I trained the model successfully but fails at converting step. I first have trouble to locate the alignment.json file. Later I discovered that the 'state.json' file, which is generated under models folder, should be the correct one. I renamed it and copy it into the source image file.
Traceback (most recent call last):
File "/Schemes/Python/faceswap/lib/cli.py", line 89, in execute_script
process = script(arguments)
File "/Schemes/Python/faceswap/scripts/convert.py", line 37, in init
Legacy(self.alignments, self.images.input_images, arguments.input_aligned_dir)
File "/Schemes/Python/faceswap/scripts/convert.py", line 318, in init
self.process(faces_dir)
File "/Schemes/Python/faceswap/scripts/convert.py", line 322, in process
no_dims = self.alignments.get_legacy_no_dims()
File "Schemes/Python/faceswap/lib/alignments.py", line 286, in get_legacy_no_dims
for alignment in val:
TypeError: 'int' object is not iterable
also, from the crash report it says (I attached the full version of crash report at the end)
ValueError: Error: Alignments file not found at
/faceswap/Data/trump2/alignments.json
But I am sure the file is there. I copied it there.
Any suggestions? Thank you!
Other relevant information
Command lined used (if not specified in steps to reproduce): python faceswap.py convert -i ~/faceswap/photo/trump/ -o ~/faceswap/output/ -m ~/faceswap/models/
Actual behavior
I trained the model successfully but fails at converting step. I first have trouble to locate the alignment.json file. Later I discovered that the 'state.json' file, which is generated under models folder, should be the correct one. I renamed it and copy it into the source image file.
However, when I compile the covert steps by using
it returns the error from the terminal saying
also, from the crash report it says (I attached the full version of crash report at the end)
ValueError: Error: Alignments file not found at /faceswap/Data/trump2/alignments.json
But I am sure the file is there. I copied it there.
Any suggestions? Thank you!
Other relevant information
and also here is the full crash report:
01/31/2019 16:21:11 MainProcess MainThread logger log_setup INFO Log level set to: INFO 01/31/2019 16:21:11 MainProcess MainThread cli execute_script DEBUG Executing: convert. PID: 8558 01/31/2019 16:21:12 MainProcess MainThread convert init DEBUG Initializing Convert: (args: Namespace(alignments_path=None, avg_color_adjust=False, blur_size=2, converter='Masked', discard_frames=False, draw_transparent=False, erosion_kernel_size=None, filter=None, frame_ranges=None, func=<bound method ScriptExecutor.execute_script of <lib.cli.ScriptExecutor object at 0x119310470>>, gpus=1, input_aligned_dir=None, input_dir='/faceswap/Data/trump2', logfile=None, loglevel='INFO', mask_type='facehullandrect', match_histogram=False, model_dir='/faceswap/models', nfilter=None, output_dir='/faceswap/output', ref_threshold=0.6, seamless_clone=False, sharpen_image=None, smooth_mask=False, swap_model=False, trainer='Original')) 01/31/2019 16:21:12 MainProcess MainThread utils get_folder DEBUG Requested path: '/Users/panliu/faceswap/output' 01/31/2019 16:21:12 MainProcess MainThread utils get_folder DEBUG Returning: '/Users/panliu/faceswap/output' 01/31/2019 16:21:12 MainProcess MainThread fsmedia init DEBUG Initializing Images 01/31/2019 16:21:12 MainProcess MainThread fsmedia check_input_folder INFO Input Directory: /faceswap/Data/trump2 01/31/2019 16:21:12 MainProcess MainThread utils get_image_paths DEBUG Scanned Folder contains 6 files 01/31/2019 16:21:12 MainProcess MainThread utils get_image_paths DEBUG Returning 4 images 01/31/2019 16:21:12 MainProcess MainThread fsmedia init DEBUG Initialized Images 01/31/2019 16:21:12 MainProcess MainThread fsmedia init DEBUG Initializing Alignments: (is_extract: False, input_is_video: False) 01/31/2019 16:21:12 MainProcess MainThread fsmedia set_folder_filename DEBUG Alignments from Input Folder: '/faceswap/Data/trump2' 01/31/2019 16:21:12 MainProcess MainThread fsmedia set_folder_filename DEBUG Setting Alignments: (folder: '/faceswap/Data/trump2' filename: 'alignments') 01/31/2019 16:21:12 MainProcess MainThread fsmedia set_serializer DEBUG No Serializer defaulting to: 'json' 01/31/2019 16:21:12 MainProcess MainThread alignments init DEBUG Initializing Alignments: (folder: '/faceswap/Data/trump2', filename: 'alignments', serializer: 'json') 01/31/2019 16:21:12 MainProcess MainThread alignments get_serializer DEBUG Getting serializer: (filename: 'alignments', serializer: 'json') 01/31/2019 16:21:12 MainProcess MainThread alignments get_serializer DEBUG Serializer set from argument: 'json' 01/31/2019 16:21:12 MainProcess MainThread alignments get_serializer VERBOSE Using 'json' serializer for alignments 01/31/2019 16:21:12 MainProcess MainThread alignments get_location DEBUG Getting location: (folder: '/faceswap/Data/trump2', filename: 'alignments') 01/31/2019 16:21:12 MainProcess MainThread alignments get_location DEBUG File extension set from serializer: 'json' 01/31/2019 16:21:12 MainProcess MainThread alignments get_location VERBOSE Alignments filepath: '/faceswap/Data/trump2/alignments.json' 01/31/2019 16:21:12 MainProcess MainThread alignments load DEBUG Loading alignments Traceback (most recent call last): File "/faceswap/lib/cli.py", line 89, in execute_script process = script(arguments) File "/faceswap/scripts/convert.py", line 34, in init self.alignments = Alignments(self.args, False, self.images.is_video) File "/faceswap/scripts/fsmedia.py", line 61, in init serializer=serializer) File "/faceswap/lib/alignments.py", line 36, in init self.data = self.load() File "/faceswap/scripts/fsmedia.py", line 97, in load data = super().load() File "/faceswap/lib/alignments.py", line 121, in load "{}".format(self.file)) ValueError: Error: Alignments file not found at /faceswap/Data/trump2/alignments.json
============ System Information ============ git_branch: Not Found git_commits: Not Found gpu_cuda: Unsupported OS gpu_cudnn: Not Found gpu_devices:
gpu_driver: 0 gpu_vram:
os_machine: x86_64 os_platform: Darwin-18.2.0-x86_64-i386-64bit os_release: 18.2.0 py_command: faceswap.py convert -i /faceswap/Data/trump2 -o /faceswap/output/ -m /faceswap/models/ py_conda_version: N/A py_implementation: CPython py_version: 3.6.7 py_virtual_env: True sys_cores: 8 sys_processor: i386 sys_ram: Total: 16384MB, Available: 7875MB, Used: 5664MB, Free: 3396MB
=============== Pip Packages =============== absl-py==0.7.0 astor==0.7.1 certifi==2018.11.29 chardet==3.0.4 Click==7.0 cloudpickle==0.7.0 cmake==3.13.3 cycler==0.10.0 dask==1.1.0 decorator==4.3.2 dlib==19.16.0 face-recognition==1.2.3 face-recognition-models==0.3.0 ffmpy==0.2.2 gast==0.2.2 grpcio==1.18.0 h5py==2.8.0 idna==2.8 Keras==2.2.4 Keras-Applications==1.0.6 Keras-Preprocessing==1.0.5 kiwisolver==1.0.1 Markdown==3.0.1 matplotlib==2.2.2 networkx==2.2 numpy==1.15.4 nvidia-ml-py3==7.352.0 opencv-python==4.0.0.21 pandas==0.23.4 pathlib==1.0.1 Pillow==5.4.1 protobuf==3.6.1 psutil==5.5.0 pydicom==1.2.2 pynvx==0.0.4 pyparsing==2.3.1 python-dateutil==2.7.5 pytz==2018.9 PyWavelets==1.0.1 PyYAML==3.13 requests==2.21.0 scandir==1.7 scikit-image==0.14.2 scikit-learn==0.20.2 scipy==1.2.0 six==1.12.0 tensorboard==1.12.2 tensorflow==1.12.0 termcolor==1.1.0 toolz==0.9.0 tqdm==4.30.0 urllib3==1.24.1 virtualenv==16.2.0 Werkzeug==0.14.1 xlrd==1.2.0