search

TachibanaYoshino / AnimeGAN

A Tensorflow implementation of AnimeGAN for fast photo animation ! This is the Open source of the paper 「AnimeGAN: a novel lightweight GAN for photo animation」, which uses the GAN framwork to transform real-world photos into anime images.
4.49k stars 660 forks source link

i cant replicate the result with hayao. #2

Closed lorrp1 closed 4 years ago

lorrp1 commented 4 years ago

the result are just like a filtered pic.

i tried both checkpoints:

Haoyao-style.zip

Haoyao-style-initial-checkpoint.zip

lorrp1 commented 4 years ago

WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/tensorflow_core/python/profiler/internal/flops_registry.py:142: tensor_shape_from_node_def_name (from tensorflow.python.framework.graph_util_impl) is deprecated and will be removed in a future version. Instructions for updating: Use tf.compat.v1.graph_util.tensor_shape_from_node_def_name 209 ops no flops stats due to incomplete shapes. Parsing Inputs... Incomplete shape.

lorrp1 commented 4 years ago

sorry i made a mistake.

Johnson-yue commented 4 years ago

@lorrp1 hi, do you replicate the result ?? I can not load AnimeGAN.model-60 weight by tf.train.get_check_state

In my way: download: Haoyao-style.zip and unzip into "checkpoint/" so, the checkpoint folder including:

checkpoint AnimeGAN.model-60.index AnimeGAN.model-60.meta AnimeGAN.model-60.data-00000-of-00001

and using test scripts: python test.py --checkpoint_dir checkpoint/AnimeGAN.model-60 --test_dir dataset/test/real --style_name H

but it failed ckpt is None by tf.train.get_check_state(checkpoint/AnimeGAN.model-60)

lorrp1 commented 4 years ago

yeah.

but results are not that good when i try to process low-quality images