ValueError: This ORT build has ['TensorrtExecutionProvider', 'CUDAExecutionProvider', 'CPUExecutionProvider'] enabled.

[santosadrian]

(simswap) C:\Users\foldd\Desktop\SimSwap>python test_video_swapmulti.py --crop_size 224 --use_mask --name people --Arc_path arcface_model/arcface_checkpoint.tar --pic_a_path lo.png --video_path pt.mp4 --output_path ./output/multi_test_swapmulti-pt.mp4 --temp_path ./temp ------------ Options ------------- Arc_path: arcface_model/arcface_checkpoint.tar aspect_ratio: 1.0 batchSize: 8 checkpoints_dir: ./checkpoints cluster_path: features_clustered_010.npy crop_size: 224 data_type: 32 dataroot: ./datasets/cityscapes/ display_winsize: 512 engine: None export_onnx: None feat_num: 3 fineSize: 512 fp16: False gpu_ids: [0] how_many: 50 id_thres: 0.03 image_size: 224 input_nc: 3 instance_feat: False isTrain: False label_feat: False label_nc: 0 latent_size: 512 loadSize: 1024 load_features: False local_rank: 0 max_dataset_size: inf model: pix2pixHD multisepcific_dir: ./demo_file/multispecific nThreads: 2 n_blocks_global: 6 n_blocks_local: 3 n_clusters: 10 n_downsample_E: 4 n_downsample_global: 3 n_local_enhancers: 1 name: people nef: 16 netG: global ngf: 64 niter_fix_global: 0 no_flip: False no_instance: False no_simswaplogo: False norm: batch norm_G: spectralspadesyncbatch3x3 ntest: inf onnx: None output_nc: 3 output_path: ./output/multi_test_swapmulti-pt.mp4 phase: test pic_a_path: lo.png pic_b_path: ./crop_224/zrf.jpg pic_specific_path: ./crop_224/zrf.jpg resize_or_crop: scale_width results_dir: ./results/ semantic_nc: 3 serial_batches: False temp_path: ./temp tf_log: False use_dropout: False use_encoded_image: False use_mask: True verbose: False video_path: pt.mp4 which_epoch: latest -------------- End ---------------- Traceback (most recent call last): File "test_video_swapmulti.py", line 58, in app = Face_detect_crop(name='antelope', root='./insightface_func/models') File "C:\Users\foldd\Desktop\SimSwap\insightface_func\face_detect_crop_multi.py", line 40, in init model = model_zoo.get_model(onnx_file) File "C:\ProgramData\Anaconda3\envs\simswap\lib\site-packages\insightface\model_zoo\model_zoo.py", line 56, in get_model model = router.get_model() File "C:\ProgramData\Anaconda3\envs\simswap\lib\site-packages\insightface\model_zoo\model_zoo.py", line 23, in get_model session = onnxruntime.InferenceSession(self.onnx_file, None) File "C:\ProgramData\Anaconda3\envs\simswap\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 335, in init self._create_inference_session(providers, provider_options, disabled_optimizers) File "C:\ProgramData\Anaconda3\envs\simswap\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 364, in _create_inference_session "onnxruntime.InferenceSession(..., providers={}, ...)".format(available_providers)) ValueError: This ORT build has ['TensorrtExecutionProvider', 'CUDAExecutionProvider', 'CPUExecutionProvider'] enabled. Since ORT 1.9, you are required to explicitly set the providers parameter when instantiating InferenceSession. For example, onnxruntime.InferenceSession(..., providers=['TensorrtExecutionProvider', 'CUDAExecutionProvider', 'CPUExecutionProvider'], ...)

[skintflickz]

Is there a question in that post somewhere ?

[santosadrian]

Sorry, I thought that this is not a forum to post questions. But if you ask, sure... how can I fix this error?

Thank you.

[skintflickz]

Ah ok.. Well the way I fixed it was , I use a conda environment btw. Uninstall onnxruntime-gpu pip install onnxruntime-gpu==1.9.0

i has something to do with the the latest version 1.12.0 and cuda version I think, I haven't been able to work it out.

Somehow that sorted the problem you have above.

However it made very little difference to processing speed on my k80, went form 1.2 it/s to 1,48 it/s

[mossan0101]

Try this one: https://github.com/mike9251/simswap-inference-pytorch It is faster than the official repository and supports the RTX3000 series for inference.

[k128]

I was able to fix this error by changing changing site-packages\insightface\model_zoo\model_zoo.py:23
from: session = onnxruntime.InferenceSession(self.onnx_file, None) to: session = onnxruntime.InferenceSession(self.onnx_file, None, providers=['CUDAExecutionProvider', 'CPUExecutionProvider'])

[white0rchardpUnK]

Ah ok.. Well the way I fixed it was , I use a conda environment btw. Uninstall onnxruntime-gpu pip install onnxruntime-gpu==1.9.0

i has something to do with the the latest version 1.12.0 and cuda version I think, I haven't been able to work it out.

Somehow that sorted the problem you have above.

However it made very little difference to processing speed on my k80, went form 1.2 it/s to 1,48 it/s

I have the same problem with my 10 series graphics card. The old version does need to be installed because the training code is not updated based on the new version.

[woctezuma]

I was able to fix this error by changing changing site-packages\insightface\model_zoo\model_zoo.py:23 from: session = onnxruntime.InferenceSession(self.onnx_file, None) to: session = onnxruntime.InferenceSession(self.onnx_file, None, providers=['CUDAExecutionProvider', 'CPUExecutionProvider'])

I can confirm that editing the following file works.

File "/usr/local/lib/python3.10/dist-packages/insightface/model_zoo/model_zoo.py", line 23

Before:

    def get_model(self):
        session = onnxruntime.InferenceSession(self.onnx_file, None)

After:

    def get_model(self):
        session = onnxruntime.InferenceSession(self.onnx_file, None, providers=['AzureExecutionProvider', 'CPUExecutionProvider'])

Related:

• https://github.com/neuralchen/SimSwap/issues/445

[TransAmMan]

I was able to fix this error by changing changing site-packages\insightface\model_zoo\model_zoo.py:23 from: session = onnxruntime.InferenceSession(self.onnx_file, None) to: session = onnxruntime.InferenceSession(self.onnx_file, None, providers=['CUDAExecutionProvider', 'CPUExecutionProvider'])

I can confirm that editing the following file works.

File "/usr/local/lib/python3.10/dist-packages/insightface/model_zoo/model_zoo.py", line 23

Before:

    def get_model(self):
        session = onnxruntime.InferenceSession(self.onnx_file, None)

After:

    def get_model(self):
        session = onnxruntime.InferenceSession(self.onnx_file, None, providers=['AzureExecutionProvider', 'CPUExecutionProvider'])

Related:

• Problem ValueError with SimSwap #445

Can you help me implement this fix for a hosted GPU runtime?