_series_1120\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1375, in _do_call
    return fn(*args)
  File "C:\DFL_RTX3000_series_1120\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1360, in _run_fn
    target_list, run_metadata)
  File "C:\DFL_RTX3000_series_1120\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1453, in _call_tf_sessionrun
    run_metadata)
tensorflow.python.framework.errors_impl.ResourceExhaustedError: 2 root error(s) found.
  (0) Resource exhausted: failed to allocate memory
         [[{{node Square_15}}]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.

         [[concat_12/concat/_1617]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.

  (1) Resource exhausted: failed to allocate memory
         [[{{node Square_15}}]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.

0 successful operations.
0 derived errors ignored.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\DFL_RTX3000_series_1120\_internal\DFL\mainscripts\Trainer.py", line 129, in trainerThread
    iter, iter_time = model.train_one_iter()
  File "C:\DFL_RTX3000_series_1120\_internal\DFL\models\ModelBase.py", line 474, in train_one_iter
    losses = self.onTrainOneIter()
  File "C:\DFL_RTX3000_series_1120\_internal\DFL\models\Model_SAEHD\Model.py", line 774, in onTrainOneIter
    src_loss, dst_loss = self.src_dst_train (warped_src, target_src, target_srcm, target_srcm_em, warped_dst, target_dst, target_dstm, target_dstm_em)
  File "C:\DFL_RTX3000_series_1120\_internal\DFL\models\Model_SAEHD\Model.py", line 584, in src_dst_train
    self.target_dstm_em:target_dstm_em,
  File "C:\DFL_RTX3000_series_1120\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 968, in run
    run_metadata_ptr)
  File "C:\DFL_RTX3000_series_1120\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1191, in _run
    feed_dict_tensor, options, run_metadata)
  File "C:\DFL_RTX3000_series_1120\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1369, in _do_run
    run_metadata)
  File "C:\DFL_RTX3000_series_1120\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1394, in _do_call
    raise type(e)(node_def, op, message)  # pylint: disable=no-value-for-parameter
tensorflow.python.framework.errors_impl.ResourceExhaustedError: 2 root error(s) found.
  (0) Resource exhausted: failed to allocate memory
         [[node Square_15 (defined at C:\DFL_RTX3000_series_1120\_internal\DFL\core\leras\ops\__init__.py:304) ]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.

         [[concat_12/concat/_1617]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.

  (1) Resource exhausted: failed to allocate memory
         [[node Square_15 (defined at C:\DFL_RTX3000_series_1120\_internal\DFL\core\leras\ops\__init__.py:304) ]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.

0 successful operations.
0 derived errors ignored.

Errors may have originated from an input operation.
Input Source operations connected to node Square_15:
mul_10 (defined at C:\DFL_RTX3000_series_1120\_internal\DFL\models\Model_SAEHD\Model.py:456)

Input Source operations connected to node Square_15:
mul_10 (defined at C:\DFL_RTX3000_series_1120\_internal\DFL\models\Model_SAEHD\Model.py:456)

Original stack trace for 'Square_15':
  File "threading.py", line 884, in _bootstrap
  File "threading.py", line 916, in _bootstrap_inner
  File "threading.py", line 864, in run
  File "C:\DFL_RTX3000_series_1120\_internal\DFL\mainscripts\Trainer.py", line 58, in trainerThread
    debug=debug)
  File "C:\DFL_RTX3000_series_1120\_internal\DFL\models\ModelBase.py", line 193, in __init__
    self.on_initialize()
  File "C:\DFL_RTX3000_series_1120\_internal\DFL\models\Model_SAEHD\Model.py", line 485, in on_initialize
    gpu_dst_loss = tf.reduce_mean ( 5*nn.dssim(gpu_target_dst_masked_opt, gpu_pred_dst_dst_masked_opt, max_val=1.0, filter_size=int(resolution/11.6) ), axis=[1])
  File "C:\DFL_RTX3000_series_1120\_internal\DFL\core\leras\ops\__init__.py", line 304, in dssim
    den1 = reducer(tf.square(img1) + tf.square(img2))
  File "C:\DFL_RTX3000_series_1120\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\gen_math_ops.py", line 10438, in square
    "Square", x=x, name=name)
  File "C:\DFL_RTX3000_series_1120\_internal\python-3.6.8\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 750, in _apply_op_helper
    attrs=attr_protos, op_def=op_def)
  File "C:\DFL_RTX3000_series_1120\_internal\python-3.6.8\lib\site-packages\tensorflow\python\framework\ops.py", line 3569, in _create_op_internal
    op_def=op_def)
  File "C:\DFL_RTX3000_series_1120\_internal\python-3.6.8\lib\site-packages\tensorflow\python\framework\ops.py", line 2045, in __init__
    self._traceback = tf_stack.extract_stack_for_node(self._c_op)