aimet-model-zoo icon indicating copy to clipboard operation
aimet-model-zoo copied to clipboard

Results 19 aimet-model-zoo issues
Sort by recently updated
recently updated
newest added

Is the link https://deepai.org/dataset/set14-super-resolution already out of dates?

Use the gpt2 model, and test the quantification accuracy. model download: https://github.com/quic/aimet-model-zoo/releases/download/torch_gpt2/gpt2_wikitext_finetune.tar.gz test data:wikitext-2-raw-v1, Item | Description -- | -- AIMET | 1.28.0 Linux kernel | 20.04 cuda | 11.6...

Currently the code [1](https://github.com/quic/aimet-model-zoo/blob/74731808045ac83542cb899f915917c9bab185ce/aimet_zoo_torch/resnet/evaluator/resnet_quanteval.py#L25) uses ```python parser.add_argument('--use-cuda', help='Use cuda', default=True, type=bool) ``` to parse the CLI parameters. The [documentation](https://github.com/quic/aimet-model-zoo/blob/74731808045ac83542cb899f915917c9bab185ce/aimet_zoo_torch/resnet/ResNet.md?plain=1#L53) mentions that this CLI flag should be used to tell the...

The released wheels do not specify any dependencies even though the code relies on modules outside the standard library. For example [image_net_data_loader.py](https://github.com/quic/aimet-model-zoo/blob/74731808045ac83542cb899f915917c9bab185ce/aimet_zoo_torch/common/utils/image_net_data_loader.py#L17C6-L17C17) requires `torch` and `torchvision`. Also there are dependencies...

Hi,we use the following code ``` from aimet_tensorflow.keras.quantsim import QuantizationSimModel from aimet_common.defs import QuantScheme sim = QuantizationSimModel(model=model, quant_scheme=QuantScheme.post_training_tf, rounding_mode="nearest", default_output_bw=8, default_param_bw=8) ``` The tf.matmul operator in the model is not...

I used aimet-model-zoo vit demo(vit_quanteval.py),and export the quanted model with json to onnx;And I use snpe-onnx-to-dlc(v2.10),but errors ![image](https://github.com/quic/aimet-model-zoo/assets/23204271/2c73fe90-3091-41c8-a30f-4ea46b2494a9)

Can I adjust the resolution of the super resolution algorithms to 640x480 instead of 128x128?

Implementations of the functions called inside QuickSRNetBase.to_dcr() are not available [ref](https://github.com/quic/aimet-model-zoo/blob/d09d2b0404d10f71a7640a87e9d5e5257b028802/aimet_zoo_torch/quicksrnet/model/models.py#L303). Can you please provide code for these ? Also curious if any unit tests were run before merging. Hoping...