Spaces:
Sleeping
Sleeping
| COLORS = [ | |
| [0.000, 0.447, 0.741], | |
| [0.850, 0.325, 0.098], | |
| [0.929, 0.694, 0.125], | |
| [0.494, 0.184, 0.556], | |
| [0.466, 0.674, 0.188], | |
| [0.301, 0.745, 0.933], | |
| [0.351, 0.760, 0.903], | |
| ] | |
| MODELS_DETAILS = { | |
| "DETR-RESNET-50": """DetrForObjectDetection( | |
| (model): DetrModel( | |
| (backbone): DetrConvModel( | |
| (conv_encoder): DetrConvEncoder( | |
| (model): FeatureListNet( | |
| (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False) | |
| (bn1): DetrFrozenBatchNorm2d() | |
| (act1): ReLU(inplace=True) | |
| (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False) | |
| (layer1): Sequential( | |
| (0): Bottleneck( | |
| (conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn1): DetrFrozenBatchNorm2d() | |
| (act1): ReLU(inplace=True) | |
| (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) | |
| (bn2): DetrFrozenBatchNorm2d() | |
| (drop_block): Identity() | |
| (act2): ReLU(inplace=True) | |
| (aa): Identity() | |
| (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn3): DetrFrozenBatchNorm2d() | |
| (act3): ReLU(inplace=True) | |
| (downsample): Sequential( | |
| (0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) | |
| ) | |
| ) | |
| (1): Bottleneck( | |
| (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn1): DetrFrozenBatchNorm2d() | |
| (act1): ReLU(inplace=True) | |
| (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) | |
| (bn2): DetrFrozenBatchNorm2d() | |
| (drop_block): Identity() | |
| (act2): ReLU(inplace=True) | |
| (aa): Identity() | |
| (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn3): DetrFrozenBatchNorm2d() | |
| (act3): ReLU(inplace=True) | |
| ) | |
| (2): Bottleneck( | |
| (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn1): DetrFrozenBatchNorm2d() | |
| (act1): ReLU(inplace=True) | |
| (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) | |
| (bn2): DetrFrozenBatchNorm2d() | |
| (drop_block): Identity() | |
| (act2): ReLU(inplace=True) | |
| (aa): Identity() | |
| (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn3): DetrFrozenBatchNorm2d() | |
| (act3): ReLU(inplace=True) | |
| ) | |
| ) | |
| (layer2): Sequential( | |
| (0): Bottleneck( | |
| (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn1): DetrFrozenBatchNorm2d() | |
| (act1): ReLU(inplace=True) | |
| (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) | |
| (bn2): DetrFrozenBatchNorm2d() | |
| (drop_block): Identity() | |
| (act2): ReLU(inplace=True) | |
| (aa): Identity() | |
| (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn3): DetrFrozenBatchNorm2d() | |
| (act3): ReLU(inplace=True) | |
| (downsample): Sequential( | |
| (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False) | |
| (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) | |
| ) | |
| ) | |
| (1): Bottleneck( | |
| (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn1): DetrFrozenBatchNorm2d() | |
| (act1): ReLU(inplace=True) | |
| (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) | |
| (bn2): DetrFrozenBatchNorm2d() | |
| (drop_block): Identity() | |
| (act2): ReLU(inplace=True) | |
| (aa): Identity() | |
| (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn3): DetrFrozenBatchNorm2d() | |
| (act3): ReLU(inplace=True) | |
| ) | |
| (2): Bottleneck( | |
| (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn1): DetrFrozenBatchNorm2d() | |
| (act1): ReLU(inplace=True) | |
| (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) | |
| (bn2): DetrFrozenBatchNorm2d() | |
| (drop_block): Identity() | |
| (act2): ReLU(inplace=True) | |
| (aa): Identity() | |
| (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn3): DetrFrozenBatchNorm2d() | |
| (act3): ReLU(inplace=True) | |
| ) | |
| (3): Bottleneck( | |
| (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn1): DetrFrozenBatchNorm2d() | |
| (act1): ReLU(inplace=True) | |
| (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) | |
| (bn2): DetrFrozenBatchNorm2d() | |
| (drop_block): Identity() | |
| (act2): ReLU(inplace=True) | |
| (aa): Identity() | |
| (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn3): DetrFrozenBatchNorm2d() | |
| (act3): ReLU(inplace=True) | |
| ) | |
| ) | |
| (layer3): Sequential( | |
| (0): Bottleneck( | |
| (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn1): DetrFrozenBatchNorm2d() | |
| (act1): ReLU(inplace=True) | |
| (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) | |
| (bn2): DetrFrozenBatchNorm2d() | |
| (drop_block): Identity() | |
| (act2): ReLU(inplace=True) | |
| (aa): Identity() | |
| (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn3): DetrFrozenBatchNorm2d() | |
| (act3): ReLU(inplace=True) | |
| (downsample): Sequential( | |
| (0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False) | |
| (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) | |
| ) | |
| ) | |
| (1): Bottleneck( | |
| (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn1): DetrFrozenBatchNorm2d() | |
| (act1): ReLU(inplace=True) | |
| (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) | |
| (bn2): DetrFrozenBatchNorm2d() | |
| (drop_block): Identity() | |
| (act2): ReLU(inplace=True) | |
| (aa): Identity() | |
| (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn3): DetrFrozenBatchNorm2d() | |
| (act3): ReLU(inplace=True) | |
| ) | |
| (2): Bottleneck( | |
| (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn1): DetrFrozenBatchNorm2d() | |
| (act1): ReLU(inplace=True) | |
| (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) | |
| (bn2): DetrFrozenBatchNorm2d() | |
| (drop_block): Identity() | |
| (act2): ReLU(inplace=True) | |
| (aa): Identity() | |
| (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn3): DetrFrozenBatchNorm2d() | |
| (act3): ReLU(inplace=True) | |
| ) | |
| (3): Bottleneck( | |
| (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn1): DetrFrozenBatchNorm2d() | |
| (act1): ReLU(inplace=True) | |
| (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) | |
| (bn2): DetrFrozenBatchNorm2d() | |
| (drop_block): Identity() | |
| (act2): ReLU(inplace=True) | |
| (aa): Identity() | |
| (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn3): DetrFrozenBatchNorm2d() | |
| (act3): ReLU(inplace=True) | |
| ) | |
| (4): Bottleneck( | |
| (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn1): DetrFrozenBatchNorm2d() | |
| (act1): ReLU(inplace=True) | |
| (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) | |
| (bn2): DetrFrozenBatchNorm2d() | |
| (drop_block): Identity() | |
| (act2): ReLU(inplace=True) | |
| (aa): Identity() | |
| (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn3): DetrFrozenBatchNorm2d() | |
| (act3): ReLU(inplace=True) | |
| ) | |
| (5): Bottleneck( | |
| (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn1): DetrFrozenBatchNorm2d() | |
| (act1): ReLU(inplace=True) | |
| (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) | |
| (bn2): DetrFrozenBatchNorm2d() | |
| (drop_block): Identity() | |
| (act2): ReLU(inplace=True) | |
| (aa): Identity() | |
| (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn3): DetrFrozenBatchNorm2d() | |
| (act3): ReLU(inplace=True) | |
| ) | |
| ) | |
| (layer4): Sequential( | |
| (0): Bottleneck( | |
| (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn1): DetrFrozenBatchNorm2d() | |
| (act1): ReLU(inplace=True) | |
| (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) | |
| (bn2): DetrFrozenBatchNorm2d() | |
| (drop_block): Identity() | |
| (act2): ReLU(inplace=True) | |
| (aa): Identity() | |
| (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn3): DetrFrozenBatchNorm2d() | |
| (act3): ReLU(inplace=True) | |
| (downsample): Sequential( | |
| (0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False) | |
| (1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) | |
| ) | |
| ) | |
| (1): Bottleneck( | |
| (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn1): DetrFrozenBatchNorm2d() | |
| (act1): ReLU(inplace=True) | |
| (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) | |
| (bn2): DetrFrozenBatchNorm2d() | |
| (drop_block): Identity() | |
| (act2): ReLU(inplace=True) | |
| (aa): Identity() | |
| (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn3): DetrFrozenBatchNorm2d() | |
| (act3): ReLU(inplace=True) | |
| ) | |
| (2): Bottleneck( | |
| (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn1): DetrFrozenBatchNorm2d() | |
| (act1): ReLU(inplace=True) | |
| (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) | |
| (bn2): DetrFrozenBatchNorm2d() | |
| (drop_block): Identity() | |
| (act2): ReLU(inplace=True) | |
| (aa): Identity() | |
| (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False) | |
| (bn3): DetrFrozenBatchNorm2d() | |
| (act3): ReLU(inplace=True) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (position_embedding): DetrSinePositionEmbedding() | |
| ) | |
| (input_projection): Conv2d(2048, 256, kernel_size=(1, 1), stride=(1, 1)) | |
| (query_position_embeddings): Embedding(100, 256) | |
| (encoder): DetrEncoder( | |
| (layers): ModuleList( | |
| (0-5): 6 x DetrEncoderLayer( | |
| (self_attn): DetrAttention( | |
| (k_proj): Linear(in_features=256, out_features=256, bias=True) | |
| (v_proj): Linear(in_features=256, out_features=256, bias=True) | |
| (q_proj): Linear(in_features=256, out_features=256, bias=True) | |
| (out_proj): Linear(in_features=256, out_features=256, bias=True) | |
| ) | |
| (self_attn_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) | |
| (activation_fn): ReLU() | |
| (fc1): Linear(in_features=256, out_features=2048, bias=True) | |
| (fc2): Linear(in_features=2048, out_features=256, bias=True) | |
| (final_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) | |
| ) | |
| ) | |
| ) | |
| (decoder): DetrDecoder( | |
| (layers): ModuleList( | |
| (0-5): 6 x DetrDecoderLayer( | |
| (self_attn): DetrAttention( | |
| (k_proj): Linear(in_features=256, out_features=256, bias=True) | |
| (v_proj): Linear(in_features=256, out_features=256, bias=True) | |
| (q_proj): Linear(in_features=256, out_features=256, bias=True) | |
| (out_proj): Linear(in_features=256, out_features=256, bias=True) | |
| ) | |
| (activation_fn): ReLU() | |
| (self_attn_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) | |
| (encoder_attn): DetrAttention( | |
| (k_proj): Linear(in_features=256, out_features=256, bias=True) | |
| (v_proj): Linear(in_features=256, out_features=256, bias=True) | |
| (q_proj): Linear(in_features=256, out_features=256, bias=True) | |
| (out_proj): Linear(in_features=256, out_features=256, bias=True) | |
| ) | |
| (encoder_attn_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) | |
| (fc1): Linear(in_features=256, out_features=2048, bias=True) | |
| (fc2): Linear(in_features=2048, out_features=256, bias=True) | |
| (final_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) | |
| ) | |
| ) | |
| (layernorm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) | |
| ) | |
| ) | |
| (class_labels_classifier): Linear(in_features=256, out_features=2, bias=True) | |
| (bbox_predictor): DetrMLPPredictionHead( | |
| (layers): ModuleList( | |
| (0-1): 2 x Linear(in_features=256, out_features=256, bias=True) | |
| (2): Linear(in_features=256, out_features=4, bias=True) | |
| ) | |
| ) | |
| )""" | |
| } | |