non-classifier case in coremltools4.0+ #581

Guanbin-Huang · 2020-06-29T19:58:23Z

❓Question

Is it possible to convert a pytorch model withtout classification layer into mlmodel? I don't know how to do it because in the example, I am asked to specify the label.

System Information

If applicable

aseemw · 2020-06-29T20:03:22Z

Just don't provide the classifier_config argument to the ct.convert call, as shown here

Guanbin-Huang · 2020-06-29T20:10:37Z

Hi, have you ever encountered this situation?

One day ago, I convert my pytorch model to onnx. It works well. But now I use your tool to do the conversion directly. It seems not good.

Guanbin-Huang · 2020-06-29T20:11:30Z

This is the complete error.
TypeError: Input strides has type <class 'coremltools.converters.mil.mil.types.type_tensor.tensor..tensor'> not compatible with expected type IntTensorInputType

Guanbin-Huang · 2020-06-29T20:16:10Z

it works well until the 7-th part

Guanbin-Huang · 2020-06-29T20:16:43Z

I run the whole thing on colab.

Guanbin-Huang · 2020-06-29T21:58:36Z

Hi, have you ever encountered this situation? [image: image] <https://user-images.githubusercontent.com/30463291/86051128-d90cd880-ba4c-11ea-88aa-c3038dafa5d6.png> One day ago, I convert my pytorch model to onnx. It works well. But now I use your tool to do the conversion directly. It seems not good. This is the complete error. TypeError: Input strides has type <class 'coremltools.converters.mil.mil.types.type_tensor.tensor..tensor'> not compatible with expected type IntTensorInputType it works well until the 7-th part [image: image] <https://user-images.githubusercontent.com/30463291/86051706-be872f00-ba4d-11ea-9354-b908148d270e.png>

…

On Mon, 29 Jun 2020 at 21:03, Aseem Wadhwa ***@***.***> wrote: Just don't provide the classifier_config argument to the ct.convert call, as shown here <https://coremltools.readme.io/docs/unified-conversion-api#conversion-from-pytorch> — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#581 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AHINKO6DHUZADM3JUWXVDR3RZDXRPANCNFSM4OLRJ5WA> .

aseemw · 2020-06-29T22:23:29Z

@HuangGuanbin can you please provide the pytorch model, which can reproduce this error? Otherwise its hard to debug the error.

Guanbin-Huang · 2020-06-29T22:24:47Z

no problem. I will do it right now. Give me a second.

…

On Mon, Jun 29, 2020 at 11:23 PM Aseem Wadhwa ***@***.***> wrote: @HuangGuanbin <https://github.com/huangguanbin> can you please provide the pytorch model, which can reproduce this error? Otherwise its hard to debug the error. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#581 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AHINKO26V5E5WAGMSM5RQ23RZEH63ANCNFSM4OLRJ5WA> .

Guanbin-Huang · 2020-06-29T22:43:17Z

https://colab.research.google.com/drive/1hfv_Qbl6ZHDbXq_HB9bo3tV89KM7Skoq?usp=sharing This is the notebook where you can reproduce the bug. And you can download the pytorch model by clicking the shared link. It contains a zip file. https://drive.google.com/file/d/1etvQPPGlr4YxBEsCgOeduicErYN18BLg/view?usp=sharing All you need to do is just go through the notebook. Make sure the zip file is in the /content folder. The checkpoint(aka the pytorch model itself) is in the /AlignedReID-master/util/log if you need to access it.

…

On Mon, Jun 29, 2020 at 11:24 PM 黄冠斌 ***@***.***> wrote: no problem. I will do it right now. Give me a second. On Mon, Jun 29, 2020 at 11:23 PM Aseem Wadhwa ***@***.***> wrote: > @HuangGuanbin <https://github.com/huangguanbin> can you please provide > the pytorch model, which can reproduce this error? Otherwise its hard to > debug the error. > > — > You are receiving this because you were mentioned. > Reply to this email directly, view it on GitHub > <#581 (comment)>, > or unsubscribe > <https://github.com/notifications/unsubscribe-auth/AHINKO26V5E5WAGMSM5RQ23RZEH63ANCNFSM4OLRJ5WA> > . >

Guanbin-Huang · 2020-06-29T22:46:11Z

If you encountered any issue to run my code, plz let me know ASAP. I will reply to you on time.

aseemw · 2020-06-29T22:52:03Z

The colab is not accessible...

Guanbin-Huang · 2020-06-29T22:53:08Z

Is the zip accessible "*?*

…

On Mon, 29 Jun 2020 at 23:52, Aseem Wadhwa ***@***.***> wrote: The colab is not accessible... — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#581 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AHINKOZJCTOK4TH6Z3O5AVLRZELKBANCNFSM4OLRJ5WA> .

Guanbin-Huang · 2020-06-29T22:54:27Z

https://colab.research.google.com/drive/1hfv_Qbl6ZHDbXq_HB9bo3tV89KM7Skoq?usp=sharing try this one.

…

On Mon, Jun 29, 2020 at 11:52 PM 黄冠斌 ***@***.***> wrote: Is the zip accessible "*?* On Mon, 29 Jun 2020 at 23:52, Aseem Wadhwa ***@***.***> wrote: > The colab is not accessible... > > — > You are receiving this because you were mentioned. > Reply to this email directly, view it on GitHub > <#581 (comment)>, > or unsubscribe > <https://github.com/notifications/unsubscribe-auth/AHINKOZJCTOK4TH6Z3O5AVLRZELKBANCNFSM4OLRJ5WA> > . >

Guanbin-Huang · 2020-06-29T22:55:58Z

if it is not accessible again, copy the code below onto colab. !unzip AlignedReID-master.zip !pip install coremltools==4.0b1 %cd AlignedReID-master/ import torch from util.FeatureExtractor import FeatureExtractor from torchvision import transforms from IPython import embed import models from scipy.spatial.distance import cosine, euclidean from util.utils import * from sklearn.preprocessing import normalize def pool2d(tensor, type= 'max'): sz = tensor.size() if type == 'max': x = torch.nn.functional.max_pool2d(tensor, kernel_size=(int(sz[2]/8 ), sz[3])) if type == 'mean': x = torch.nn.functional.mean_pool2d(tensor, kernel_size=(int(sz[2]/8 ), sz[3])) x = x[0].cpu().data.numpy() x = np.transpose(x,(2,1,0))[0] return x if __name__ == '__main__': os.environ['CUDA_VISIBLE_DEVICES'] = "0" use_gpu = torch.cuda.is_available() if torch.cuda.is_available(): map_location = lambda storage, loc: storage.cuda() else: map_location = 'cpu' model = models.init_model(name='resnet50', num_classes=751, loss={ 'softmax', 'metric'}, use_gpu=use_gpu,aligned=True) checkpoint = torch.load( "/content/AlignedReID-master/util/log/checkpoint_ep300.pth.tar" , map_location=map_location) model.load_state_dict(checkpoint['state_dict']) model.eval() # Trace with random data example_input = torch.rand(1, 3, 256,128) traced_model = torch.jit.trace(model, example_input) traced_model.save("reid.pt") import coremltools as ct # Convert the saved PyTorch model to Core ML mlmodel = ct.convert("reid.pt", inputs=[ct.TensorType(shape=(1, 3, 256, 128))])

…

On Mon, Jun 29, 2020 at 11:54 PM 黄冠斌 ***@***.***> wrote: https://colab.research.google.com/drive/1hfv_Qbl6ZHDbXq_HB9bo3tV89KM7Skoq?usp=sharing try this one. On Mon, Jun 29, 2020 at 11:52 PM 黄冠斌 ***@***.***> wrote: > Is the zip accessible "*?* > > > On Mon, 29 Jun 2020 at 23:52, Aseem Wadhwa ***@***.***> > wrote: > >> The colab is not accessible... >> >> — >> You are receiving this because you were mentioned. >> Reply to this email directly, view it on GitHub >> <#581 (comment)>, >> or unsubscribe >> <https://github.com/notifications/unsubscribe-auth/AHINKOZJCTOK4TH6Z3O5AVLRZELKBANCNFSM4OLRJ5WA> >> . >> >

Guanbin-Huang · 2020-06-29T23:48:01Z

I changed the link of zip file by mistake. If you want to download it again. use this one. https://drive.google.com/file/d/1ufh5kndXMdWfKPRT85dDtEwhZ1MXnPg7/view?usp=sharing

Guanbin-Huang · 2020-06-30T00:14:11Z

I would appreciate it if you can also check how precise the conversion is. Because some say conversion leads to loss of precision. That means given same input matrix but get different output matrix. THANK YOU!!

…

On Mon, Jun 29, 2020 at 11:55 PM 黄冠斌 ***@***.***> wrote: if it is not accessible again, copy the code below onto colab. !unzip AlignedReID-master.zip !pip install coremltools==4.0b1 %cd AlignedReID-master/ import torch from util.FeatureExtractor import FeatureExtractor from torchvision import transforms from IPython import embed import models from scipy.spatial.distance import cosine, euclidean from util.utils import * from sklearn.preprocessing import normalize def pool2d(tensor, type= 'max'): sz = tensor.size() if type == 'max': x = torch.nn.functional.max_pool2d(tensor, kernel_size=(int(sz[2]/8 ), sz[3])) if type == 'mean': x = torch.nn.functional.mean_pool2d(tensor, kernel_size=(int(sz[2]/8 ), sz[3])) x = x[0].cpu().data.numpy() x = np.transpose(x,(2,1,0))[0] return x if __name__ == '__main__': os.environ['CUDA_VISIBLE_DEVICES'] = "0" use_gpu = torch.cuda.is_available() if torch.cuda.is_available(): map_location = lambda storage, loc: storage.cuda() else: map_location = 'cpu' model = models.init_model(name='resnet50', num_classes=751, loss={ 'softmax', 'metric'}, use_gpu=use_gpu,aligned=True) checkpoint = torch.load( "/content/AlignedReID-master/util/log/checkpoint_ep300.pth.tar" , map_location=map_location) model.load_state_dict(checkpoint['state_dict']) model.eval() # Trace with random data example_input = torch.rand(1, 3, 256,128) traced_model = torch.jit.trace(model, example_input) traced_model.save("reid.pt") import coremltools as ct # Convert the saved PyTorch model to Core ML mlmodel = ct.convert("reid.pt", inputs=[ct.TensorType(shape=(1, 3, 256, 128))]) On Mon, Jun 29, 2020 at 11:54 PM 黄冠斌 ***@***.***> wrote: > > https://colab.research.google.com/drive/1hfv_Qbl6ZHDbXq_HB9bo3tV89KM7Skoq?usp=sharing > try this one. > > On Mon, Jun 29, 2020 at 11:52 PM 黄冠斌 ***@***.***> wrote: > >> Is the zip accessible "*?* >> >> >> On Mon, 29 Jun 2020 at 23:52, Aseem Wadhwa ***@***.***> >> wrote: >> >>> The colab is not accessible... >>> >>> — >>> You are receiving this because you were mentioned. >>> Reply to this email directly, view it on GitHub >>> <#581 (comment)>, >>> or unsubscribe >>> <https://github.com/notifications/unsubscribe-auth/AHINKOZJCTOK4TH6Z3O5AVLRZELKBANCNFSM4OLRJ5WA> >>> . >>> >>

Guanbin-Huang · 2020-06-30T14:25:20Z

Any progress on this?

…

On Tue, 30 Jun 2020 at 01:13, 黄冠斌 ***@***.***> wrote: I would appreciate it if you can also check how precise the conversion is. Because some say conversion leads to loss of precision. That means given same input matrix but get different output matrix. THANK YOU!! On Mon, Jun 29, 2020 at 11:55 PM 黄冠斌 ***@***.***> wrote: > if it is not accessible again, copy the code below onto colab. > > !unzip AlignedReID-master.zip > !pip install coremltools==4.0b1 > > > > %cd AlignedReID-master/ > > > > import torch > from util.FeatureExtractor import FeatureExtractor > from torchvision import transforms > from IPython import embed > import models > from scipy.spatial.distance import cosine, euclidean > from util.utils import * > from sklearn.preprocessing import normalize > > def pool2d(tensor, type= 'max'): > sz = tensor.size() > if type == 'max': > x = torch.nn.functional.max_pool2d(tensor, kernel_size=(int(sz[2]/8 > ), sz[3])) > if type == 'mean': > x = torch.nn.functional.mean_pool2d(tensor, kernel_size=(int(sz[2]/ > 8), sz[3])) > x = x[0].cpu().data.numpy() > x = np.transpose(x,(2,1,0))[0] > return x > > if __name__ == '__main__': > os.environ['CUDA_VISIBLE_DEVICES'] = "0" > use_gpu = torch.cuda.is_available() > if torch.cuda.is_available(): > map_location = lambda storage, loc: storage.cuda() > else: > map_location = 'cpu' > > model = models.init_model(name='resnet50', num_classes=751, loss={ > 'softmax', 'metric'}, use_gpu=use_gpu,aligned=True) > > checkpoint = torch.load( > "/content/AlignedReID-master/util/log/checkpoint_ep300.pth.tar" > , map_location=map_location) > model.load_state_dict(checkpoint['state_dict']) > > model.eval() > > # Trace with random data > example_input = torch.rand(1, 3, 256,128) > traced_model = torch.jit.trace(model, example_input) > > traced_model.save("reid.pt") > import coremltools as ct > # Convert the saved PyTorch model to Core ML > mlmodel = ct.convert("reid.pt", > inputs=[ct.TensorType(shape=(1, 3, 256, 128))]) > > > On Mon, Jun 29, 2020 at 11:54 PM 黄冠斌 ***@***.***> wrote: > >> >> https://colab.research.google.com/drive/1hfv_Qbl6ZHDbXq_HB9bo3tV89KM7Skoq?usp=sharing >> try this one. >> >> On Mon, Jun 29, 2020 at 11:52 PM 黄冠斌 ***@***.***> wrote: >> >>> Is the zip accessible "*?* >>> >>> >>> On Mon, 29 Jun 2020 at 23:52, Aseem Wadhwa ***@***.***> >>> wrote: >>> >>>> The colab is not accessible... >>>> >>>> — >>>> You are receiving this because you were mentioned. >>>> Reply to this email directly, view it on GitHub >>>> <#581 (comment)>, >>>> or unsubscribe >>>> <https://github.com/notifications/unsubscribe-auth/AHINKOZJCTOK4TH6Z3O5AVLRZELKBANCNFSM4OLRJ5WA> >>>> . >>>> >>>

JialeHu · 2020-06-30T21:05:53Z

I had the same issue (TypeError: Input strides has type <class
'coremltools.converters.mil.mil.types.type_tensor.tensor..tensor'> not
compatible with expected type IntTensorInputType).
I am wondering if it is the issue related compatibility between coreML tensor and torch Tensor?

Guanbin-Huang · 2020-07-02T09:31:59Z

any progress?

quangphap208 · 2020-07-05T04:24:52Z

i had same issue:
TypeError: Input strides has type <class 'coremltools.converters.mil.mil.types.type_tensor.tensor..tensor'> not compatible with expected type IntTensorInputType

DawerG · 2020-07-05T16:58:01Z

Seems like the error message for type mismatch of input tensors is not very descriptive.
@quangphap208 @JialeHu Which models are you hitting this error on? Since type mismatch can happen in any model for different reasons. Some of the them might be bugs but others might be genuine errors. Therefore, this needs to investigated on a model basis.

DawerG · 2020-07-05T18:38:36Z

@HuangGuanbin Can you please re-convert your model after incorporating this following change?

Replace this line
strides = inputs[2]
in https://github.com/apple/coremltools/blob/e87f1d0d6ca1dc9cd812f14f777ead0bba70bf43/coremltools/converters/mil/frontend/torch/ops.py#L1421

with following code snippet

    strides = inputs[2]
    if strides.op.op_type == "const"  and (not strides.val):
        strides = mb.const(val=kernel_sizes.val, name=strides.name)

DawerG · 2020-07-05T18:46:30Z

Since this issue is not related to ONNX. For PyTorch related issues in the future, please use coremltools repository https://github.com/apple/coremltools.

DawerG · 2020-07-08T20:22:31Z

@HuangGuanbin This PR apple/coremltools#769 fixes the reported issue. Please verify if it solves your problem.

JialeHu · 2020-07-13T01:23:34Z

@HuangGuanbin This PR apple/coremltools#769 fixes the reported issue. Please verify if it solves your problem.

This solves the issue for me. Thanks a lot.

Guanbin-Huang · 2020-07-14T03:00:09Z

strides = inputs[2]
if strides.op.op_type == "const"  and (not strides.val):
    strides = mb.const(val=kernel_sizes.val, name=strides.name)

I tried what you said, but it is not working yet.

Guanbin-Huang · 2020-07-14T03:05:02Z

I checked the latest notification. But I'm not sure what i should modify.

Guanbin-Huang · 2020-07-14T03:05:17Z

@JialeHu

Guanbin-Huang added the question Response providing clarification needed. Will not be assigned to a release. (type) label Jun 29, 2020

aseemw added bug Unexpected behaviour that should be corrected (type) and removed question Response providing clarification needed. Will not be assigned to a release. (type) labels Jun 29, 2020

quangphap208 mentioned this issue Jul 5, 2020

Error while converting op of type: Slice. Error message: Input shape not available #551

Open

DawerG self-assigned this Jul 8, 2020

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

non-classifier case in coremltools4.0+ #581

non-classifier case in coremltools4.0+ #581

Guanbin-Huang commented Jun 29, 2020

aseemw commented Jun 29, 2020

Guanbin-Huang commented Jun 29, 2020

Guanbin-Huang commented Jun 29, 2020

Guanbin-Huang commented Jun 29, 2020

Guanbin-Huang commented Jun 29, 2020

Guanbin-Huang commented Jun 29, 2020 via email

aseemw commented Jun 29, 2020

Guanbin-Huang commented Jun 29, 2020 via email

Guanbin-Huang commented Jun 29, 2020 via email

Guanbin-Huang commented Jun 29, 2020

aseemw commented Jun 29, 2020

Guanbin-Huang commented Jun 29, 2020 via email

Guanbin-Huang commented Jun 29, 2020 via email

Guanbin-Huang commented Jun 29, 2020 via email

Guanbin-Huang commented Jun 29, 2020

Guanbin-Huang commented Jun 30, 2020 via email

Guanbin-Huang commented Jun 30, 2020 via email

JialeHu commented Jun 30, 2020

Guanbin-Huang commented Jul 2, 2020

quangphap208 commented Jul 5, 2020

DawerG commented Jul 5, 2020 •

edited

Loading

DawerG commented Jul 5, 2020 •

edited

Loading

DawerG commented Jul 5, 2020 •

edited

Loading

DawerG commented Jul 8, 2020

JialeHu commented Jul 13, 2020

Guanbin-Huang commented Jul 14, 2020

Guanbin-Huang commented Jul 14, 2020

Guanbin-Huang commented Jul 14, 2020

non-classifier case in coremltools4.0+ #581

non-classifier case in coremltools4.0+ #581

Comments

Guanbin-Huang commented Jun 29, 2020

❓Question

System Information

aseemw commented Jun 29, 2020

Guanbin-Huang commented Jun 29, 2020

Guanbin-Huang commented Jun 29, 2020

Guanbin-Huang commented Jun 29, 2020

Guanbin-Huang commented Jun 29, 2020

Guanbin-Huang commented Jun 29, 2020 via email

aseemw commented Jun 29, 2020

Guanbin-Huang commented Jun 29, 2020 via email

Guanbin-Huang commented Jun 29, 2020 via email

Guanbin-Huang commented Jun 29, 2020

aseemw commented Jun 29, 2020

Guanbin-Huang commented Jun 29, 2020 via email

Guanbin-Huang commented Jun 29, 2020 via email

Guanbin-Huang commented Jun 29, 2020 via email

Guanbin-Huang commented Jun 29, 2020

Guanbin-Huang commented Jun 30, 2020 via email

Guanbin-Huang commented Jun 30, 2020 via email

JialeHu commented Jun 30, 2020

Guanbin-Huang commented Jul 2, 2020

quangphap208 commented Jul 5, 2020

DawerG commented Jul 5, 2020 • edited Loading

DawerG commented Jul 5, 2020 • edited Loading

DawerG commented Jul 5, 2020 • edited Loading

DawerG commented Jul 8, 2020

JialeHu commented Jul 13, 2020

Guanbin-Huang commented Jul 14, 2020

Guanbin-Huang commented Jul 14, 2020

Guanbin-Huang commented Jul 14, 2020

DawerG commented Jul 5, 2020 •

edited

Loading

DawerG commented Jul 5, 2020 •

edited

Loading

DawerG commented Jul 5, 2020 •

edited

Loading