v1.0

VITA/util/s2wrapper/core.py

+#  ------------------------------------------------------------------------------------------
+#  Copyright (c) 2024 Baifeng Shi.
+#  All rights reserved.
+#
+#  Licensed under the MIT License (MIT). See LICENSE in the repo root for license information.
+#  ------------------------------------------------------------------------------------------
+
+import math
+
+import torch
+import torch.nn.functional as F
+from einops import rearrange
+
+from .utils import batched_forward, merge_chessboard, split_chessboard
+
+
+def forward(
+    model,
+    input,
+    scales=None,
+    img_sizes=None,
+    max_split_size=None,
+    resize_output_to_idx=0,
+    num_prefix_token=0,
+    output_shape="bnc",
+    split_forward=False,
+):
+
+    assert input.dim() == 4, "Input image must be in the shape of BxCxHxW."
+    assert input.shape[2] == input.shape[3], "Currently only square images are supported."
+    assert output_shape in [
+        "bnc",
+        "bchw",
+    ], "Output shape should be either BxNxC (e.g., ViT) or BxCxHxW (e.g., ConvNet)."
+    assert (
+        output_shape == "bnc" or num_prefix_token == 0
+    ), "For ConvNet there shouldn't be any prefix token."
+
+    b, c, input_size, _ = input.shape
+
+    # image size for each scale
+    assert scales is not None or img_sizes is not None, "Please assign either scales or img_sizes."
+    img_sizes = img_sizes or [int(input_size * scale) for scale in scales]
+
+    # prepare multiscale inputs
+    max_split_size = (
+        max_split_size or input_size
+    )  # The maximum size of each split of image. Set as the input size by default
+    num_splits = [
+        math.ceil(size / max_split_size) for size in img_sizes
+    ]  # number of splits each scale
+    input_multiscale = []
+    for size, num_split in zip(img_sizes, num_splits):
+        x = F.interpolate(input.to(torch.float32), size=size, mode="bicubic").to(input.dtype)
+        x = split_chessboard(x, num_split=num_split)
+        input_multiscale.append(x)
+
+    # run feedforward on each scale
+    outs_multiscale = [
+        batched_forward(model, x, b) if split_forward else model(x) for x in input_multiscale
+    ]
+    if num_prefix_token > 0:
+        outs_prefix_multiscale = [out[:, :num_prefix_token] for out in outs_multiscale]
+        outs_multiscale = [out[:, num_prefix_token:] for out in outs_multiscale]
+    if output_shape == "bnc":
+        outs_multiscale = [
+            rearrange(
+                out, "b (h w) c -> b c h w", h=int(out.shape[1] ** 0.5), w=int(out.shape[1] ** 0.5)
+            )
+            for out in outs_multiscale
+        ]
+
+    # merge outputs of different splits for each scale separately
+    outs_multiscale = [
+        merge_chessboard(out, num_split=num_split)
+        for num_split, out in zip(num_splits, outs_multiscale)
+    ]
+
+    # interpolate outputs from different scales and concat together
+    output_size = outs_multiscale[resize_output_to_idx].shape[-2]
+    out = torch.cat(
+        [
+            F.interpolate(outs_multiscale[i].to(torch.float32), size=output_size, mode="area").to(
+                outs_multiscale[i].dtype
+            )
+            for i in range(len(outs_multiscale))
+        ],
+        dim=1,
+    )
+    if output_shape == "bnc":
+        out = rearrange(out, "b c h w -> b (h w) c")
+    if num_prefix_token > 0:
+        # take the mean of prefix tokens from different splits for each scale
+        outs_prefix_multiscale = [
+            torch.stack(out.split(b, dim=0), dim=0).mean(dim=0) for out in outs_prefix_multiscale
+        ]
+        out_prefix_multiscale = torch.cat(outs_prefix_multiscale, dim=-1)
+        out = torch.cat([out_prefix_multiscale, out], dim=1)
+
+    return out

VITA/util/s2wrapper/utils.py

+#  ------------------------------------------------------------------------------------------
+#  Copyright (c) 2024 Baifeng Shi.
+#  All rights reserved.
+#
+#  Licensed under the MIT License (MIT). See LICENSE in the repo root for license information.
+#  ------------------------------------------------------------------------------------------
+
+import torch
+
+
+def split_chessboard(x, num_split):
+    """
+    x: b * c * h * w
+    Deividing x into num_split**2 sub-squares, and concatenate all the sub-squares on the batch dimension
+    """
+    B, C, H, W = x.shape
+    assert H % num_split == 0 and W % num_split == 0
+    h, w = H // num_split, W // num_split
+    x_split = torch.cat(
+        [
+            x[:, :, i * h : (i + 1) * h, j * w : (j + 1) * w]
+            for i in range(num_split)
+            for j in range(num_split)
+        ],
+        dim=0,
+    )
+    return x_split
+
+
+def merge_chessboard(x, num_split):
+    """
+    x: b * c * h * w
+    Assuming x contains num_split**2 sub-squares concatenated along batch dimension, merge the sub-squares back to the original whole square.
+    (inverse of split_chessboard)
+    """
+    B, C, H, W = x.shape
+    assert B % (num_split**2) == 0
+    b = B // (num_split**2)
+    x_merge = torch.cat(
+        [
+            torch.cat(
+                [
+                    x[(i * num_split + j) * b : (i * num_split + j + 1) * b]
+                    for j in range(num_split)
+                ],
+                dim=-1,
+            )
+            for i in range(num_split)
+        ],
+        dim=-2,
+    )
+    return x_merge
+
+
+def batched_forward(model, x, batch_size=-1):
+    if batch_size == -1:
+        return model(x)
+    else:
+        x_batched = x.split(batch_size)
+        outs = [model(x) for x in x_batched]
+        return torch.cat(outs, dim=0)

VITA/util/utils.py

+import logging
+import logging.handlers
+import os
+import sys
+
+from vita.constants import LOGDIR
+
+server_error_msg = "**NETWORK ERROR DUE TO HIGH TRAFFIC. PLEASE REGENERATE OR REFRESH THIS PAGE.**"
+moderation_msg = "YOUR INPUT VIOLATES OUR CONTENT MODERATION GUIDELINES. PLEASE TRY AGAIN."
+
+handler = None
+
+
+def disable_torch_init():
+    """
+    Disable the redundant torch default initialization to accelerate model creation.
+    """
+    import torch
+
+    setattr(torch.nn.Linear, "reset_parameters", lambda self: None)
+    setattr(torch.nn.LayerNorm, "reset_parameters", lambda self: None)
+
+
+def build_logger(logger_name, logger_filename):
+    global handler
+
+    formatter = logging.Formatter(
+        fmt="%(asctime)s | %(levelname)s | %(name)s | %(message)s",
+        datefmt="%Y-%m-%d %H:%M:%S",
+    )
+
+    # Set the format of root handlers
+    if not logging.getLogger().handlers:
+        logging.basicConfig(level=logging.INFO)
+    logging.getLogger().handlers[0].setFormatter(formatter)
+
+    # Redirect stdout and stderr to loggers
+    stdout_logger = logging.getLogger("stdout")
+    stdout_logger.setLevel(logging.INFO)
+    sl = StreamToLogger(stdout_logger, logging.INFO)
+    sys.stdout = sl
+
+    stderr_logger = logging.getLogger("stderr")
+    stderr_logger.setLevel(logging.ERROR)
+    sl = StreamToLogger(stderr_logger, logging.ERROR)
+    sys.stderr = sl
+
+    # Get logger
+    logger = logging.getLogger(logger_name)
+    logger.setLevel(logging.INFO)
+
+    # Add a file handler for all loggers
+    if handler is None:
+        os.makedirs(LOGDIR, exist_ok=True)
+        filename = os.path.join(LOGDIR, logger_filename)
+        handler = logging.handlers.TimedRotatingFileHandler(
+            filename, when="D", utc=True, encoding="UTF-8"
+        )
+        handler.setFormatter(formatter)
+
+        for name, item in logging.root.manager.loggerDict.items():
+            if isinstance(item, logging.Logger):
+                item.addHandler(handler)
+
+    return logger
+
+
+class StreamToLogger(object):
+    """
+    Fake file-like stream object that redirects writes to a logger instance.
+    """
+
+    def __init__(self, logger, log_level=logging.INFO):
+        self.terminal = sys.stdout
+        self.logger = logger
+        self.log_level = log_level
+        self.linebuf = ""
+
+    def __getattr__(self, attr):
+        return getattr(self.terminal, attr)
+
+    def write(self, buf):
+        temp_linebuf = self.linebuf + buf
+        self.linebuf = ""
+        for line in temp_linebuf.splitlines(True):
+            # From the io.TextIOWrapper docs:
+            #   On output, if newline is None, any '\n' characters written
+            #   are translated to the system default line separator.
+            # By default sys.stdout.write() expects '\n' newlines and then
+            # translates them so this is still cross platform.
+            if line[-1] == "\n":
+                self.logger.log(self.log_level, line.rstrip())
+            else:
+                self.linebuf += line
+
+    def flush(self):
+        if self.linebuf != "":
+            self.logger.log(self.log_level, self.linebuf.rstrip())
+        self.linebuf = ""
+
+
+def violates_moderation(text):
+    """
+    Check whether the text violates OpenAI moderation API.
+    """
+    url = "https://api.openai.com/v1/moderations"
+    headers = {
+        "Content-Type": "application/json",
+        "Authorization": "Bearer " + os.environ["OPENAI_API_KEY"],
+    }
+    text = text.replace("\n", "")
+    data = "{" + '"input": ' + f'"{text}"' + "}"
+    data = data.encode("utf-8")
+    try:
+        ret = requests.post(url, headers=headers, data=data, timeout=5)
+        flagged = ret.json()["results"][0]["flagged"]
+    except requests.exceptions.RequestException as e:
+        flagged = False
+    except KeyError as e:
+        flagged = False
+
+    return flagged
+
+
+def pretty_print_semaphore(semaphore):
+    if semaphore is None:
+        return "None"
+    return f"Semaphore(value={semaphore._value}, locked={semaphore.locked()})"

coco/README.md

+# Coco2017
+
+
+
+## Getting started
+
+To make it easy for you to get started with GitLab, here's a list of recommended next steps.
+
+Already a pro? Just edit this README.md and make it your own. Want to make it easy? [Use the template at the bottom](#editing-this-readme)!
+
+## Add your files
+
+- [ ] [Create](https://docs.gitlab.com/ee/user/project/repository/web_editor.html#create-a-file) or [upload](https://docs.gitlab.com/ee/user/project/repository/web_editor.html#upload-a-file) files
+- [ ] [Add files using the command line](https://docs.gitlab.com/ee/gitlab-basics/add-file.html#add-a-file-using-the-command-line) or push an existing Git repository with the following command:
+
+```
+cd existing_repo
+git remote add origin http://113.200.138.88:18080/aidatasets/coco2017.git
+git branch -M main
+git push -uf origin main
+```
+
+## Integrate with your tools
+
+- [ ] [Set up project integrations](http://10.100.2.119/aidatasets/coco2017/-/settings/integrations)
+
+## Collaborate with your team
+
+- [ ] [Invite team members and collaborators](https://docs.gitlab.com/ee/user/project/members/)
+- [ ] [Create a new merge request](https://docs.gitlab.com/ee/user/project/merge_requests/creating_merge_requests.html)
+- [ ] [Automatically close issues from merge requests](https://docs.gitlab.com/ee/user/project/issues/managing_issues.html#closing-issues-automatically)
+- [ ] [Enable merge request approvals](https://docs.gitlab.com/ee/user/project/merge_requests/approvals/)
+- [ ] [Set auto-merge](https://docs.gitlab.com/ee/user/project/merge_requests/merge_when_pipeline_succeeds.html)
+
+## Test and Deploy
+
+Use the built-in continuous integration in GitLab.
+
+- [ ] [Get started with GitLab CI/CD](https://docs.gitlab.com/ee/ci/quick_start/index.html)
+- [ ] [Analyze your code for known vulnerabilities with Static Application Security Testing (SAST)](https://docs.gitlab.com/ee/user/application_security/sast/)
+- [ ] [Deploy to Kubernetes, Amazon EC2, or Amazon ECS using Auto Deploy](https://docs.gitlab.com/ee/topics/autodevops/requirements.html)
+- [ ] [Use pull-based deployments for improved Kubernetes management](https://docs.gitlab.com/ee/user/clusters/agent/)
+- [ ] [Set up protected environments](https://docs.gitlab.com/ee/ci/environments/protected_environments.html)
+
+***
+
+# Editing this README
+
+When you're ready to make this README your own, just edit this file and use the handy template below (or feel free to structure it however you want - this is just a starting point!). Thanks to [makeareadme.com](https://www.makeareadme.com/) for this template.
+
+## Suggestions for a good README
+
+Every project is different, so consider which of these sections apply to yours. The sections used in the template are suggestions for most open source projects. Also keep in mind that while a README can be too long and detailed, too long is better than too short. If you think your README is too long, consider utilizing another form of documentation rather than cutting out information.
+
+## Name
+Choose a self-explaining name for your project.
+
+## Description
+Let people know what your project can do specifically. Provide context and add a link to any reference visitors might be unfamiliar with. A list of Features or a Background subsection can also be added here. If there are alternatives to your project, this is a good place to list differentiating factors.
+
+## Badges
+On some READMEs, you may see small images that convey metadata, such as whether or not all the tests are passing for the project. You can use Shields to add some to your README. Many services also have instructions for adding a badge.
+
+## Visuals
+Depending on what you are making, it can be a good idea to include screenshots or even a video (you'll frequently see GIFs rather than actual videos). Tools like ttygif can help, but check out Asciinema for a more sophisticated method.
+
+## Installation
+Within a particular ecosystem, there may be a common way of installing things, such as using Yarn, NuGet, or Homebrew. However, consider the possibility that whoever is reading your README is a novice and would like more guidance. Listing specific steps helps remove ambiguity and gets people to using your project as quickly as possible. If it only runs in a specific context like a particular programming language version or operating system or has dependencies that have to be installed manually, also add a Requirements subsection.
+
+## Usage
+Use examples liberally, and show the expected output if you can. It's helpful to have inline the smallest example of usage that you can demonstrate, while providing links to more sophisticated examples if they are too long to reasonably include in the README.
+
+## Support
+Tell people where they can go to for help. It can be any combination of an issue tracker, a chat room, an email address, etc.
+
+## Roadmap
+If you have ideas for releases in the future, it is a good idea to list them in the README.
+
+## Contributing
+State if you are open to contributions and what your requirements are for accepting them.
+
+For people who want to make changes to your project, it's helpful to have some documentation on how to get started. Perhaps there is a script that they should run or some environment variables that they need to set. Make these steps explicit. These instructions could also be useful to your future self.
+
+You can also document commands to lint the code or run tests. These steps help to ensure high code quality and reduce the likelihood that the changes inadvertently break something. Having instructions for running tests is especially helpful if it requires external setup, such as starting a Selenium server for testing in a browser.
+
+## Authors and acknowledgment
+Show your appreciation to those who have contributed to the project.
+
+## License
+For open source projects, say how it is licensed.
+
+## Project status
+If you have run out of energy or time for your project, put a note at the top of the README saying that development has slowed down or stopped completely. Someone may choose to fork your project or volunteer to step in as a maintainer or owner, allowing your project to keep going. You can also make an explicit request for maintainers.