Add model

README.md

@@ -0,0 +1,191 @@
+---
+tags:
+- image-classification
+- timm
+library_name: timm
+license: apache-2.0
+datasets:
+- imagenet-1k
+---
+# Model card for lamhalobotnet50ts_256.a1h_in1k
+
+A Lambda+Halo+BoTNet image classification model (based on ResNet architecture). Trained on ImageNet-1k in `timm` by Ross Wightman.
+
+NOTE: this model did not adhere to any specific paper configuration, it was tuned for reasonable training times and reduced frequency of self-attention blocks.
+
+Recipe details:
+ * Based on [ResNet Strikes Back](https://arxiv.org/abs/2110.00476) `A1` recipe
+ * LAMB optimizer
+ * Stronger dropout, stochastic depth, and RandAugment than paper `A1` recipe
+ * Cosine LR schedule with warmup
+
+This model architecture is implemented using `timm`'s flexible [BYOBNet (Bring-Your-Own-Blocks Network)](https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/byobnet.py).
+
+BYOB (with BYOANet attention specific blocks) allows configuration of:
+ * block / stage layout
+ * block-type interleaving
+ * stem layout
+ * output stride (dilation)
+ * activation and norm layers
+ * channel and spatial / self-attention layers
+
+...and also includes `timm` features common to many other architectures, including:
+ * stochastic depth
+ * gradient checkpointing
+ * layer-wise LR decay
+ * per-stage feature extraction
+
+
+## Model Details
+- **Model Type:** Image classification / feature backbone
+- **Model Stats:**
+  - Params (M): 22.6
+  - GMACs: 5.0
+  - Activations (M): 18.4
+  - Image size: 256 x 256
+- **Papers:**
+  - LambdaNetworks: Modeling Long-Range Interactions Without Attention: https://arxiv.org/abs/2102.08602
+  - Scaling Local Self-Attention for Parameter Efficient Visual Backbones: https://arxiv.org/abs/2103.12731
+  - Bottleneck Transformers for Visual Recognition: https://arxiv.org/abs/2101.11605
+  - ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476
+- **Dataset:** ImageNet-1k
+
+## Model Usage
+### Image Classification
+```python
+from urllib.request import urlopen
+from PIL import Image
+import timm
+
+img = Image.open(urlopen(
+    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
+))
+
+model = timm.create_model('lamhalobotnet50ts_256.a1h_in1k', pretrained=True)
+model = model.eval()
+
+# get model specific transforms (normalization, resize)
+data_config = timm.data.resolve_model_data_config(model)
+transforms = timm.data.create_transform(**data_config, is_training=False)
+
+output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1
+
+top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
+```
+
+### Feature Map Extraction
+```python
+from urllib.request import urlopen
+from PIL import Image
+import timm
+
+img = Image.open(urlopen(
+    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
+))
+
+model = timm.create_model(
+    'lamhalobotnet50ts_256.a1h_in1k',
+    pretrained=True,
+    features_only=True,
+)
+model = model.eval()
+
+# get model specific transforms (normalization, resize)
+data_config = timm.data.resolve_model_data_config(model)
+transforms = timm.data.create_transform(**data_config, is_training=False)
+
+output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1
+
+for o in output:
+    # print shape of each feature map in output
+    # e.g.:
+    #  torch.Size([1, 32, 128, 128])
+    #  torch.Size([1, 256, 64, 64])
+    #  torch.Size([1, 512, 32, 32])
+    #  torch.Size([1, 1024, 16, 16])
+    #  torch.Size([1, 2048, 8, 8])
+
+    print(o.shape)
+```
+
+### Image Embeddings
+```python
+from urllib.request import urlopen
+from PIL import Image
+import timm
+
+img = Image.open(urlopen(
+    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
+))
+
+model = timm.create_model(
+    'lamhalobotnet50ts_256.a1h_in1k',
+    pretrained=True,
+    num_classes=0,  # remove classifier nn.Linear
+)
+model = model.eval()
+
+# get model specific transforms (normalization, resize)
+data_config = timm.data.resolve_model_data_config(model)
+transforms = timm.data.create_transform(**data_config, is_training=False)
+
+output = model(transforms(img).unsqueeze(0))  # output is (batch_size, num_features) shaped tensor
+
+# or equivalently (without needing to set num_classes=0)
+
+output = model.forward_features(transforms(img).unsqueeze(0))
+# output is unpooled, a (1, 2048, 8, 8) shaped tensor
+
+output = model.forward_head(output, pre_logits=True)
+# output is a (1, num_features) shaped tensor
+```
+
+## Model Comparison
+Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
+
+## Citation
+```bibtex
+@misc{rw2019timm,
+  author = {Ross Wightman},
+  title = {PyTorch Image Models},
+  year = {2019},
+  publisher = {GitHub},
+  journal = {GitHub repository},
+  doi = {10.5281/zenodo.4414861},
+  howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
+}
+```
+```bibtex
+@article{Bello2021LambdaNetworksML,
+  title={LambdaNetworks: Modeling Long-Range Interactions Without Attention},
+  author={Irwan Bello},
+  journal={ArXiv},
+  year={2021},
+  volume={abs/2102.08602}
+}
+```
+```bibtex
+@article{Vaswani2021ScalingLS,
+  title={Scaling Local Self-Attention for Parameter Efficient Visual Backbones},
+  author={Ashish Vaswani and Prajit Ramachandran and A. Srinivas and Niki Parmar and Blake A. Hechtman and Jonathon Shlens},
+  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
+  year={2021},
+  pages={12889-12899}
+}
+```
+```bibtex
+@article{Srinivas2021BottleneckTF,
+  title={Bottleneck Transformers for Visual Recognition},
+  author={A. Srinivas and Tsung-Yi Lin and Niki Parmar and Jonathon Shlens and P. Abbeel and Ashish Vaswani},
+  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
+  year={2021},
+  pages={16514-16524}
+}
+```
+```bibtex
+@inproceedings{wightman2021resnet,
+  title={ResNet strikes back: An improved training procedure in timm},
+  author={Wightman, Ross and Touvron, Hugo and Jegou, Herve},
+  booktitle={NeurIPS 2021 Workshop on ImageNet: Past, Present, and Future}
+}
+```

config.json

@@ -0,0 +1,40 @@
+{
+  "architecture": "lamhalobotnet50ts_256",
+  "num_classes": 1000,
+  "num_features": 2048,
+  "pretrained_cfg": {
+    "tag": "a1h_in1k",
+    "custom_load": false,
+    "input_size": [
+      3,
+      256,
+      256
+    ],
+    "min_input_size": [
+      3,
+      224,
+      224
+    ],
+    "fixed_input_size": true,
+    "interpolation": "bicubic",
+    "crop_pct": 0.95,
+    "crop_mode": "center",
+    "mean": [
+      0.485,
+      0.456,
+      0.406
+    ],
+    "std": [
+      0.229,
+      0.224,
+      0.225
+    ],
+    "num_classes": 1000,
+    "pool_size": [
+      8,
+      8
+    ],
+    "first_conv": "stem.conv1.conv",
+    "classifier": "head.fc"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9a8238bba6caee41459062af11610701b0c0d61be195e059a0df24b0b765277
+size 90531036

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fd62f985cdbb7bb40e075d0d2dd458b3a350adb47812dc9039f9f3cf64e82cd
+size 90626633