Update finetune detail, rerun model doc gen.

Author: rwightman

docs/models/.templates/code_snippets.md

@@ -56,7 +56,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('{{ model_name }}', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('{{ model_name }}', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/adversarial-inception-v3.md

@@ -64,7 +64,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('adv_inception_v3', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('adv_inception_v3', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/advprop.md

@@ -62,7 +62,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('tf_efficientnet_b0_ap', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('tf_efficientnet_b0_ap', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/big-transfer.md

@@ -60,7 +60,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('resnetv2_101x1_bitm', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('resnetv2_101x1_bitm', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/csp-darknet.md

@@ -62,7 +62,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('cspdarknet53', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('cspdarknet53', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/csp-resnet.md

@@ -60,7 +60,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('cspresnet50', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('cspresnet50', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/csp-resnext.md

@@ -60,7 +60,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('cspresnext50', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('cspresnext50', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/densenet.md

@@ -62,7 +62,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('densenet121', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('densenet121', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/dla.md

@@ -62,7 +62,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('dla102', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('dla102', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/dpn.md

@@ -62,7 +62,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('dpn107', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('dpn107', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/ecaresnet.md

@@ -60,7 +60,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('ecaresnet101d', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('ecaresnet101d', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/efficientnet-pruned.md

@@ -66,7 +66,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('efficientnet_b1_pruned', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('efficientnet_b1_pruned', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/efficientnet.md

@@ -64,7 +64,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('efficientnet_b0', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('efficientnet_b0', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/ensemble-adversarial.md

@@ -64,7 +64,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('ens_adv_inception_resnet_v2', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('ens_adv_inception_resnet_v2', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/ese-vovnet.md

@@ -62,7 +62,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('ese_vovnet19b_dw', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('ese_vovnet19b_dw', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/fbnet.md

@@ -62,7 +62,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('fbnetc_100', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('fbnetc_100', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/gloun-inception-v3.md

@@ -62,7 +62,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('gluon_inception_v3', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('gluon_inception_v3', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/gloun-resnet.md

@@ -62,7 +62,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('gluon_resnet101_v1b', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('gluon_resnet101_v1b', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/gloun-resnext.md

@@ -62,7 +62,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('gluon_resnext101_32x4d', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('gluon_resnext101_32x4d', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/gloun-senet.md

@@ -62,7 +62,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('gluon_senet154', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('gluon_senet154', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/gloun-seresnext.md

@@ -62,7 +62,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('gluon_seresnext101_32x4d', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('gluon_seresnext101_32x4d', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/gloun-xception.md

@@ -62,7 +62,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('gluon_xception65', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('gluon_xception65', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/hrnet.md

@@ -60,7 +60,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('hrnet_w18', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('hrnet_w18', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/ig-resnext.md

@@ -64,7 +64,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('ig_resnext101_32x16d', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('ig_resnext101_32x16d', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/inception-resnet-v2.md

@@ -60,7 +60,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('inception_resnet_v2', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('inception_resnet_v2', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/inception-v3.md

@@ -60,7 +60,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('inception_v3', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('inception_v3', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/inception-v4.md

@@ -59,7 +59,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('inception_v4', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('inception_v4', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/legacy-se-resnet.md

@@ -60,7 +60,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('legacy_seresnet101', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('legacy_seresnet101', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/legacy-se-resnext.md

@@ -60,7 +60,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('legacy_seresnext101_32x4d', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('legacy_seresnext101_32x4d', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/legacy-senet.md

@@ -62,7 +62,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('legacy_senet154', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('legacy_senet154', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/mixnet.md

@@ -60,7 +60,7 @@ To extract image features with this model, follow the [timm feature extraction e
 ## How do I finetune this model?
 You can finetune any of the pre-trained models just by changing the classifier (the last layer).
 ```python
-model = timm.create_model('mixnet_l', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
+model = timm.create_model('mixnet_l', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
 ```
 To finetune on your own dataset, you have to write a training loop or adapt [timm's training
 script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.