fix typo

open-mmlab · nbei · Oct 16, 2021 · Oct 15, 2021 · Oct 15, 2021 · Oct 16, 2021
commit c53cc39dc209af1ce07926857da6471193151ee0
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -37,4 +37,4 @@ repos:
     rev: v2.1.0
     hooks:
       - id: codespell
-        args: ["--skip", "*.ipynb,tools/data/hvu/label_map.json", "-L", "formating,te,nd,thre,Gool,gool"]
+        args: ["--skip", "*.ipynb,tools/data/hvu/label_map.json", "-L", "formating,te,nd,thre,Gool,gool,lod"]
diff --git a/apps/conditional_interpolate.py b/apps/conditional_interpolate.py
@@ -44,7 +44,7 @@ def parse_args():
     parser.add_argument(
         '--fix-z',
         action='store_true',
-        help='whether to fix the noise for conditonal model')
+        help='whether to fix the noise for conditional model')
     parser.add_argument(
         '--fix-y',
         action='store_true',

diff --git a/configs/_base_/datasets/imagenet_noaug_128.py b/configs/_base_/datasets/imagenet_noaug_128.py
@@ -4,7 +4,7 @@
 # different from mmcls, we adopt the setting used in BigGAN.
 # Importantly, the `to_rgb` is set to `False` to remain image orders as BGR.
 # Remove `RandomFlip` augmentation and change `RandomCropLongEdge` to
-# `CenterCropLongEdge` to elminate randomness.
+# `CenterCropLongEdge` to elminiate randomness.
 img_norm_cfg = dict(
     mean=[127.5, 127.5, 127.5], std=[127.5, 127.5, 127.5], to_rgb=False)
 train_pipeline = [

diff --git a/configs/_base_/datasets/imagenet_noaug_256.py b/configs/_base_/datasets/imagenet_noaug_256.py
@@ -4,7 +4,7 @@
 # different from mmcls, we adopt the setting used in BigGAN.
 # Importantly, the `to_rgb` is set to `False` to remain image orders as BGR.
 # Remove `RandomFlip` augmentation and change `RandomCropLongEdge` to
-# `CenterCropLongEdge` to elminate randomness.
+# `CenterCropLongEdge` to elminiate randomness.
 img_norm_cfg = dict(
     mean=[127.5, 127.5, 127.5], std=[127.5, 127.5, 127.5], to_rgb=False)
 train_pipeline = [

diff --git a/configs/biggan/README.md b/configs/biggan/README.md
@@ -36,7 +36,7 @@ Evaluation of our trained BIgGAN.
 Note: This is an unfinished version (1150k iter) of BigGAN trained on `ImageNet1k`. The model with the best performance is still on the way.
 
 ## Converted weights
-Since we havn't finished training our models, we provide you with several pre-trained weights which have been evaluated. Here, we refer to [BigGAN-PyTorch](https://github.com/ajbrock/BigGAN-PyTorch) and [pytorch-pretrained-BigGAN](https://github.com/huggingface/pytorch-pretrained-BigGAN).
+Since we haven't finished training our models, we provide you with several pre-trained weights which have been evaluated. Here, we refer to [BigGAN-PyTorch](https://github.com/ajbrock/BigGAN-PyTorch) and [pytorch-pretrained-BigGAN](https://github.com/huggingface/pytorch-pretrained-BigGAN).
 
 Evaluation results and download links are provided below.
 

diff --git a/configs/sngan_proj/README.md b/configs/sngan_proj/README.md
@@ -25,8 +25,8 @@
 | sngan_proj_32  | CIFAR10  |      w       |     5     |    500000     |            [9.5564 (490000)](https://download.openmmlab.com/mmgen/sngan_proj/sngan_proj_cifar10_32_lr-2e-4_b64x1_wReLUinplace_is-iter490000_20210709_202230-cd863c74.pth)            |            [8.3462 (490000)](https://download.openmmlab.com/mmgen/sngan_proj/sngan_proj_cifar10_32_lr-2e-4-b64x1_wReLUinplace_fid-iter490000_20210709_203038-191b2648.pth)            |         [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/sngan_proj/sngan_proj_32_wReLUinplace_lr-2e-4_ndisc5_cifar10_b64x1.py)         |           [Log](https://download.openmmlab.com/mmgen/sngan_proj/sngan_proj_cifar10_32_lr-2e-4_b64x1_wReLUinplace_20210624_063454_is-cd863c74_fid-191b2648.json)            |
 | sngan_proj_128 | ImageNet |     w/o      |     5     |    1000000    | [30.0651 (952000)](https://download.openmmlab.com/mmgen/sngan_proj/sngan_proj_imagenet1k_128_Glr2e-4_Dlr5e-5_ndisc5_b128x2_woReLUinplace_is-iter952000_20210730_132027-9c884a21.pth) | [32.6193 (988000)](https://download.openmmlab.com/mmgen/sngan_proj/sngan_proj_imagenet1k_128_Glr2e-4_Dlr5e-5_ndisc5_b128x2_woReLUinplace_fid-iter988000_20210730_131424-061bf803.pth) | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/sngan_proj/sngan_proj_128_woReLUinplace_Glr-2e-4_Dlr-5e-5_ndisc5_imagenet1k_b128x2.py) | [Log](https://download.openmmlab.com/mmgen/sngan_proj/sngan_proj_imagenet1k_128_Glr2e-4_Dlr5e-5_ndisc5_b128x2_woReLUinplace_20210730_131424_fid-061bf803_is-9c884a21.json) |
 | sngan_proj_128 | ImageNet |      w       |     5     |    1000000    | [28.1799 (944000)](https://download.openmmlab.com/mmgen/sngan_proj/sngan_proj_imagenet1k_128_Glr2e-4_Dlr5e-5_ndisc5_b128x2_wReLUinplace_is-iter944000_20210730_132714-ca0ccd07.pth)  | [33.4821 (988000)](https://download.openmmlab.com/mmgen/sngan_proj/sngan_proj_imagenet1k_128_Glr2e-4_Dlr5e-5_ndisc5_b128x2_wReLUinplace_fid-iter988000_20210730_132401-9a682411.pth)  | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/sngan_proj/sngan_proj_128_wReLUinplace_Glr-2e-4_Dlr-5e-5_ndisc5_imagenet1k_b128x2.py)  | [Log](https://download.openmmlab.com/mmgen/sngan_proj/sngan_proj_imagenet1k_128_Glr2e-4_Dlr5e-5_ndisc5_b128x2_wReLUinplace_20210730_132401_fid-9a682411_is-ca0ccd07.json)  |
-| sngan_proj_128 | ImageNet |     w/o      |     2     |    2000000    |                                                                                     Coming soon                                                                                      |                                                                                     Comming soon                                                                                      |                                                                          Comming Soon                                                                          |                                                                                Comming Soon                                                                                |
-| sngan_proj_128 | ImageNet |      w       |     2     |    2000000    |                                                                                     Coming soon                                                                                      |                                                                                     Comming soon                                                                                      |                                                                          Comming Soon                                                                          |                                                                                Comming Soon                                                                                |
+| sngan_proj_128 | ImageNet |     w/o      |     2     |    2000000    |                                                                                     Coming soon                                                                                      |                                                                                     Coming soon                                                                                      |                                                                          Coming Soon                                                                          |                                                                                Coming Soon                                                                                |
+| sngan_proj_128 | ImageNet |      w       |     2     |    2000000    |                                                                                     Coming soon                                                                                      |                                                                                     Coming soon                                                                                      |                                                                          Coming Soon                                                                          |                                                                                Coming Soon                                                                                |
 
 '\*' Iteration counting rule in our implementation is different from others. If you want to align with other codebases, you can use the following conversion formula:
 ```

diff --git a/configs/styleganv2/README.md b/configs/styleganv2/README.md
@@ -65,7 +65,7 @@ bash tools/dist_train.sh \
   --work-dir ./work_dirs/quick-test
 ```
 
-With a simliar way, users can switch to [config for partial-GD](https://github.com/open-mmlab/mmgeneration/tree/master/configs/styleganv2/stylegan2_c2_fp16_quicktest_ffhq_256_b4x8_800k.py) and [config for globalG-partialD](https://github.com/open-mmlab/mmgeneration/tree/master/configs/styleganv2/stylegan2_c2_fp16-globalG-partialD_PL-R1-no-scaler_ffhq_256_b4x8_800k.py) to test the other two mixed precision training configuration.
+With a similar way, users can switch to [config for partial-GD](https://github.com/open-mmlab/mmgeneration/tree/master/configs/styleganv2/stylegan2_c2_fp16_quicktest_ffhq_256_b4x8_800k.py) and [config for globalG-partialD](https://github.com/open-mmlab/mmgeneration/tree/master/configs/styleganv2/stylegan2_c2_fp16-globalG-partialD_PL-R1-no-scaler_ffhq_256_b4x8_800k.py) to test the other two mixed precision training configuration.
 
 
 *Note that to use the [APEX](https://github.com/NVIDIA/apex) toolkit, you have to installed it following the official guidance. (APEX is not included in our requirements.) If you are using GPUs without tensor core, you would better to switch to the newer PyTorch version (>= 1.7,0). Otherwise, the APEX installation or running may meet several bugs.*

diff --git a/docs/quick_run.md b/docs/quick_run.md
@@ -53,7 +53,7 @@ from mmgen.apis import init_model, sample_img2img_model
 config_file = 'configs/pix2pix/pix2pix_vanilla_unet_bn_wo_jitter_flip_1x4_186840_edges2shoes.py'
 # you can download this checkpoint in advance and use a local file path.
 checkpoint_file = 'https://download.openmmlab.com/mmgen/pix2pix/pix2pix_vanilla_unet_bn_wo_jitter_flip_1x4_186840_edges2shoes_convert-bgr_20210410_174116-aaaa3687.pth'
-# Specify the path to image you want to transalte
+# Specify the path to image you want to translate
 image_path = 'tests/data/paired/test/33_AB.jpg'
 device = 'cuda:0'
 # init a generatvie
@@ -174,7 +174,7 @@ Then, users can use the evaluation script with the following command:
 ```shell
 bash eval.sh ${CONFIG_FILE} ${CKPT_FILE} --batch-size 10 --online
 ```
-If you are in slurm enviroment, please switch to the [tools/slurm_eval.sh](https://github.com/open-mmlab/mmgeneration/tree/master/tools/slurm_eval.sh) by using the following commands:
+If you are in slurm environment, please switch to the [tools/slurm_eval.sh](https://github.com/open-mmlab/mmgeneration/tree/master/tools/slurm_eval.sh) by using the following commands:
 
 ```shell
 bash slurm_eval.sh ${PLATFORM} ${JOBNAME} ${CONFIG_FILE} ${CONFIG_FILE} \
@@ -269,7 +269,7 @@ To be noted that, the selection of Inception V3 and image resize method can sign
 
 We also perform a survey on the influence of data loading pipeline and the version of pretrained Inception V3 on the IS result. All IS are evaluated on the same group of images which are randomly selected from the ImageNet dataset.
 
-<details> <summary> Show the Comparsion Results </summary>
+<details> <summary> Show the Comparison Results </summary>
 
 | Code Base | Inception V3 Version | Data Loader Backend | Resize Interpolation Method | IS |
 | -- | -- | -- | -- | -- |
@@ -357,7 +357,7 @@ In this section, we will discuss how to evaluate the generative models, especial
 In [eval_hooks.py](https://github.com/open-mmlab/mmgeneration/blob/master/mmgen/core/evaluation/eval_hooks.py), `GenerativeEvalHook` is provided to evaluate generative models duiring training. The most important argument for this hook is `metrics`. In fact, users can directly copy the configs in the last section to define the evaluation metric. To evaluate the model with `FID` metric, please add the following python codes in your config file:
 
 ```python
-# define the evaluation keywords, otherwise evalution will not be
+# define the evaluation keywords, otherwise evaluation will not be
 # added in training
 evaluation = dict(
     type='GenerativeEvalHook',

diff --git a/docs/tutorials/config.md b/docs/tutorials/config.md
@@ -91,7 +91,7 @@ custom_hooks = [  # add customized hooks for training
 
 metrics = dict(  # metrics we used to test this model
     fid50k=dict(
-        inception_pkl='work_dirs/inception_pkl/ffhq-256-50k-rgb.pkl',  # provdie the inception pkl for FID
+        inception_pkl='work_dirs/inception_pkl/ffhq-256-50k-rgb.pkl',  # provide the inception pkl for FID
         bgr2rgb=True))  # change the order of the image channel when extracting inception features
 
 checkpoint_config = dict(interval=10000, by_epoch=False, max_keep_ckpts=30)  # define checkpoint hook

diff --git a/docs/tutorials/inception_stat.md b/docs/tutorials/inception_stat.md
@@ -45,7 +45,7 @@ If `${FLIP}` is set as `True`, the following config of horizontal flip operation
 dict(type='Flip', keys=['real_img'], direction='horizontal')
 ```
 
-If you want to use a specific pipeline otherwise the pre-defiend ones, you can use `--pipeline-cfg` to pass a config file contains the data pipeline you want to use.
+If you want to use a specific pipeline otherwise the pre-defined ones, you can use `--pipeline-cfg` to pass a config file contains the data pipeline you want to use.
 ```shell
 python tools/utils/inception_stat.py --imgsdir ${IMGS_PATH} --pklname ${PKLNAME} --pipeline-cfg ${PIPELINE}
 ```

diff --git a/mmgen/apis/inference.py b/mmgen/apis/inference.py
@@ -67,7 +67,7 @@ def sample_uncoditional_model(model,
     """
     # set eval mode
     model.eval()
-    # constrcut sampling list for batches
+    # construct sampling list for batches
     n_repeat = num_samples // num_batches
     batches_list = [num_batches] * n_repeat
 
@@ -111,7 +111,7 @@ def sample_conditional_model(model,
     """
     # set eval mode
     model.eval()
-    # constrcut sampling list for batches
+    # construct sampling list for batches
     n_repeat = num_samples // num_batches
     batches_list = [num_batches] * n_repeat
 

diff --git a/mmgen/apis/train.py b/mmgen/apis/train.py
@@ -19,7 +19,7 @@
 def set_random_seed(seed, deterministic=False, use_rank_shift=True):
     """Set random seed.
 
-    In this function, we just modify the default behavior of the simliar
+    In this function, we just modify the default behavior of the similar
     function defined in MMCV.
 
     Args:

diff --git a/mmgen/core/evaluation/eval_hooks.py b/mmgen/core/evaluation/eval_hooks.py
@@ -23,7 +23,7 @@ class GenerativeEvalHook(Hook):
     the evaluation during the training procedure.
 
     In our config system, you only need to add `evaluation` with the detailed
-    configureations. Below is serveral usage cases for different situations.
+    configureations. Below is several usage cases for different situations.
     What you need to do is to add these lines at the end of your config file.
     Then, you can use this evaluation hook in the training procedure.
 
@@ -48,7 +48,7 @@ class GenerativeEvalHook(Hook):
                 bgr2rgb=True),
             sample_kwargs=dict(sample_model='ema'))
 
-    #. Use FID and IS simutaneously and save the best checkpoints respectively
+    #. Use FID and IS simultaneously and save the best checkpoints respectively
 
     .. code-block:: python
         :linenos:
@@ -153,7 +153,7 @@ def __init__(self,
                 former, latter = self.milestones[idx], self.milestones[idx + 1]
                 if former >= latter:
                     raise ValueError(
-                        'Elements in `milestones` shoule in ascending order.')
+                        'Elements in `milestones` should in ascending order.')
         else:
             raise TypeError('`interval` only support `int` or `dict`,'
                             f'recieve {type(self.interval)} instead.')

diff --git a/mmgen/core/evaluation/evaluation.py b/mmgen/core/evaluation/evaluation.py
@@ -237,7 +237,7 @@ def single_gpu_online_evaluation(model, data_loader, metrics, logger,
     # generated in a metric-special way and not shared between different
     # metrics.
     # For reconstruction metrics like 'GaussianKLD', they do not
-    # receive images but receive a dict with cooresponding probabilistic
+    # receive images but receive a dict with corresponding probabilistic
     # parameter.
 
     special_metrics = []

diff --git a/mmgen/core/evaluation/metric_utils.py b/mmgen/core/evaluation/metric_utils.py
@@ -92,7 +92,7 @@ def _hox_downsample(img):
 
 
 def _f_special_gauss(size, sigma):
-    r"""Return a circularly symmetric gaussian kernel.
+    r"""Return a circular symmetric gaussian kernel.
 
     Ref: https://github.com/tkarras/progressive_growing_of_gans/blob/master/metrics/ms_ssim.py  # noqa
 

diff --git a/mmgen/core/evaluation/metrics.py b/mmgen/core/evaluation/metrics.py
@@ -363,8 +363,8 @@ def __init__(self, num_images, image_shape=None):
         self.image_shape = image_shape
         self.num_real_need = num_images
         self.num_fake_need = num_images
-        self.num_real_feeded = 0  # record of the feeded real images
-        self.num_fake_feeded = 0  # record of the feeded fake images
+        self.num_real_feeded = 0  # record of the fed real images
+        self.num_fake_feeded = 0  # record of the fed fake images
         self._result_str = None  # string of metric result
 
     @property
@@ -385,7 +385,7 @@ def feed(self, batch, mode):
         operation in 'feed_op' function.
 
         Args:
-            batch (Tensor | dict): Images or dict to be feeded into
+            batch (Tensor | dict): Images or dict to be fed into
                 metric object. If ``Tensor`` is passed, the order of ``Tensor``
                 should be "NCHW". If ``dict`` is passed, each term in the
                 ``dict`` are ``Tensor`` with order "NCHW".
@@ -736,6 +736,7 @@ def feed_op(self, minibatch, mode):
         if mode == 'reals':
             real_pyramid = laplacian_pyramid(minibatch, self.n_pyramids - 1,
                                              self.gaussian_k)
+            # lod: layer_of_descriptors
             for lod, level in enumerate(real_pyramid):
                 desc = get_descriptors_for_minibatch(level, self.nhood_size,
                                                      self.nhoods_per_image)
@@ -960,7 +961,7 @@ def extract_features(self, images):
 class IS(Metric):
     """IS (Inception Score) metric.
 
-    The images are splitted into groups, and the inception score is calculated
+    The images are split into groups, and the inception score is calculated
     on each group of images, then the mean and standard deviation of the score
     is reported. The calculation of the inception score on a group of images
     involves first using the inception v3 model to calculate the conditional
@@ -1034,7 +1035,7 @@ def __init__(self,
 
     def pil_resize(self, x):
         """Apply Bicubic interpolation with Pillow backend. Before and after
-        interpolation operation, we have to perform a type convertion beteen
+        interpolation operation, we have to perform a type conversion between
         torch.tensor and PIL.Image, and these operations make resize process a
         bit slow.
 

diff --git a/mmgen/core/hooks/ceph_hooks.py b/mmgen/core/hooks/ceph_hooks.py
@@ -9,7 +9,7 @@
 class PetrelUploadHook(Hook):
     """Upload Data with Petrel.
 
-    With this hook, users can easily upload datas to the cloud server for
+    With this hook, users can easily upload data to the cloud server for
     saving local spaces. Please read the notes below for using this hook,
     especially for the declaration of ``petrel``.
 

diff --git a/mmgen/datasets/builder.py b/mmgen/datasets/builder.py
@@ -35,7 +35,7 @@ def build_dataset(cfg, default_args=None):
             Defaults to None.
 
     Returns:
-        Objet: Dataset for sampling data batch.
+        Object: Dataset for sampling data batch.
     """
     from .dataset_wrappers import RepeatDataset
     if isinstance(cfg, (list, tuple)):

diff --git a/mmgen/models/architectures/fid_inception.py b/mmgen/models/architectures/fid_inception.py
@@ -196,7 +196,7 @@ def forward(self, x):
             x (torch.Tensor): Input tensor of shape BxCxHxW.
 
         Returns:
-            torch.Tensor: Feature Maps of x outputed by this block.
+            torch.Tensor: Feature Maps of x outputted by this block.
         """
         branch1x1 = self.branch1x1(x)
 
@@ -230,7 +230,7 @@ def forward(self, x):
             x (torch.Tensor): Input tensor of shape BxCxHxW.
 
         Returns:
-            torch.Tensor: Feature Maps of x outputed by this block.
+            torch.Tensor: Feature Maps of x outputted by this block.
         """
         branch1x1 = self.branch1x1(x)
 
@@ -267,7 +267,7 @@ def forward(self, x):
             x (torch.Tensor): Input tensor of shape BxCxHxW.
 
         Returns:
-            torch.Tensor: Feature Maps of x outputed by this block.
+            torch.Tensor: Feature Maps of x outputted by this block.
         """
         branch1x1 = self.branch1x1(x)
 
@@ -309,7 +309,7 @@ def forward(self, x):
             x (torch.Tensor): Input tensor of shape BxCxHxW.
 
         Returns:
-            torch.Tensor: Feature Maps of x outputed by this block.
+            torch.Tensor: Feature Maps of x outputted by this block.
         """
         branch1x1 = self.branch1x1(x)