Category : transfer-learning

I’m training my model on around 4000 Chest X-Ray images using Transfer Learning (EfficientNet B1). The training is as follows: Epoch 1/10 99/99 [==============================] – 1437s 14s/step – loss: 0.6446 – accuracy: 0.8617 – val_loss: 0.3128 – val_accuracy: 0.9178 Epoch 2/10 99/99 [==============================] – 193s 2s/step – loss: 0.2179 – accuracy: 0.9356 – val_loss: 0.4521 ..

Read more

I am training an image classification model on sagemaker with input data configurations as: Train test split is 70-30 15 classes with data sizes in test ranging from 40-3000. For train, the class sample sizes range from 100-7000. Model configurations for training in sagemaker are: num_layers = 18 image_shape = "3,700,800" num_classes = class_count mini_batch_size ..

Read more

I’m implementing PyTorch’s transfer learning tutorial to classify images to three classes. I want to enhance/improve the tutorial’s code to plot the training and validation losses overtime but not sure how to do it. The tutorial code is here https://pytorch.org/tutorials/beginner/transfer_learning_tutorial.html I think, somewhere in this code block, I need to plot the graph. def train_model(model, ..

Read more

ValueError: Graph disconnected: cannot obtain value for tensor Tensor("input_1:0", shape=(None, 288, 288, 3), dtype=float32) at layer "stem_conv". The following previous layers were accessed without issue: [] I’m using github/qubvel efficientnet and segmentation_networks implementations, and trying to connect the last bilinear upsize layer to efficientnet via a conv2d layer. but I get the above error. Here ..

Read more