Skip to content

Core Compatibility Report: famous-fish/v0¤

🟡 bioimageio format validation
status valid-format
source https://hypha.aicell.io/bioimage-io/artifacts/famous-fish/files/rdf.yaml?version=v0
id famous-fish
version 0.3.0
applied format model 0.5.9
bioimageio.spec 0.5.9.1
Location Details
✔️ Successfully created `ModelDescr` instance.
✔️ bioimageio.spec format validation model 0.5.9
⚠ inputs.0.sample_tensor 
Needs to be filled for FAIR compliance
⚠ outputs.0.sample_tensor 
Needs to be filled for FAIR compliance
✔️ weights.pytorch_state_dict Created conda environment 'ef1c05b6df561758fe3fb414f76da731344df3d2de91919109a29942a98d6531'
❌ weights.pytorch_state_dict Reproduce test outputs from test inputs (pytorch_state_dict)
❌ weights.pytorch_state_dict 
Output 'masks': 101770 of 455955 elements disagree with expected values. (223201.9 ppm). 
Max relative difference not accounted for by absolute tolerance (1.00e-03):
1.00e+00 (= \|-1.10e+01 - 1.10e+01\|/\|1.10e+01 + 1e-6\|) at {'batch': np.int64(0), 'y': np.int64(246), 'x': np.int64(302)} 
Max absolute difference not accounted for by relative tolerance (1.00e-02):
1.00e+00 (= \|-1.0000000e+00 - 1.0000000e+00\|) at {'batch': np.int64(0), 'y': np.int64(44), 'x': np.int64(71)}
weights.pytorch_state_dict 
recommended conda environment (Reproduce test outputs from test inputs (pytorch_state_dict))
See Recommended Conda Environment 1.
weights.pytorch_state_dict 
conda compare (Reproduce test outputs from test inputs (pytorch_state_dict))
 
Success. All the packages in the specification file are present in the environment with matching
version and build string.
✔️ weights.pytorch_state_dict Run pytorch_state_dict inference for inputs with batch_size: 1 and size parameter n: 0
✔️ weights.pytorch_state_dict Run pytorch_state_dict inference for inputs with batch_size: 2 and size parameter n: 0 
%YAML 1.2
---
name: cellpose
channels:
  - pytorch
  - conda-forge
  - nodefaults
dependencies:
  - bioimageio.core
  - imagecodecs
  - pip
  - python>=3.9
  - pytorch
  - setuptools
  - torchvision
  - pip:
      - cellpose==3.1.0