Spaces:
Running
on
Zero
Running
on
Zero
File size: 2,674 Bytes
a49cc2f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 |
# coding=utf-8
# Copyright 2024 HuggingFace Inc.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import unittest
from diffusers import AutoencoderDC
from diffusers.utils.testing_utils import (
enable_full_determinism,
floats_tensor,
torch_device,
)
from ..test_modeling_common import ModelTesterMixin, UNetTesterMixin
enable_full_determinism()
class AutoencoderDCTests(ModelTesterMixin, UNetTesterMixin, unittest.TestCase):
model_class = AutoencoderDC
main_input_name = "sample"
base_precision = 1e-2
def get_autoencoder_dc_config(self):
return {
"in_channels": 3,
"latent_channels": 4,
"attention_head_dim": 2,
"encoder_block_types": (
"ResBlock",
"EfficientViTBlock",
),
"decoder_block_types": (
"ResBlock",
"EfficientViTBlock",
),
"encoder_block_out_channels": (8, 8),
"decoder_block_out_channels": (8, 8),
"encoder_qkv_multiscales": ((), (5,)),
"decoder_qkv_multiscales": ((), (5,)),
"encoder_layers_per_block": (1, 1),
"decoder_layers_per_block": [1, 1],
"downsample_block_type": "conv",
"upsample_block_type": "interpolate",
"decoder_norm_types": "rms_norm",
"decoder_act_fns": "silu",
"scaling_factor": 0.41407,
}
@property
def dummy_input(self):
batch_size = 4
num_channels = 3
sizes = (32, 32)
image = floats_tensor((batch_size, num_channels) + sizes).to(torch_device)
return {"sample": image}
@property
def input_shape(self):
return (3, 32, 32)
@property
def output_shape(self):
return (3, 32, 32)
def prepare_init_args_and_inputs_for_common(self):
init_dict = self.get_autoencoder_dc_config()
inputs_dict = self.dummy_input
return init_dict, inputs_dict
@unittest.skip("AutoencoderDC does not support `norm_num_groups` because it does not use GroupNorm.")
def test_forward_with_norm_groups(self):
pass
|