|
Location |
Details |
| ✔️ |
|
Successfully created `ModelDescr` instance. |
| ✔️ |
|
bioimageio.spec format validation model 0.5.9 |
| ⚠ |
documentation |
No '# Validation' (sub)section found in README.md. |
| ✔️ |
weights.torchscript |
Created conda environment '5337c9602c7bddf436ffd2b7d541b6a00a82afd44b0968565fc1173fe7dd2d68' |
| ✔️ |
weights.torchscript |
Reproduce test outputs from test inputs (torchscript) |
| ℹ |
weights.torchscript |
Output `prediction`: all elements agree with expected values.
Max relative difference not accounted for by absolute tolerance (1.00e-03):
0.00e+00 (= \|3.31e+00 - 3.31e+00\|/\|3.31e+00 + 1e-6\|) at {'batch': np.int64(0), 'channel': np.int64(0), 'y': np.int64(0), 'x': np.int64(0)}
Max absolute difference not accounted for by relative tolerance (1.00e-03):
0.00e+00 (= \|-1.5475182e-04 - -1.5312748e-04\|) at {'batch': np.int64(0), 'channel': np.int64(1), 'y': np.int64(576), 'x': np.int64(1003)} |
|
weights.torchscript |
recommended conda environment (Reproduce test outputs from test inputs (torchscript)) |
|
|
%YAML 1.2
---
channels:
- conda-forge
- nodefaults
dependencies:
- conda-forge::bioimageio.core>=0.9.4
- pip
- pytorch==2.5.1
- torchvision==0.20.1
|
|
weights.torchscript |
conda compare (Reproduce test outputs from test inputs (torchscript)) |
|
|
Success. All the packages in the specification file are present in the environment with matching
version and build string. |
| ✔️ |
weights.torchscript |
Run torchscript inference for inputs with batch_size: 1 and size parameter n: 0 |
| ✔️ |
weights.torchscript |
Run torchscript inference for inputs with batch_size: 1 and size parameter n: 1 |
| ✔️ |
weights.torchscript |
Run torchscript inference for inputs with batch_size: 1 and size parameter n: 2 |
| ✔️ |
weights.torchscript |
Run torchscript inference for inputs with batch_size: 2 and size parameter n: 0 |
| ✔️ |
weights.torchscript |
Run torchscript inference for inputs with batch_size: 2 and size parameter n: 1 |
| ✔️ |
weights.torchscript |
Run torchscript inference for inputs with batch_size: 2 and size parameter n: 2 |