diff options
Diffstat (limited to 'src/notebooks/03a-line-prediction.ipynb')
| -rw-r--r-- | src/notebooks/03a-line-prediction.ipynb | 41 |
1 files changed, 27 insertions, 14 deletions
diff --git a/src/notebooks/03a-line-prediction.ipynb b/src/notebooks/03a-line-prediction.ipynb index 539fb6e..13f4ff1 100644 --- a/src/notebooks/03a-line-prediction.ipynb +++ b/src/notebooks/03a-line-prediction.ipynb @@ -32,34 +32,35 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 13, "metadata": {}, "outputs": [], "source": [ - "from text_recognizer.models import LineCTCModel\n", - "from text_recognizer.networks import LineRecurrentNetwork" + "from text_recognizer.models import CRNNModel\n", + "from text_recognizer.networks import ConvolutionalRecurrentNetwork" ] }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ - "2020-09-09 20:38:27.854 | DEBUG | text_recognizer.datasets.emnist_lines_dataset:_load_data:164 - EmnistLinesDataset loading data from HDF5...\n" + "2021-01-04 21:35:35.605 | DEBUG | text_recognizer.datasets.emnist_lines_dataset:_load_data:152 - EmnistLinesDataset loading data from HDF5...\n" ] } ], "source": [ - "emnist_lines = EmnistLinesDataset(train=False)" + "emnist_lines = EmnistLinesDataset(train=False)\n", + "emnist_lines.load_or_generate_data()" ] }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 9, "metadata": {}, "outputs": [], "source": [ @@ -69,7 +70,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 10, "metadata": {}, "outputs": [], "source": [ @@ -78,7 +79,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 11, "metadata": {}, "outputs": [ { @@ -87,7 +88,7 @@ "torch.Size([34])" ] }, - "execution_count": 7, + "execution_count": 11, "metadata": {}, "output_type": "execute_result" } @@ -98,14 +99,26 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 16, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ - "2020-09-01 23:37:30.291 | DEBUG | text_recognizer.models.base:load_weights:405 - Loading network with pretrained weights.\n" + "2021-01-04 21:37:05.918 | DEBUG | text_recognizer.models.base:load_weights:432 - Loading network with pretrained weights.\n" + ] + }, + { + "ename": "TypeError", + "evalue": "'NoneType' object is not subscriptable", + "output_type": "error", + "traceback": [ + "\u001b[0;31m----------------------------------------------------------------\u001b[0m", + "\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m<ipython-input-16-df17e62a822a>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 13\u001b[0m \u001b[0;34m\"patch_size\"\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;36m28\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m28\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 14\u001b[0m \"stride\": [1, 14],}\n\u001b[0;32m---> 15\u001b[0;31m \u001b[0mline_ctc_model\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mCRNNModel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"ConvolutionalRecurrentNetwork\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"IamLinesDataset\"\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m#, network_args)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", + "\u001b[0;32m~/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/text_recognizer/models/crnn_model.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, network_fn, dataset, network_args, dataset_args, metrics, criterion, criterion_args, optimizer, optimizer_args, lr_scheduler, lr_scheduler_args, swa_args, device)\u001b[0m\n\u001b[1;32m 49\u001b[0m )\n\u001b[1;32m 50\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 51\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpad_token\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdataset_args\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"args\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"pad_token\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 52\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_mapper\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 53\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_mapper\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mEmnistMapper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpad_token\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpad_token\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mTypeError\u001b[0m: 'NoneType' object is not subscriptable" ] } ], @@ -124,7 +137,7 @@ " \"num_classes\": 80,\n", " \"patch_size\": [28, 28],\n", " \"stride\": [1, 14],}\n", - "line_ctc_model = LineCTCModel(LineRecurrentNetwork, EmnistLinesDataset) #, network_args)" + "line_ctc_model = CRNNModel(\"ConvolutionalRecurrentNetwork\", \"IamLinesDataset\") #, network_args)" ] }, { @@ -398,7 +411,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.4" + "version": "3.8.2" } }, "nbformat": 4, |