pytorch-image-models

pytorch-image-models copied to clipboard

from torchvision.models.feature_extraction import create_feature_extractor import random import seaborn as sns import matplotlib.pyplot as plt return_nodes = ['blocks.0', 'blocks.10', 'blocks.20', 'blocks.23'] feat_ext = create_feature_extractor(model, return_nodes=return_nodes) with torch.no_grad(): out = feat_ext(inps[0]) fig,...

ratom

writing 'train.log' by default

1

During my use, the training log cannot be written by default, and the output path must be specified. However, this function can be easily realized by changing the setup order...

hova88

tf_efficientnet_b0_ap model was removed but is still in the doc

2

**Describe the bug** A clear and concise description of what the bug is. tf_efficientnet_b0_ap model was removed in https://github.com/rwightman/pytorch-image-models/commit/6a01101905e78007e5396f5ffdaae0c4725ba72c#diff-27c2bbd967991cbb5264f93cb5da34895fdab02424b2cc8c63d3d0768e65d47aL1833, but is still in doc https://github.com/rwightman/pytorch-image-models/blob/6a01101905e78007e5396f5ffdaae0c4725ba72c/docs/models/advprop.md#how-do-i-use-this-model-on-an-image **To Reproduce** Steps to reproduce...

xwang233

[BUG] Feature extraction and gradient checkpointing

1

In models with feature extraction that use FeatureListNet, trying to enable gradient checkpointing results in an error. **To Reproduce** Steps to reproduce the behavior: 1. Start Google Colab 2. Run...

fffffgggg54

[FEATURE] Script to convert weight from Jax to PyTorch

6

**Is your feature request related to a problem? Please describe.** I am trying to create multiple checkpoints of ViT at different iterations. Are there any systematic way to perform such...

yazdanbakhsh

[FEATURE] BEIT pre-training model

2

**Is your feature request related to a problem? Please describe.** There is no problem or bug **Describe the solution you'd like** I would like the implementation of BEIT pre-training pipeline...

lorenzbaraldi

[BUG] ViT ImageNet1K weights

2

**Describe the bug** In Version: 0.5.4 for example, dose vit_tiny_patch16_224 means vit_tiny trained from scratch on ImageNet1K? However, in the current Version 0.6, vit_tiny_patch16_224 means vit_tiny pretrained on 21k and...

hellojialee

When creating a model using `timm.create_model(arch, pretrained=True, in_chans=1, num_classes=1)`, single-channel input images can be used with `tf_efficientnet_b2_ns`, but not `efficientnet_b3_pruned`. The pruned models result in the following error: ``` File...

jphdotam

[Feature] Make (non `rmlp`) MaxxViT to support variable resolution

1

Dear rwightman, thanks for you job. I was going to input a tensor with size (16,3 112,112) to test the MaxxViT small 224 model， but it failed . do you...

mywebinfo65536

Gradient accumulation included into training script

1

Added parameter 'iters_to_accumulate' to perform [gradient accumulation](https://pytorch.org/docs/stable/notes/amp_examples.html#working-with-scaled-gradients) during training.

lorenzbaraldi