我在stylegan上训练了我的模型，并建立了一个pkl文件。 现在我正在尝试测试以查看重量的结果 我训练了模型并尝试通过运行pretrianed_example.py文件进行验证 但显示错误
这是我的pretrained_example.py脚本
import os
import pickle
import numpy as np
import PIL.Image
import dnnlib
import dnnlib.tflib as tflib
import config
import tensorflow as tf
def main():
# Initialize TensorFlow.
tflib.init_tf()
# Load pre-trained network.
# To this
url = os.path.abspath("results/00008-sgan-custom_dataset-1gpu/network-snapshot-009748.pkl")
with open(url, 'rb') as f:
_G, _D, Gs = pickle.load(f)
# _G = Instantaneous snapshot of the generator. Mainly useful for resuming a previous training run.
# _D = Instantaneous snapshot of the discriminator. Mainly useful for resuming a previous training run.
# Gs = Long-term average of the generator. Yields higher-quality results than the instantaneous snapshot.
# Print network details.
Gs.print_layers()
# Pick latent vector.
for x in range(0, 100):
# Pick latent vector.
rnd = np.random.RandomState(x)
latents = rnd.randn(1, Gs.input_shape[1])
fmt = dict(func=tflib.convert_images_to_uint8, nchw_to_nhwc=True)
images = Gs.run(latents, None, truncation_psi=0.7, randomize_noise=True, output_transform=fmt)
os.makedirs(config.result_dir, exist_ok=True)
png_filename = os.path.join(config.result_dir + '/finished', 'example' + str(x) + '.png')
PIL.Image.fromarray(images[1], 'RGB').save(png_filename)
if __name__ == "__main__":
main()
这是错误：
---------------------------------------------------------------------------
ResourceExhaustedError Traceback (most recent call last)
C:\ProgramData\Anaconda3\envs\old_tensorflow\lib\site-packages\tensorflow\python\client\session.py in _do_call(self, fn, *args)
1355 try:
-> 1356 return fn(*args)
1357 except errors.OpError as e:
C:\ProgramData\Anaconda3\envs\old_tensorflow\lib\site-packages\tensorflow\python\client\session.py in _run_fn(feed_dict, fetch_list, target_list, options, run_metadata)
1340 return self._call_tf_sessionrun(
-> 1341 options, feed_dict, fetch_list, target_list, run_metadata)
1342
C:\ProgramData\Anaconda3\envs\old_tensorflow\lib\site-packages\tensorflow\python\client\session.py in _call_tf_sessionrun(self, options, feed_dict, fetch_list, target_list, run_metadata)
1428 self._session, options, feed_dict, fetch_list, target_list,
-> 1429 run_metadata)
1430
ResourceExhaustedError: OOM when allocating tensor with shape[3,3,512,512] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[{{node G_synthesis_16/32x32/Conv0_up/weight/Initializer/random_normal/RandomStandardNormal}}]]
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.
During handling of the above exception, another exception occurred:
ResourceExhaustedError Traceback (most recent call last)
<ipython-input-18-cdc9c653bba8> in <module>
28 PIL.Image.fromarray(images[1], 'RGB').save(png_filename)
29 if __name__ == "__main__":
---> 30 main()
<ipython-input-18-cdc9c653bba8> in main()
7 url = os.path.abspath("results/00008-sgan-custom_dataset-1gpu/network-snapshot-009748.pkl")
8 with open(url, 'rb') as f:
----> 9 _G, _D, Gs = pickle.load(f)
10 # _G = Instantaneous snapshot of the generator. Mainly useful for resuming a previous training run.
11 # _D = Instantaneous snapshot of the discriminator. Mainly useful for resuming a previous training run.
~\Documents\python\stylegan\dnnlib\tflib\network.py in __setstate__(self, state)
297 # Init TensorFlow graph.
298 self._init_graph()
--> 299 self.reset_own_vars()
300 tfutil.set_vars({self.find_var(name): value for name, value in state["variables"]})
301
~\Documents\python\stylegan\dnnlib\tflib\network.py in reset_own_vars(self)
188 def reset_own_vars(self) -> None:
189 """Re-initialize all variables of this network, excluding sub-networks."""
--> 190 tfutil.run([var.initializer for var in self.own_vars.values()])
191
192 def reset_vars(self) -> None:
~\Documents\python\stylegan\dnnlib\tflib\tfutil.py in run(*args, **kwargs)
24 """Run the specified ops in the default session."""
25 assert_tf_initialized()
---> 26 return tf.get_default_session().run(*args, **kwargs)
27
28
C:\ProgramData\Anaconda3\envs\old_tensorflow\lib\site-packages\tensorflow\python\client\session.py in run(self, fetches, feed_dict, options, run_metadata)
948 try:
949 result = self._run(None, fetches, feed_dict, options_ptr,
--> 950 run_metadata_ptr)
951 if run_metadata:
952 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
C:\ProgramData\Anaconda3\envs\old_tensorflow\lib\site-packages\tensorflow\python\client\session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
1171 if final_fetches or final_targets or (handle and feed_dict_tensor):
1172 results = self._do_run(handle, final_targets, final_fetches,
-> 1173 feed_dict_tensor, options, run_metadata)
1174 else:
1175 results = []
C:\ProgramData\Anaconda3\envs\old_tensorflow\lib\site-packages\tensorflow\python\client\session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
1348 if handle is None:
1349 return self._do_call(_run_fn, feeds, fetches, targets, options,
-> 1350 run_metadata)
1351 else:
1352 return self._do_call(_prun_fn, handle, feeds, fetches)
C:\ProgramData\Anaconda3\envs\old_tensorflow\lib\site-packages\tensorflow\python\client\session.py in _do_call(self, fn, *args)
1368 pass
1369 message = error_interpolation.interpolate(message, self._graph)
-> 1370 raise type(e)(node_def, op, message)
1371
1372 def _extend_graph(self):
ResourceExhaustedError: OOM when allocating tensor with shape[3,3,512,512] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[node G_synthesis_16/32x32/Conv0_up/weight/Initializer/random_normal/RandomStandardNormal (defined at <string>:149) ]]
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.
您完成了！只需运行“ python pretrained_example.py”，然后查看结果！您应该在结果目录中有一个生成的图像。如果您想生成多个，可以对pretrained_example.py
进行这些更改提前谢谢