# Issues converting a PyTorch model to CoreML
**URL:**
**Author:**  [@eightysix](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Feightysix)%5C
**Post date:** [September 28, 2023, 4:20pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fissues-converting-a-pytorch-model-to-coreml%2F56728%2F1 "2023-09-28T16:20:07Z")
Hello.
I’m an iOS/macOS developer who’s very new to AI.
I’d like to integrate to test some [radiology-related AI models](https://github.com/mlmed/torchxrayvision) in a Swift environment, but I’m having issues converting them to CoreML.
Specifically, I’m encountering this error: `AssertionError: tensor value not consistent between torch ir and state_dict`, for which I’ve found no information anywhere.
This is my full Jupyter notebook for conversion:
```auto
import torchxrayvision as xrv
import skimage, torch, torchvision
model = xrv.models.DenseNet(weights="densenet121-res224-rsna")
model.eval()
example_input = torch.rand(1, 1, 224, 224)
traced_model = torch.jit.trace(model, example_input)
out = traced_model(example_input)
import coremltools as ct
scale = 1/(0.226*255.0)
bias = [- 0.485/(0.229) , - 0.456/(0.224), - 0.406/(0.225)]
image_input = ct.ImageType(name="input_1",
shape=example_input.shape,
scale=scale, bias=bias)
model = ct.convert(
traced_model,
inputs=[image_input],
compute_units=ct.ComputeUnit.CPU_ONLY,
)
```
---
**Author:**  [@Krass1](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FKrass1)%5C
**Post date:** [March 28, 2024, 10:34pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fissues-converting-a-pytorch-model-to-coreml%2F56728%2F2 "2024-03-28T22:34:07Z")
Hi, I was able to successfully convert it, but had to make a few changes. The changes and the edited code are below. Hope it helps.
1. Used coremltools v7.0, torch v2.1.0, torchvision v0.16, python v3.10
2. coremltools needs a custom operation `isnan` to be added to the `ops.py` file. The function I came up with looks like this:
```auto
@register_torch_op
def isnan(context, node):
torchTensor, = _get_inputs(context, node, expected=1)
x = mb.const(val=(torchTensor != torchTensor), name=node.name)
context.add(x, node.name)
```
1. The scale and bias need to be changed to match what the model you are using expects. In the case of `densenet121-res224-rsna` the scale is 1/1024 and bias is 0.
2. Lastly we have to add `color_layout=ct.colorlayout.GRAYSCALE` to the `input_image` in order to tell coreML to expect only one channel of color and not three.
Here is the code that works for me and generates a coreML model, but I have not put this model in an app to see if it performs as expected.
````auto
import torchxrayvision as xrv
import skimage, torch, torchvision
import coremltools as ct
model = xrv.models.DenseNet(weights="densenet121-res224-rsna")
model.eval()
example_input = torch.rand(1, 1, 1024, 1024)
traced_model = torch.jit.trace(model, example_input)
scale = 1/(1024)
bias = [0, 0, 0]
image_input = ct.ImageType(name="input_1", shape=example_input.shape, color_layout=ct.colorlayout.GRAYSCALE, scale=scale, bias=bias)
output = ct.TensorType(name="output")
mlmodel = ct.convert(traced_model, inputs=[image_input], outputs=[output])
print(mlmodel)```
````
---
**Author:**  [@system](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsystem)%5C
**Post date:** [April 10, 2024, 12:19pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fissues-converting-a-pytorch-model-to-coreml%2F56728%2F3 "2024-04-10T12:19:47Z")
Closed on April 10, 2024, 12:19pm UTC
This topic was automatically closed 12 hours after the last reply. New replies are no longer allowed.