bhky / opennsfw2 Goto Github PK

View Code? Open in Web Editor NEW

319.0 319.0 42.0 48.38 MB

Keras implementation of the Yahoo Open-NSFW model

License: MIT License

Python 97.13% Shell 2.87%

image-classification image-preprocessing jax keras nsfw-classifier tensorflow2

opennsfw2's People

Contributors

Stargazers

Watchers

Forkers

bevog msmyers edwios winterxx strategist922 wolfworld6 templeblock piancat aniketmaurya smangal rbarreto chickensarad raxpyraxp fffaded leraner justinline kingmo888 aerotube128 berkayakin c93614 hldh214 unable-prune sachinsenals yinxuping doncat99 edenbuaa rohankumardubey sahilverma0696 palverdata iradewa pictofeed anietieakpan suryatmodulus mattmatters longtruong brgrp hantupota jbeomchoi ekojs hwj6666666 pincident theparitt

opennsfw2's Issues

OpenNSFW in PyTorch

Hey!
Thanks for great work!
Your current work is using tensorflow and the highest supported CUDA driver version for TF gpu usage is 11.8
I am running CUDA 12.2, and cannot get to use ur code with gpu, as tf does not supports gpu for cuda above 11.8
Do u have any valuable resoruce to convert/ckpts this work in pytorch?

Update to 0.11.0 causing exceptions

Our low level implementation is causing an error once we update to the 0.11.0 release.

Code

def predict_frame(target_frame : Frame) -> bool:
	image = Image.fromarray(target_frame)
	image = opennsfw2.preprocess_image(image, opennsfw2.Preprocessing.YAHOO)
	views = numpy.expand_dims(image, axis = 0)
	_, probability = get_predictor().predict(views)[0]
	return probability > MAX_PROBABILITY

Source: https://github.com/facefusion/facefusion/blob/master/facefusion/predictor.py

Error

Traceback (most recent call last):
  File "/home/henry/PycharmProjects/facefusion/venv/lib/python3.10/site-packages/gradio/routes.py", line 523, in run_predict
    output = await app.get_blocks().process_api(
  File "/home/henry/PycharmProjects/facefusion/venv/lib/python3.10/site-packages/gradio/blocks.py", line 1437, in process_api
    result = await self.call_function(
  File "/home/henry/PycharmProjects/facefusion/venv/lib/python3.10/site-packages/gradio/blocks.py", line 1109, in call_function
    prediction = await anyio.to_thread.run_sync(
  File "/home/henry/PycharmProjects/facefusion/venv/lib/python3.10/site-packages/anyio/to_thread.py", line 33, in run_sync
    return await get_asynclib().run_sync_in_worker_thread(
  File "/home/henry/PycharmProjects/facefusion/venv/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 877, in run_sync_in_worker_thread
    return await future
  File "/home/henry/PycharmProjects/facefusion/venv/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 807, in run
    result = context.run(func, *args)
  File "/home/henry/PycharmProjects/facefusion/venv/lib/python3.10/site-packages/gradio/utils.py", line 865, in wrapper
    response = f(*args, **kwargs)
  File "/home/henry/PycharmProjects/facefusion/facefusion/uis/components/preview.py", line 95, in update_preview_image
    preview_frame = process_preview_frame(target_frame)
  File "/home/henry/PycharmProjects/facefusion/facefusion/uis/components/preview.py", line 118, in process_preview_frame
    if predict_frame(temp_frame):
  File "/home/henry/PycharmProjects/facefusion/facefusion/predictor.py", line 33, in predict_frame
    _, probability = get_predictor().predict(views)[0]
  File "/home/henry/PycharmProjects/facefusion/venv/lib/python3.10/site-packages/keras_core/src/utils/traceback_utils.py", line 123, in error_handler
    raise e.with_traceback(filtered_tb) from None
  File "/home/henry/PycharmProjects/facefusion/venv/lib/python3.10/site-packages/tensorflow/python/eager/execute.py", line 53, in quick_execute
    tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
tensorflow.python.framework.errors_impl.InternalError: Graph execution error:

Detected at node 'StatefulPartitionedCall' defined at (most recent call last):
    File "/usr/lib/python3.10/threading.py", line 973, in _bootstrap
      self._bootstrap_inner()
    File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner
      self.run()
    File "/home/henry/PycharmProjects/facefusion/venv/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 807, in run
      result = context.run(func, *args)
    File "/home/henry/PycharmProjects/facefusion/venv/lib/python3.10/site-packages/gradio/utils.py", line 865, in wrapper
      response = f(*args, **kwargs)
    File "/home/henry/PycharmProjects/facefusion/facefusion/uis/components/preview.py", line 95, in update_preview_image
      preview_frame = process_preview_frame(target_frame)
    File "/home/henry/PycharmProjects/facefusion/facefusion/uis/components/preview.py", line 118, in process_preview_frame
      if predict_frame(temp_frame):
    File "/home/henry/PycharmProjects/facefusion/facefusion/predictor.py", line 33, in predict_frame
      _, probability = get_predictor().predict(views)[0]
    File "/home/henry/PycharmProjects/facefusion/venv/lib/python3.10/site-packages/keras_core/src/utils/traceback_utils.py", line 118, in error_handler
      return fn(*args, **kwargs)
    File "/home/henry/PycharmProjects/facefusion/venv/lib/python3.10/site-packages/keras_core/src/backend/tensorflow/trainer.py", line 504, in predict
      batch_outputs = self.predict_function(data)
    File "/home/henry/PycharmProjects/facefusion/venv/lib/python3.10/site-packages/keras_core/src/backend/tensorflow/trainer.py", line 210, in one_step_on_data_distributed
      outputs = self.distribute_strategy.run(
Node: 'StatefulPartitionedCall'
libdevice not found at ./libdevice.10.bc
         [[{{node StatefulPartitionedCall}}]] [Op:__inference_one_step_on_data_distributed_4826]

small demo website

would be nice to have a small website that allows users to demo the model instead of having to run it all, such as https://maybeshewill-cv.github.io/nsfw_classification/

Replace PIL with CV2

At this time I might "piss you off" by asking to replace Pillow by OpenCV and Numpy? Most AI projects have this dependencies already so it makes sense to me - in our case I have the PIL dependency just for one line:

image = Image.fromarray(target_frame)

It's fine you close that issue instantly. Please consider it.

'opennsfw2' has no attribute 'preprocess_image'

partially initialized module 'opennsfw2' has no attribute 'preprocess_image' (most likely due to a circular import)
这是什么原因啊

Huge video memory footprint

My python version is 3.8, cuda version is 10.2.

module 'opennsfw2' has no attribute 'predict_images'

Please help resolve this error for python3.6

module 'opennsfw2' has no attribute 'predict_images'

Uninstall

How to remove this from repo?

Support for Mac M1

This awesome lib depends on tensorflow and therefore cannot be installed on Mac with M1 chip as this needs tensorflow-macos. We are using opennsfw2 for roop and would love to give support to our users.

ERROR WITH NO ERROR

Hi,
I don't understand what happened with opennsfw2 code.
My installation is OK. I install Keras and Tensorflow 2.0 with CUDA but nothing,
Any idea ?
I attached a screenshot.
Thank you to help me

Problem with dm-tree dependency

It says no module named 'tree' when trying to install or run opennsfw2

sample output

hello,
thanks for ur great work
can we get an example output of video processing ? like is it able to detect hentai or anime nudity too ?

Range for video prediction

Is there a chance you implement a frame range for video prediction like.

predict_video_frames(video_path, (100, 200))

Many people in my community gonna appreciate that.

Regards

Which NSFW Area is this AI covering?

Hi,

very cool project, I am looking for an AI, which can cover on the one side nudity, but doesn't judge sexy images and also bans traumatic images, like horror and the crazy things, like NSFW 4 things, is it possible with this AI?

I found this image online, which is your AI covering?

Thanks!

Improved Memory Management for Model Reuse

Hello, and first of all, thank you for this fantastic project; I truly appreciate it.

I've encountered what may be a minor issue when using predict_images in a for-loop, which results in an Out Of Memory (OOM) error on my 4GB RAM machine. After investigating the code, I found the following line:

opennsfw2/opennsfw2/_inference.py

Line 31 in 9654c1e

model = make_open_nsfw_model(weights_path=weights_path)

It appears that the model is created anew with every call to predict_images, which could lead to memory leaks, as suggested by my testing. To address this, I attempted to move the model creation outside the function like this:

global_model = make_open_nsfw_model(weights_path=get_default_weights_path())

Then, I utilized the global model within the function, as shown below:

predictions = global_model.predict(images, batch_size=batch_size, verbose=0)

This change seems to have resolved the memory issue on my end.

How to continue train the model?

I have my own porn dataset. How can I resume the training process with the the current model?
thanks
Best.