Deep-Live-Cam icon indicating copy to clipboard operation
Deep-Live-Cam copied to clipboard

Why not in the/data/python/DeepLiveCam/data/video file to generate the output directory goal

Open jxaujunjun opened this issue 1 year ago • 2 comments

Execute the command: python run.py --source "/data/python/DeepLiveCam/data/source/rock.jpg" --target "/data/python/DeepLiveCam/data/source/demo.mp4" -o "/data/python/DeepLiveCam/data/output" --execution-provider cuda

Why not in the/data/python/DeepLiveCam/data/video file to generate the output directory goal

(deep-live-cam-python310-cuda118) root@autodl-container-36da11a152-6c203099:/data/python/DeepLiveCam# python run.py --source "/data/python/DeepLiveCam/data/source/rock.jpg" --target "/data/python/DeepLiveCam/data/source/demo.mp4" -o "/data/python/DeepLiveCam/data/output" --execution-provider cuda Applied providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}, 'CUDAExecutionProvider': {'tunable_op_max_tuning_duration_ms': '0', 'enable_skip_layer_norm_strict_mode': '0', 'tunable_op_tuning_enable': '0', 'device_id': '0', 'has_user_compute_stream': '0', 'gpu_mem_limit': '18446744073709551615', 'gpu_external_alloc': '0', 'gpu_external_free': '0', 'gpu_external_empty_cache': '0', 'cudnn_conv_algo_search': 'EXHAUSTIVE', 'cudnn_conv1d_pad_to_nc1d': '0', 'arena_extend_strategy': 'kNextPowerOfTwo', 'do_copy_in_default_stream': '1', 'enable_cuda_graph': '0', 'cudnn_conv_use_max_workspace': '1', 'tunable_op_enable': '0'}} find model: /root/.insightface/models/buffalo_l/1k3d68.onnx landmark_3d_68 ['None', 3, 192, 192] 0.0 1.0 Applied providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}, 'CUDAExecutionProvider': {'tunable_op_max_tuning_duration_ms': '0', 'enable_skip_layer_norm_strict_mode': '0', 'tunable_op_tuning_enable': '0', 'device_id': '0', 'has_user_compute_stream': '0', 'gpu_mem_limit': '18446744073709551615', 'gpu_external_alloc': '0', 'gpu_external_free': '0', 'gpu_external_empty_cache': '0', 'cudnn_conv_algo_search': 'EXHAUSTIVE', 'cudnn_conv1d_pad_to_nc1d': '0', 'arena_extend_strategy': 'kNextPowerOfTwo', 'do_copy_in_default_stream': '1', 'enable_cuda_graph': '0', 'cudnn_conv_use_max_workspace': '1', 'tunable_op_enable': '0'}} find model: /root/.insightface/models/buffalo_l/2d106det.onnx landmark_2d_106 ['None', 3, 192, 192] 0.0 1.0 Applied providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}, 'CUDAExecutionProvider': {'tunable_op_max_tuning_duration_ms': '0', 'enable_skip_layer_norm_strict_mode': '0', 'tunable_op_tuning_enable': '0', 'device_id': '0', 'has_user_compute_stream': '0', 'gpu_mem_limit': '18446744073709551615', 'gpu_external_alloc': '0', 'gpu_external_free': '0', 'gpu_external_empty_cache': '0', 'cudnn_conv_algo_search': 'EXHAUSTIVE', 'cudnn_conv1d_pad_to_nc1d': '0', 'arena_extend_strategy': 'kNextPowerOfTwo', 'do_copy_in_default_stream': '1', 'enable_cuda_graph': '0', 'cudnn_conv_use_max_workspace': '1', 'tunable_op_enable': '0'}} find model: /root/.insightface/models/buffalo_l/det_10g.onnx detection [1, 3, '?', '?'] 127.5 128.0 Applied providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}, 'CUDAExecutionProvider': {'tunable_op_max_tuning_duration_ms': '0', 'enable_skip_layer_norm_strict_mode': '0', 'tunable_op_tuning_enable': '0', 'device_id': '0', 'has_user_compute_stream': '0', 'gpu_mem_limit': '18446744073709551615', 'gpu_external_alloc': '0', 'gpu_external_free': '0', 'gpu_external_empty_cache': '0', 'cudnn_conv_algo_search': 'EXHAUSTIVE', 'cudnn_conv1d_pad_to_nc1d': '0', 'arena_extend_strategy': 'kNextPowerOfTwo', 'do_copy_in_default_stream': '1', 'enable_cuda_graph': '0', 'cudnn_conv_use_max_workspace': '1', 'tunable_op_enable': '0'}} find model: /root/.insightface/models/buffalo_l/genderage.onnx genderage ['None', 3, 96, 96] 0.0 1.0 Applied providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}, 'CUDAExecutionProvider': {'tunable_op_max_tuning_duration_ms': '0', 'enable_skip_layer_norm_strict_mode': '0', 'tunable_op_tuning_enable': '0', 'device_id': '0', 'has_user_compute_stream': '0', 'gpu_mem_limit': '18446744073709551615', 'gpu_external_alloc': '0', 'gpu_external_free': '0', 'gpu_external_empty_cache': '0', 'cudnn_conv_algo_search': 'EXHAUSTIVE', 'cudnn_conv1d_pad_to_nc1d': '0', 'arena_extend_strategy': 'kNextPowerOfTwo', 'do_copy_in_default_stream': '1', 'enable_cuda_graph': '0', 'cudnn_conv_use_max_workspace': '1', 'tunable_op_enable': '0'}} find model: /root/.insightface/models/buffalo_l/w600k_r50.onnx recognition ['None', 3, 112, 112] 127.5 127.5 set det-size: (640, 640) [DLC.CORE] Processing... [DLC.CORE] Creating temp resources... [DLC.CORE] Extracting frames... [DLC.FACE-SWAPPER] Progressing... Processing: 0%| | 0/631 [00:00<?, ?frame/s, execution_providers=['CUDAExecutionProvider'], execution_threads=8, max_memory=16]Applied providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}, 'CUDAExecutionProvider': {'tunable_op_max_tuning_duration_ms': '0', 'enable_skip_layer_norm_strict_mode': '0', 'tunable_op_tuning_enable': '0', 'device_id': '0', 'has_user_compute_stream': '0', 'gpu_mem_limit': '18446744073709551615', 'gpu_external_alloc': '0', 'gpu_external_free': '0', 'gpu_external_empty_cache': '0', 'cudnn_conv_algo_search': 'EXHAUSTIVE', 'cudnn_conv1d_pad_to_nc1d': '0', 'arena_extend_strategy': 'kNextPowerOfTwo', 'do_copy_in_default_stream': '1', 'enable_cuda_graph': '0', 'cudnn_conv_use_max_workspace': '1', 'tunable_op_enable': '0'}} inswapper-shape: [1, 3, 128, 128] Processing: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 631/631 [00:43<00:00, 14.37frame/s, execution_providers=['CUDAExecutionProvider'], execution_threads=8, max_memory=16] [DLC.CORE] Creating video with 30.0 fps... [DLC.CORE] Restoring audio might cause issues as fps are not kept... [DLC.CORE] Processing to video succeed! (deep-live-cam-python310-cuda118) root@autodl-container-36da11a152-6c203099:/data/python/DeepLiveCam#

jxaujunjun avatar Dec 16 '24 06:12 jxaujunjun

Have you solved it? I have the same problem

GabriellaMS avatar Dec 23 '24 09:12 GabriellaMS

What kind of a system are you running it on?

I can see from your output root and autodl-container-36da11a152-6c203099, so i have two "concerns". First is, are you checking the folder with the correct permissions? Secondly, is this a docker container? If so, have you added the correct volumes? ( Using Docker can lead to other future issues if you're unable to set up your environment properly. Just FYI)

luna-nightbyte avatar Jan 28 '25 21:01 luna-nightbyte